feat: scopist skill package v0.1.0

2026-08-14 18:40:03 +02:00
commit 3dafcaae3a
9 changed files with 1124 additions and 0 deletions
--- a/PROVENANCE.md
+++ b/PROVENANCE.md
@@ -0,0 +1,31 @@
+# Data provenance — scopist
+
+Where the content of this skill package comes from, counted by
+content items (tasks, competences, tools, evidence entries, curated
+knowledge). Rendered live by Gitea:
+
+```mermaid
+%%{init: {'theme':'base','themeVariables':{'pie1':'#f9a825','pie2':'#1e88e5','pie3':'#ff355e','pie4':'#d97757','pie5':'#8e24aa','pieOuterStrokeWidth':'0px','pieSectionTextColor':'#fff'}}}%%
+pie showData
+    title Content sources — scopist
+    "ESCO (occupation & competences)" : 28
+    "O*NET (tasks & tools)" : 138
+    "Job boards (market evidence)" : 36
+    "Anthropic official Claude skills" : 5
+    "External AI skill packs (mapped)" : 195
+```
+
+| Source | Items | Share | Files |
+|---|---|---|---|
+| ESCO (occupation & competences) | 28 | 7.0 % | references/profile.md, references/skills.md |
+| O*NET (tasks & tools) | 138 | 34.3 % | references/tasks.md, references/tools.md |
+| Job boards (market evidence) | 36 | 9.0 % | references/market.md (full report) + "Market evidence" headline sections |
+| Wikipedia & AI expert curation | 0 | 0.0 % | glossary, literature, usecases, intake, quality, evals/ |
+| Anthropic official Claude skills | 5 | 1.2 % | references/ai-skills.md, section "anthropics/skills" (official Claude Code skills) |
+| External AI skill packs (mapped) | 195 | 48.5 % | references/ai-skills.md (per-source attribution inside) |
+| Stack Exchange practitioner Q&A (CC-BY-SA) | 0 | 0.0 % | references/practitioner-qa.md (per-entry attribution inside) |
+
+Licensing: O*NET (USDOL/ETA, CC BY 4.0) · ESCO (© European Union) ·
+job-ad evidence via official APIs (JSearch/Adzuna) · Wikipedia content
+paraphrased with source URLs — never copied · external AI skills are
+linked, not copied (Apache-2.0/MIT/source-available, see ai-skills.md).
--- a/SKILL.md
+++ b/SKILL.md
@@ -0,0 +1,51 @@
+---
+name: scopist
+description: "Occupational skill for the role 'scopist' (also: freelance scopist). Use when the user asks for typical scopist work such as: typical scopist responsibilities"
+---
+
+# Scopist
+
+Scopists edit the transcripts created by court reporters in order to make of them a readable professional legal document. They listen or read to the reports given to them in order to apply punctuation, missing words, format, and improve the accuracy of the document.
+
+## Core workflow
+
+
+## How to use this skill
+
+- Read [references/profile.md](references/profile.md) for the occupation profile and scope.
+- Consult [references/tasks.md](references/tasks.md) for the full task and activity inventory.
+- Check [references/skills.md](references/skills.md) for essential vs. optional competences.
+- Check [references/tools.md](references/tools.md) for the software commonly used in this role.
+- See [references/ai-skills.md](references/ai-skills.md) — matched external AI agent skills (per-source attribution).
+
+## Key competences (essential)
+
+- apply grammar and spelling rules
+- grammar
+- legal terminology
+- observe confidentiality
+- provide written content
+- spelling
+- stenography
+- study court hearings
+- transcription methods
+- type error-free documents
+- type texts from audio sources
+- use dictionaries
+- use free typing techniques
+
+## Hot technologies
+
+- Adobe Acrobat
+- Adobe Illustrator
+- Adobe InDesign
+- Adobe Photoshop
+- Apple macOS
+- Cisco Webex
+- Facebook
+- Google Docs
+- Google Workspace software
+- Intuit QuickBooks
+
+---
+*Sources: ESCO v1.2.1 (http://data.europa.eu/esco/occupation/42c769cd-4c60-4bac-94d2-29a492b82b74), O*NET 30.3 (43-6011.00, manual nearest match). See manifest.json for licensing/attribution.*
--- a/manifest.json
+++ b/manifest.json
@@ -0,0 +1,310 @@
+{
+  "name": "scopist",
+  "title": "scopist",
+  "version": "0.1.0",
+  "layer": "core",
+  "language": "en",
+  "generated": "2026-07-07",
+  "ids": {
+    "esco_uri": "http://data.europa.eu/esco/occupation/42c769cd-4c60-4bac-94d2-29a492b82b74",
+    "esco_code": "3343.5",
+    "isco_group": "3343",
+    "onet_soc": "43-6011.00",
+    "crosswalk_match": "manual nearest via ISCO 3343 (Executive Secretaries and Executive Administrative Assistants)"
+  },
+  "sources": [
+    {
+      "name": "ESCO",
+      "version": "1.2.1",
+      "url": "https://esco.ec.europa.eu/"
+    },
+    {
+      "name": "O*NET",
+      "version": "30.3",
+      "url": "https://www.onetcenter.org/",
+      "license": "CC BY 4.0"
+    }
+  ],
+  "attribution": "This package includes information from the O*NET Database (v30.3) by the U.S. Department of Labor, Employment and Training Administration (USDOL/ETA), CC BY 4.0. skillfactor is not endorsed by USDOL/ETA. ESCO data (v1.2.1) (c) European Union, used per the ESCO download conditions: https://esco.ec.europa.eu/en/use-esco/download",
+  "counts": {
+    "tasks": 0,
+    "dwas": 0,
+    "skills_essential": 13,
+    "skills_optional": 14,
+    "software": 0
+  },
+  "enrichment_ai_skills": {
+    "generated": "2026-07-14",
+    "method": "deterministic mapping (ISCO prefix + title/competence keywords)",
+    "sources": {
+      "anthropics/skills": {
+        "repo": "https://github.com/anthropics/skills",
+        "commit": "f6656c1",
+        "license": "Apache-2.0; the document skills (docx/pdf/pptx/xlsx) are source-available \u2014 see the LICENSE.txt in the upstream skill folder",
+        "skills": 2
+      },
+      "NoizAI/skills": {
+        "repo": "https://github.com/NoizAI/skills",
+        "commit": "2a0e09d",
+        "license": "no explicit license \u2014 referenced by link only",
+        "skills": 1
+      },
+      "silverstein/minutes": {
+        "repo": "https://github.com/silverstein/minutes",
+        "commit": "3fb2e83",
+        "license": "MIT",
+        "skills": 2
+      },
+      "vibeeval/vibecosystem": {
+        "repo": "https://github.com/vibeeval/vibecosystem",
+        "commit": "cea9462",
+        "license": "MIT",
+        "skills": 2
+      },
+      "fcakyon/claude-codex-settings": {
+        "repo": "https://github.com/fcakyon/claude-codex-settings",
+        "commit": "44b7c00",
+        "license": "Apache-2.0",
+        "skills": 2
+      },
+      "foryourhealth111-pixel/Vibe-Skills": {
+        "repo": "https://github.com/foryourhealth111-pixel/Vibe-Skills",
+        "commit": "34429a8",
+        "license": "Apache-2.0",
+        "skills": 5
+      },
+      "davila7/claude-code-templates": {
+        "repo": "https://github.com/davila7/claude-code-templates",
+        "commit": "fa79251",
+        "license": "MIT",
+        "skills": 6
+      },
+      "davepoon/buildwithclaude": {
+        "repo": "https://github.com/davepoon/buildwithclaude",
+        "commit": "3c94e0c",
+        "license": "MIT",
+        "skills": 3
+      },
+      "snyk/agent-scan": {
+        "repo": "https://github.com/snyk/agent-scan",
+        "commit": "f3a4621",
+        "license": "Apache-2.0",
+        "skills": 3
+      },
+      "ThinkInAIXYZ/deepchat": {
+        "repo": "https://github.com/ThinkInAIXYZ/deepchat",
+        "commit": "f275c92",
+        "license": "Apache-2.0",
+        "skills": 3
+      },
+      "brycewang-stanford/Auto-Empirical-Research-Skills": {
+        "repo": "https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills",
+        "commit": "85bf545",
+        "license": "CC-BY-4.0",
+        "skills": 4
+      },
+      "mukul975/Anthropic-Cybersecurity-Skills": {
+        "repo": "https://github.com/mukul975/Anthropic-Cybersecurity-Skills",
+        "commit": "673da1f",
+        "license": "Apache-2.0",
+        "skills": 3
+      },
+      "mohitagw15856/pm-claude-skills": {
+        "repo": "https://github.com/mohitagw15856/pm-claude-skills",
+        "commit": "876fa30",
+        "license": "MIT",
+        "skills": 3
+      },
+      "nexu-io/open-design": {
+        "repo": "https://github.com/nexu-io/open-design",
+        "commit": "4b66023",
+        "license": "Apache-2.0",
+        "skills": 2
+      },
+      "AlpacaLabsLLC/skills-for-architects": {
+        "repo": "https://github.com/AlpacaLabsLLC/skills-for-architects",
+        "commit": "4476576",
+        "license": "MIT",
+        "skills": 2
+      },
+      "ComPDFKit/compdf-skills": {
+        "repo": "https://github.com/ComPDFKit/compdf-skills",
+        "commit": "b77153e",
+        "license": "no explicit license \u2014 referenced by link only",
+        "skills": 1
+      },
+      "rameerez/claude-code-startup-skills": {
+        "repo": "https://github.com/rameerez/claude-code-startup-skills",
+        "commit": "410f81f",
+        "license": "MIT",
+        "skills": 1
+      },
+      "affaan-m/everything-claude-code": {
+        "repo": "https://github.com/affaan-m/everything-claude-code",
+        "commit": "ed38744",
+        "license": "MIT",
+        "skills": 1
+      },
+      "infrasity-labs/dev-gtm-claude-skills": {
+        "repo": "https://github.com/infrasity-labs/dev-gtm-claude-skills",
+        "commit": "02cfefb",
+        "license": "MIT",
+        "skills": 2
+      },
+      "jeremylongshore/claude-code-plugins-plus-skills": {
+        "repo": "https://github.com/jeremylongshore/claude-code-plugins-plus-skills",
+        "commit": "e112938a",
+        "license": "MIT",
+        "skills": 12
+      },
+      "pedrohcgs/claude-code-my-workflow": {
+        "repo": "https://github.com/pedrohcgs/claude-code-my-workflow",
+        "commit": "be53c12",
+        "license": "MIT",
+        "skills": 1
+      },
+      "microsoft/skills": {
+        "repo": "https://github.com/microsoft/skills",
+        "commit": "dc543aa",
+        "license": "MIT",
+        "skills": 1
+      },
+      "K-Dense-AI/claude-scientific-skills": {
+        "repo": "https://github.com/K-Dense-AI/claude-scientific-skills",
+        "commit": "4d97e29",
+        "license": "MIT",
+        "skills": 1
+      },
+      "K-Dense-AI/scientific-agent-skills": {
+        "repo": "https://github.com/K-Dense-AI/scientific-agent-skills",
+        "commit": "4d97e29",
+        "license": "MIT",
+        "skills": 1
+      },
+      "egorfedorov/claude-context-optimizer": {
+        "repo": "https://github.com/egorfedorov/claude-context-optimizer",
+        "commit": "c604d3a",
+        "license": "MIT",
+        "skills": 1
+      },
+      "a5c-ai/babysitter": {
+        "repo": "https://github.com/a5c-ai/babysitter",
+        "commit": "44a5d58b",
+        "license": "MIT",
+        "skills": 1
+      },
+      "hoangsonww/Claude-Code-Agent-Monitor": {
+        "repo": "https://github.com/hoangsonww/Claude-Code-Agent-Monitor",
+        "commit": "8f87ce1",
+        "license": "MIT",
+        "skills": 1
+      },
+      "feiskyer/claude-code-settings": {
+        "repo": "https://github.com/feiskyer/claude-code-settings",
+        "commit": "0eb042a",
+        "license": "MIT",
+        "skills": 1
+      },
+      "michalparkola/tapestry-skills-for-claude-code": {
+        "repo": "https://github.com/michalparkola/tapestry-skills-for-claude-code",
+        "commit": "80e1dc5",
+        "license": "MIT",
+        "skills": 1
+      },
+      "transloadit/skills": {
+        "repo": "https://github.com/transloadit/skills",
+        "commit": "8dd2fd9",
+        "license": "no explicit license \u2014 referenced by link only",
+        "skills": 1
+      },
+      "zebbern/claude-code-guide": {
+        "repo": "https://github.com/zebbern/claude-code-guide",
+        "commit": "d2c5280",
+        "license": "MIT",
+        "skills": 1
+      },
+      "staruhub/ClaudeSkills": {
+        "repo": "https://github.com/staruhub/ClaudeSkills",
+        "commit": "3d4045d",
+        "license": "MIT",
+        "skills": 1
+      },
+      "hypnguyen1209/offensive-claude": {
+        "repo": "https://github.com/hypnguyen1209/offensive-claude",
+        "commit": "4d62be7",
+        "license": "MIT",
+        "skills": 1
+      },
+      "ViryaZheng/recomby-geo": {
+        "repo": "https://github.com/ViryaZheng/recomby-geo",
+        "commit": "530d5e2",
+        "license": "MIT",
+        "skills": 1
+      },
+      "heshengtao/super-agent-party": {
+        "repo": "https://github.com/heshengtao/super-agent-party",
+        "commit": "181588d",
+        "license": "custom (see upstream LICENSE)",
+        "skills": 1
+      },
+      "OpenRaiser/NanoResearch": {
+        "repo": "https://github.com/OpenRaiser/NanoResearch",
+        "commit": "7144364",
+        "license": "MIT",
+        "skills": 1
+      },
+      "Orchestra-Research/AI-research-SKILLs": {
+        "repo": "https://github.com/Orchestra-Research/AI-research-SKILLs",
+        "commit": "773a529",
+        "license": "MIT",
+        "skills": 1
+      },
+      "zechenzhangAGI/AI-research-SKILLs": {
+        "repo": "https://github.com/zechenzhangAGI/AI-research-SKILLs",
+        "commit": "773a529",
+        "license": "MIT",
+        "skills": 1
+      },
+      "harperreed/dotfiles": {
+        "repo": "https://github.com/harperreed/dotfiles",
+        "commit": "6b5ced1",
+        "license": "MIT",
+        "skills": 1
+      },
+      "jabrena/plinth": {
+        "repo": "https://github.com/jabrena/plinth",
+        "commit": "065eae8",
+        "license": "Apache-2.0",
+        "skills": 1
+      }
+    },
+    "total_skills": 80,
+    "tiers": {
+      "core": 36,
+      "adjacent": 44
+    }
+  },
+  "provenance": {
+    "items": {
+      "esco": 28,
+      "onet": 138,
+      "jobads": 36,
+      "wiki_ai": 0,
+      "anthropic": 5,
+      "ai_skills": 195,
+      "stackx": 0
+    },
+    "share_percent": {
+      "esco": 7.0,
+      "onet": 34.3,
+      "jobads": 9.0,
+      "wiki_ai": 0.0,
+      "anthropic": 1.2,
+      "ai_skills": 48.5,
+      "stackx": 0.0
+    },
+    "method": "content items per source category"
+  },
+  "collar": "white",
+  "computer_work": true
+}
--- a/references/ai-skills.md
+++ b/references/ai-skills.md
@@ -0,0 +1,418 @@
+# External AI agent skills — scopist
+
+Proven, publicly available AI agent skills mapped to this occupation.
+Nothing is copied from the sources: every entry is a name, a one-line
+summary and a link to the upstream skill package. Each section names
+its source repository, commit, license and retrieval date.
+
+**Tiers:** `core` = the skill directly exercises a top market hard
+skill, tool or method (from gated job-ad evidence) or an essential
+ESCO competence of this occupation; `adjacent` =
+plausibly useful, secondary. Entries are capped at 12 per source
+and 80 in total per occupation (core first,
+strongest matches survive); everything beyond the caps is excluded
+and logged in the pipeline audit trail, not in this package.
+
+_Matched deterministically (ISCO group + title/competence keywords,
+tiered against market evidence + ESCO essentials) by
+`pipeline/p5_enrich_ai_skills.py` on 2026-07-14._
+
+## Source: anthropics/skills
+
+- Repository: [https://github.com/anthropics/skills](https://github.com/anthropics/skills) (commit `f6656c1`, retrieved 2026-07-14)
+- License: Apache-2.0; the document skills (docx/pdf/pptx/xlsx) are source-available — see the LICENSE.txt in the upstream skill folder
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `docx` | adjacent | Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to … | [source](https://github.com/anthropics/skills/tree/main/skills/docx) |
+| `pdf` | adjacent | Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating … | [source](https://github.com/anthropics/skills/tree/main/skills/pdf) |
+
+## Source: a5c-ai/babysitter
+
+- Repository: [https://github.com/a5c-ai/babysitter](https://github.com/a5c-ai/babysitter) (commit `44a5d58b`, retrieved 2026-07-14)
+- License: MIT
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `ipa-transcription-phonological` | adjacent | Transcribe speech using International Phonetic Alphabet and analyze sound systems including phonotactics and phonological rules | [source](https://github.com/a5c-ai/babysitter/tree/44a5d58b/library/specializations/domains/social-sciences-humanities/humanities/skills/ipa-transcription-phonological) |
+
+## Source: affaan-m/everything-claude-code
+
+- Repository: [https://github.com/affaan-m/everything-claude-code](https://github.com/affaan-m/everything-claude-code) (commit `ed38744`, retrieved 2026-07-14)
+- License: MIT
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `agentic-os` | core | Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases. | [source](https://github.com/affaan-m/everything-claude-code/tree/ed38744/skills/agentic-os) |
+
+## Source: AlpacaLabsLLC/skills-for-architects
+
+- Repository: [https://github.com/AlpacaLabsLLC/skills-for-architects](https://github.com/AlpacaLabsLLC/skills-for-architects) (commit `4476576`, retrieved 2026-07-14)
+- License: MIT
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `slide-deck-generator` | core | Generate a self-contained HTML slide deck from a topic, outline, report, or data. Use for presentations and slide decks; not for editing PowerPoint files. | [source](https://github.com/AlpacaLabsLLC/skills-for-architects/tree/4476576/skills/slide-deck-generator) |
+| `meeting-minutes` | adjacent | Turn a meeting transcript, notes, or conversation into collision-safe, source-linked minutes in meetings/YYYY-MM-DD-slug.md. Use for project meeting records, attendance, discussion, stated information, decisions, action candidates, and … | [source](https://github.com/AlpacaLabsLLC/skills-for-architects/tree/4476576/skills/meeting-minutes) |
+
+## Source: brycewang-stanford/Auto-Empirical-Research-Skills
+
+- Repository: [https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills](https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills) (commit `85bf545`, retrieved 2026-07-14)
+- License: CC-BY-4.0
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `markitdown` | core | Convert various file formats (PDF, Office documents, images, audio, web content, structured data) to Markdown optimized for LLM processing. Use when converting documents to markdown, extracting text from PDFs/Office files, transcribing … | [source](https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/tree/85bf545/skills/67-econfin-workflow-toolkit/markitdown) |
+| `slide-excellence` | core | Multi-agent slide review (visual, pedagogy, proofreading). Use for comprehensive quality check before milestones. | [source](https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/tree/85bf545/skills/12-pedrohcgs-claude-code-my-workflow/dot-claude/skills/slide-excellence) |
+| `review` | adjacent | All quality reviews — routes to appropriate critics based on target file type and flags. Replaces /paper-excellence, /proofread, /econometrics-check, /review-r, /review-paper. | [source](https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/tree/85bf545/skills/16-hsantanna88-clo-author/dot-claude/skills/review) |
+| `referee2` | adjacent | Systematic audit and review by Referee 2. Two modes — "deck" reviews slide presentations for rhetoric, visual quality, and compile cleanliness; "code" performs cross-language replication and econometric audit of empirical pipelines. Use … | [source](https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/tree/85bf545/skills/13-scunning1975-MixtapeTools/skills/referee2) |
+
+## Source: ComPDFKit/compdf-skills
+
+- Repository: [https://github.com/ComPDFKit/compdf-skills](https://github.com/ComPDFKit/compdf-skills) (commit `b77153e`, retrieved 2026-07-14)
+- License: no explicit license — referenced by link only
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `pdf-to-word-docx` | core | PDF to Word converts PDF to editable Word/DOCX with AI-powered layout analysis and table recognition, built on ComPDF Conversion SDK to better preserve tables, multi-column layouts, lists, and images for downstream editing. It fits … | [source](https://github.com/ComPDFKit/compdf-skills/tree/b77153e/skills/pdf-to-word-docx) |
+
+## Source: davepoon/buildwithclaude
+
+- Repository: [https://github.com/davepoon/buildwithclaude](https://github.com/davepoon/buildwithclaude) (commit `3c94e0c`, retrieved 2026-07-14)
+- License: MIT
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `docx` | core | Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new … | [source](https://github.com/davepoon/buildwithclaude/tree/3c94e0c/plugins/all-skills/skills/docx) |
+| `pptx` | core | Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, … | [source](https://github.com/davepoon/buildwithclaude/tree/3c94e0c/plugins/all-skills/skills/pptx) |
+| `xlsx` | core | Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new … | [source](https://github.com/davepoon/buildwithclaude/tree/3c94e0c/plugins/all-skills/skills/xlsx) |
+
+## Source: davila7/claude-code-templates
+
+- Repository: [https://github.com/davila7/claude-code-templates](https://github.com/davila7/claude-code-templates) (commit `fa79251`, retrieved 2026-07-14)
+- License: MIT
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `doc` | core | Use when the task involves reading, creating, or editing `.docx` documents, especially when formatting or layout fidelity matters; prefer `python-docx` plus the bundled `scripts/render_docx.py` for visual checks. | [source](https://github.com/davila7/claude-code-templates/tree/fa79251/cli-tool/components/skills/document-processing/doc) |
+| `spreadsheet` | core | Use when tasks involve creating, editing, analyzing, or formatting spreadsheets (`.xlsx`, `.csv`, `.tsv`) using Python (`openpyxl`, `pandas`), especially when formulas, references, and formatting need to be preserved and verified. | [source](https://github.com/davila7/claude-code-templates/tree/fa79251/cli-tool/components/skills/document-processing/spreadsheet) |
+| `conversation-memory` | core | Persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory Use when: conversation memory, remember, memory persistence, long-term memory, chat history. | [source](https://github.com/davila7/claude-code-templates/tree/fa79251/cli-tool/components/skills/ai-research/conversation-memory) |
+| `transcribe` | core | Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in interviews or meetings. | [source](https://github.com/davila7/claude-code-templates/tree/fa79251/cli-tool/components/skills/media/transcribe) |
+| `markitdown` | adjacent | Convert files and office documents to Markdown. Supports PDF, DOCX, PPTX, XLSX, images (with OCR), audio (with transcription), HTML, CSV, JSON, XML, ZIP, YouTube URLs, EPubs and more. | [source](https://github.com/davila7/claude-code-templates/tree/fa79251/cli-tool/components/skills/scientific/markitdown) |
+| `peft-fine-tuning` | adjacent | Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter … | [source](https://github.com/davila7/claude-code-templates/tree/fa79251/cli-tool/components/skills/ai-research/fine-tuning-peft) |
+
+## Source: egorfedorov/claude-context-optimizer
+
+- Repository: [https://github.com/egorfedorov/claude-context-optimizer](https://github.com/egorfedorov/claude-context-optimizer) (commit `c604d3a`, retrieved 2026-07-14)
+- License: MIT
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `cco-overhead` | adjacent | Audit the fixed context overhead every session starts with — system prompt, MCP tools, agents, CLAUDE.md, memory — measured from real transcript usage | [source](https://github.com/egorfedorov/claude-context-optimizer/tree/c604d3a/skills/cco-overhead) |
+
+## Source: fcakyon/claude-codex-settings
+
+- Repository: [https://github.com/fcakyon/claude-codex-settings](https://github.com/fcakyon/claude-codex-settings) (commit `44b7c00`, retrieved 2026-07-14)
+- License: Apache-2.0
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `doc` | core | Use when the task involves reading, creating, or editing `.docx` documents, especially when formatting or layout fidelity matters; prefer `python-docx` plus the bundled `scripts/render_docx.py` for visual checks. | [source](https://github.com/fcakyon/claude-codex-settings/tree/44b7c00/plugins/openai-office-skills/skills/doc) |
+| `spreadsheet` | core | Use when tasks involve creating, editing, analyzing, or formatting spreadsheets (`.xlsx`, `.csv`, `.tsv`) with formula-aware workflows, cached recalculation, and visual review. | [source](https://github.com/fcakyon/claude-codex-settings/tree/44b7c00/plugins/openai-office-skills/skills/spreadsheet) |
+
+## Source: feiskyer/claude-code-settings
+
+- Repository: [https://github.com/feiskyer/claude-code-settings](https://github.com/feiskyer/claude-code-settings) (commit `0eb042a`, retrieved 2026-07-14)
+- License: MIT
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `youtube-transcribe-skill` | adjacent | Extract subtitles/transcripts from YouTube videos. Triggers: "youtube transcript", "extract subtitles", "video captions", "视频字幕", "字幕提取", "YouTube转文字", "提取字幕". | [source](https://github.com/feiskyer/claude-code-settings/tree/0eb042a/skills/youtube-transcribe-skill) |
+
+## Source: foryourhealth111-pixel/Vibe-Skills
+
+- Repository: [https://github.com/foryourhealth111-pixel/Vibe-Skills](https://github.com/foryourhealth111-pixel/Vibe-Skills) (commit `34429a8`, retrieved 2026-07-14)
+- License: Apache-2.0
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `doc` | core | Use when the task involves reading, creating, or editing `.docx` documents, especially when formatting or layout fidelity matters; prefer `python-docx` plus the bundled `scripts/render_docx.py` for visual checks. | [source](https://github.com/foryourhealth111-pixel/Vibe-Skills/tree/34429a8/bundled/skills/doc) |
+| `spreadsheet` | core | Use when tasks involve creating, editing, analyzing, or formatting spreadsheets (`.xlsx`, `.csv`, `.tsv`) using Python (`openpyxl`, `pandas`), especially when formulas, references, and formatting need to be preserved and verified. | [source](https://github.com/foryourhealth111-pixel/Vibe-Skills/tree/34429a8/bundled/skills/spreadsheet) |
+| `transcribe` | core | Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in interviews or meetings. | [source](https://github.com/foryourhealth111-pixel/Vibe-Skills/tree/34429a8/bundled/skills/transcribe) |
+| `markitdown` | adjacent | Convert files and office documents to Markdown. Supports PDF, DOCX, PPTX, XLSX, images (with OCR), audio (with transcription), HTML, CSV, JSON, XML, ZIP, YouTube URLs, EPubs and more. | [source](https://github.com/foryourhealth111-pixel/Vibe-Skills/tree/34429a8/bundled/skills/markitdown) |
+| `slides-as-code` | adjacent | Build research slides with text-first source (Slidev/Marp/Reveal/Quarto) and reproducible export (PDF). Includes structure, figure reuse rules, and quality checklist for top-tier scientific presentations. | [source](https://github.com/foryourhealth111-pixel/Vibe-Skills/tree/34429a8/bundled/skills/slides-as-code) |
+
+## Source: harperreed/dotfiles
+
+- Repository: [https://github.com/harperreed/dotfiles](https://github.com/harperreed/dotfiles) (commit `6b5ced1`, retrieved 2026-07-14)
+- License: MIT
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `swiftui-performance-audit` | adjacent | Audit and improve SwiftUI runtime performance from code review and architecture. Use for requests to diagnose slow rendering, janky scrolling, high CPU/memory usage, excessive view updates, or layout thrash in SwiftUI apps, and to provide … | [source](https://github.com/harperreed/dotfiles/tree/6b5ced1/.claude/skills/swiftui-performance-audit) |
+
+## Source: heshengtao/super-agent-party
+
+- Repository: [https://github.com/heshengtao/super-agent-party](https://github.com/heshengtao/super-agent-party) (commit `181588d`, retrieved 2026-07-14)
+- License: custom (see upstream LICENSE)
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `officeCLI` | adjacent | Create, analyze, proofread, and modify Office documents (.docx, .xlsx, .pptx) using the officecli CLI tool. Use when the user wants to create, inspect, check formatting, find issues, add charts, or modify Office documents. | [source](https://github.com/heshengtao/super-agent-party/tree/181588d/skills/officeCLI) |
+
+## Source: hoangsonww/Claude-Code-Agent-Monitor
+
+- Repository: [https://github.com/hoangsonww/Claude-Code-Agent-Monitor](https://github.com/hoangsonww/Claude-Code-Agent-Monitor) (commit `8f87ce1`, retrieved 2026-07-14)
+- License: MIT
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `transcript-replay` | adjacent | Walk a Claude Code session transcript turn-by-turn from Agent Monitor data, summarizing each user, assistant, and tool message in order so a long conversation can be reviewed quickly. Anchors the recap to the session header (model, cost, … | [source](https://github.com/hoangsonww/Claude-Code-Agent-Monitor/tree/8f87ce1/plugins/ccam-sessions/skills/transcript-replay) |
+
+## Source: hypnguyen1209/offensive-claude
+
+- Repository: [https://github.com/hypnguyen1209/offensive-claude](https://github.com/hypnguyen1209/offensive-claude) (commit `4d62be7`, retrieved 2026-07-14)
+- License: MIT
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `exploit-development` | adjacent | Use when turning a memory-corruption bug into a working PoC — stack/ROP, glibc heap & FSOP, format strings, browser/JIT type confusion & UAF, Linux/Windows kernel LPE against ASLR/DEP/CFG/CET/V8-Sandbox | [source](https://github.com/hypnguyen1209/offensive-claude/tree/4d62be7/skills/exploit-development) |
+
+## Source: infrasity-labs/dev-gtm-claude-skills
+
+- Repository: [https://github.com/infrasity-labs/dev-gtm-claude-skills](https://github.com/infrasity-labs/dev-gtm-claude-skills) (commit `02cfefb`, retrieved 2026-07-14)
+- License: MIT
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `brief-outline-generator` | core | Generates a fully structured SEO content **outline** (not a finished brief) and exports it as a formatted .docx Word document. The output is a skeleton for a writer to fill in — section headings, topic prompts, angles — not pre-written … | [source](https://github.com/infrasity-labs/dev-gtm-claude-skills/tree/02cfefb/skills/brief-outline-generator) |
+| `summarize-interview` | adjacent | Summarize a user interview transcript into structured insights with key themes, quotes, and action items. Use after conducting user interviews to extract and share findings efficiently. | [source](https://github.com/infrasity-labs/dev-gtm-claude-skills/tree/02cfefb/.claude/skills/summarize-interview) |
+
+## Source: jabrena/plinth
+
+- Repository: [https://github.com/jabrena/plinth](https://github.com/jabrena/plinth) (commit `065eae8`, retrieved 2026-07-14)
+- License: Apache-2.0
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `145-java-refactoring-high-performance` | adjacent | Use when you need to refactor Java code for high performance — including memory/allocation reduction, CPU hot-path optimization, and syntax/API/control-flow improvements. This should trigger for requests such as Review Java code for high … | [source](https://github.com/jabrena/plinth/tree/065eae8/skills/145-java-refactoring-high-performance) |
+
+## Source: jeremylongshore/claude-code-plugins-plus-skills
+
+- Repository: [https://github.com/jeremylongshore/claude-code-plugins-plus-skills](https://github.com/jeremylongshore/claude-code-plugins-plus-skills) (commit `e112938a`, retrieved 2026-07-14)
+- License: MIT
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `elevenlabs-core-workflow-b` | core | Implement ElevenLabs speech-to-speech, sound effects, audio isolation, and speech-to-text. Use when converting voice to another voice, generating sound effects from text, removing background noise, or transcribing audio. Trigger: … | [source](https://github.com/jeremylongshore/claude-code-plugins-plus-skills/tree/e112938a/plugins/saas-packs/elevenlabs-pack/skills/elevenlabs-core-workflow-b) |
+| `granola-common-errors` | adjacent | Troubleshoot common Granola errors \u2014 audio capture failures, transcription\ \ issues,\ncalendar sync problems, and integration errors. Platform-specific fixes\ \ for macOS and Windows.\nTrigger: \"granola error\", \"granola not … | [source](https://github.com/jeremylongshore/claude-code-plugins-plus-skills/tree/e112938a/plugins/saas-packs/granola-pack/skills/granola-common-errors) |
+| `assemblyai-core-workflow-a` | adjacent | Execute AssemblyAI primary workflow: async transcription with audio intelligence. Use when transcribing audio/video files, enabling speaker diarization, sentiment analysis, entity detection, PII redaction, or content moderation. Trigger … | [source](https://github.com/jeremylongshore/claude-code-plugins-plus-skills/tree/e112938a/plugins/saas-packs/assemblyai-pack/skills/assemblyai-core-workflow-a) |
+| `deepgram-migration-deep-dive` | adjacent | Deep dive into migrating to Deepgram from other transcription providers. Use when migrating from AWS Transcribe, Google Cloud STT, Azure Speech, OpenAI Whisper, AssemblyAI, or Rev.ai to Deepgram. Trigger: "deepgram migration", "switch to … | [source](https://github.com/jeremylongshore/claude-code-plugins-plus-skills/tree/e112938a/plugins/saas-packs/deepgram-pack/skills/deepgram-migration-deep-dive) |
+| `podium-call-transcript-pipeline` | adjacent | Durable, idempotent ingest pipeline for Podium call transcripts — the layer between Podium's transcript webhook and a downstream RAG/LLM queue. Survives minutes-to-hours transcript latency, partial-then-final overwrites, non-English … | [source](https://github.com/jeremylongshore/claude-code-plugins-plus-skills/tree/e112938a/plugins/saas-packs/podium-pack/skills/podium-call-transcript-pipeline) |
+| `twinmind-data-handling` | adjacent | Handle TwinMind meeting data with GDPR compliance: transcript storage, memory vault management, data export, and deletion policies. Use when implementing data handling, or managing TwinMind meeting AI operations. Trigger with phrases like … | [source](https://github.com/jeremylongshore/claude-code-plugins-plus-skills/tree/e112938a/plugins/saas-packs/twinmind-pack/skills/twinmind-data-handling) |
+| `twinmind-incident-runbook` | adjacent | Incident response for TwinMind failures: transcription not starting, audio not captured, sync failures, and calendar disconnect. Use when implementing incident runbook, or managing TwinMind meeting AI operations. Trigger with phrases like … | [source](https://github.com/jeremylongshore/claude-code-plugins-plus-skills/tree/e112938a/plugins/saas-packs/twinmind-pack/skills/twinmind-incident-runbook) |
+| `twinmind-observability` | adjacent | Monitor TwinMind transcription quality, meeting coverage, action item extraction rates, and memory vault health. Use when implementing observability, or managing TwinMind meeting AI operations. Trigger with phrases like "twinmind … | [source](https://github.com/jeremylongshore/claude-code-plugins-plus-skills/tree/e112938a/plugins/saas-packs/twinmind-pack/skills/twinmind-observability) |
+| `twinmind-reference-architecture` | adjacent | Production architecture for meeting AI systems using TwinMind: transcription pipeline, memory vault, action item workflow, and calendar integration. Use when implementing reference architecture, or managing TwinMind meeting AI operations. … | [source](https://github.com/jeremylongshore/claude-code-plugins-plus-skills/tree/e112938a/plugins/saas-packs/twinmind-pack/skills/twinmind-reference-architecture) |
+| `twinmind-install-auth` | adjacent | Install and configure TwinMind Chrome extension, mobile app, and API access. Use when setting up TwinMind for meeting transcription, configuring calendar integration, or initializing TwinMind in your workflow. Trigger with phrases like … | [source](https://github.com/jeremylongshore/claude-code-plugins-plus-skills/tree/e112938a/plugins/saas-packs/twinmind-pack/skills/twinmind-install-auth) |
+| `twinmind-webhooks-events` | adjacent | Handle TwinMind meeting events including transcription completion, action item extraction, and calendar sync notifications. Use when implementing webhooks events, or managing TwinMind meeting AI operations. Trigger with phrases like … | [source](https://github.com/jeremylongshore/claude-code-plugins-plus-skills/tree/e112938a/plugins/saas-packs/twinmind-pack/skills/twinmind-webhooks-events) |
+| `gamma-core-workflow-a` | adjacent | Generate presentations, documents, and webpages via Gamma API. Use when creating content from text prompts, configuring themes, image styles, text modes, and output formats. Trigger: "gamma generate", "gamma presentation from text", "gamma … | [source](https://github.com/jeremylongshore/claude-code-plugins-plus-skills/tree/e112938a/plugins/saas-packs/gamma-pack/skills/gamma-core-workflow-a) |
+
+## Source: K-Dense-AI/claude-scientific-skills
+
+- Repository: [https://github.com/K-Dense-AI/claude-scientific-skills](https://github.com/K-Dense-AI/claude-scientific-skills) (commit `4d97e29`, retrieved 2026-07-14)
+- License: MIT
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `markitdown` | adjacent | Convert files and office documents to Markdown. Supports PDF, DOCX, PPTX, XLSX, images (with OCR), audio (with transcription), HTML, CSV, JSON, XML, ZIP, YouTube URLs, EPubs and more. | [source](https://github.com/K-Dense-AI/claude-scientific-skills/tree/4d97e29/skills/markitdown) |
+
+## Source: K-Dense-AI/scientific-agent-skills
+
+- Repository: [https://github.com/K-Dense-AI/scientific-agent-skills](https://github.com/K-Dense-AI/scientific-agent-skills) (commit `4d97e29`, retrieved 2026-07-14)
+- License: MIT
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `markitdown` | adjacent | Convert files and office documents to Markdown. Supports PDF, DOCX, PPTX, XLSX, images (with OCR), audio (with transcription), HTML, CSV, JSON, XML, ZIP, YouTube URLs, EPubs and more. | [source](https://github.com/K-Dense-AI/scientific-agent-skills/tree/4d97e29/skills/markitdown) |
+
+## Source: michalparkola/tapestry-skills-for-claude-code
+
+- Repository: [https://github.com/michalparkola/tapestry-skills-for-claude-code](https://github.com/michalparkola/tapestry-skills-for-claude-code) (commit `80e1dc5`, retrieved 2026-07-14)
+- License: MIT
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `youtube-transcript` | adjacent | Download YouTube video transcripts when user provides a YouTube URL or asks to download/get/fetch a transcript from YouTube. Also use when user wants to transcribe or get captions/subtitles from a YouTube video. | [source](https://github.com/michalparkola/tapestry-skills-for-claude-code/tree/80e1dc5/youtube-transcript) |
+
+## Source: microsoft/skills
+
+- Repository: [https://github.com/microsoft/skills](https://github.com/microsoft/skills) (commit `dc543aa`, retrieved 2026-07-14)
+- License: MIT
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `continual-learning` | core | Guide for implementing continual learning in AI coding agents — hooks, memory scoping, reflection patterns. Use when setting up learning infrastructure for agents. | [source](https://github.com/microsoft/skills/tree/dc543aa/.github/skills/continual-learning) |
+
+## Source: mohitagw15856/pm-claude-skills
+
+- Repository: [https://github.com/mohitagw15856/pm-claude-skills](https://github.com/mohitagw15856/pm-claude-skills) (commit `876fa30`, retrieved 2026-07-14)
+- License: MIT
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `meeting-notes` | core | Structure and format meeting notes following PM best practices. Use when asked to create meeting notes, format discussion notes, capture action items, or document decisions from any meeting type. Produces structured notes with decisions, … | [source](https://github.com/mohitagw15856/pm-claude-skills/tree/876fa30/plugins/pm-essentials/skills/meeting-notes) |
+| `board-minutes` | adjacent | Write formal board meeting minutes from an agenda, notes, transcript, or discussion summary. Use when asked to draft board minutes, governance minutes, meeting minutes for a board, or a formal record of decisions and actions. Produces … | [source](https://github.com/mohitagw15856/pm-claude-skills/tree/876fa30/plugins/pm-business/skills/board-minutes) |
+| `legal-brief` | adjacent | Draft a structured legal brief, case summary, or legal argument outline. Use when asked to write a legal brief, case note, legal memo, argument outline, or position paper. Produces a structured document using IRAC format (Issue, Rule, … | [source](https://github.com/mohitagw15856/pm-claude-skills/tree/876fa30/plugins/pm-legal/skills/legal-brief) |
+
+## Source: mukul975/Anthropic-Cybersecurity-Skills
+
+- Repository: [https://github.com/mukul975/Anthropic-Cybersecurity-Skills](https://github.com/mukul975/Anthropic-Cybersecurity-Skills) (commit `673da1f`, retrieved 2026-07-14)
+- License: Apache-2.0
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `analyzing-macro-malware-in-office-documents` | core | Analyzes malicious VBA macros embedded in Microsoft Office documents (Word, Excel, PowerPoint) to identify download cradles, payload execution, persistence mechanisms, and anti-analysis techniques. Uses olevba, oledump, and VBA … | [source](https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/673da1f/skills/analyzing-macro-malware-in-office-documents) |
+| `analyzing-memory-dumps-with-volatility` | core | Analyzes RAM memory dumps from compromised systems using the Volatility framework to identify malicious processes, injected code, network connections, loaded modules, and extracted credentials. Supports Windows, Linux, and macOS memory … | [source](https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/673da1f/skills/analyzing-memory-dumps-with-volatility) |
+| `performing-endpoint-forensics-investigation` | adjacent | Performs digital forensics investigation on compromised endpoints including memory acquisition, disk imaging, artifact analysis, and timeline reconstruction. Use when investigating security incidents, collecting evidence for legal … | [source](https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/673da1f/skills/performing-endpoint-forensics-investigation) |
+
+## Source: nexu-io/open-design
+
+- Repository: [https://github.com/nexu-io/open-design](https://github.com/nexu-io/open-design) (commit `4b66023`, retrieved 2026-07-14)
+- License: Apache-2.0
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `minimax-docx` | core | Professional DOCX document creation and editing using OpenXML SDK. Useful for branded reports, polished proposals, and template-based authoring. | [source](https://github.com/nexu-io/open-design/tree/4b66023/skills/minimax-docx) |
+| `docx` | adjacent | Create, edit, and analyze Word documents with tracked changes, comments, and formatting. Useful for design briefs, copy docs, and review-ready deliverables. | [source](https://github.com/nexu-io/open-design/tree/4b66023/skills/docx) |
+
+## Source: NoizAI/skills
+
+- Repository: [https://github.com/NoizAI/skills](https://github.com/NoizAI/skills) (commit `2a0e09d`, retrieved 2026-07-14)
+- License: no explicit license — referenced by link only
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `speech-to-text` | core | Use this skill whenever the user wants to transcribe audio to text, convert speech to text, or get a transcript from an audio or video file. Triggers include: any mention of 'transcribe', 'transcription', 'speech to text', 'STT', 'convert … | [source](https://github.com/NoizAI/skills/tree/2a0e09d/skills/speech-to-text) |
+
+## Source: OpenRaiser/NanoResearch
+
+- Repository: [https://github.com/OpenRaiser/NanoResearch](https://github.com/OpenRaiser/NanoResearch) (commit `7144364`, retrieved 2026-07-14)
+- License: MIT
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `peft-fine-tuning` | adjacent | Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter … | [source](https://github.com/OpenRaiser/NanoResearch/tree/7144364/skills/vendor-ai-research/peft) |
+
+## Source: Orchestra-Research/AI-research-SKILLs
+
+- Repository: [https://github.com/Orchestra-Research/AI-research-SKILLs](https://github.com/Orchestra-Research/AI-research-SKILLs) (commit `773a529`, retrieved 2026-07-14)
+- License: MIT
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `peft-fine-tuning` | adjacent | Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter … | [source](https://github.com/Orchestra-Research/AI-research-SKILLs/tree/773a529/03-fine-tuning/peft) |
+
+## Source: pedrohcgs/claude-code-my-workflow
+
+- Repository: [https://github.com/pedrohcgs/claude-code-my-workflow](https://github.com/pedrohcgs/claude-code-my-workflow) (commit `be53c12`, retrieved 2026-07-14)
+- License: MIT
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `slide-excellence` | core | Multi-agent comprehensive slide review (visual + pedagogy + proofreading, plus TikZ / parity / substance conditionally). Use when user says "full review", "excellence pass", "comprehensive check", "review everything", "pre-release review", … | [source](https://github.com/pedrohcgs/claude-code-my-workflow/tree/be53c12/.claude/skills/slide-excellence) |
+
+## Source: rameerez/claude-code-startup-skills
+
+- Repository: [https://github.com/rameerez/claude-code-startup-skills](https://github.com/rameerez/claude-code-startup-skills) (commit `410f81f`, retrieved 2026-07-14)
+- License: MIT
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `transcribe-video` | core | Generate subtitles (SRT/VTT) and plain text transcripts from video or audio files using AWS Transcribe. Use when creating captions, extracting spoken content, generating transcripts for notes, or making video content searchable. | [source](https://github.com/rameerez/claude-code-startup-skills/tree/410f81f/skills/transcribe-video) |
+
+## Source: silverstein/minutes
+
+- Repository: [https://github.com/silverstein/minutes](https://github.com/silverstein/minutes) (commit `3fb2e83`, retrieved 2026-07-14)
+- License: MIT
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `minutes-video-review` | core | Analyze a product walkthrough, bug report video, Loom, or ScreenPal using Minutes transcription plus visual review. Use when the user wants a recorded demo or bug clip turned into a durable brief with transcript, key frames, issues, and … | [source](https://github.com/silverstein/minutes/tree/3fb2e83/.agents/skills/minutes/minutes-video-review) |
+| `minutes-record` | core | Start or stop recording a meeting, call, or voice memo. Use this whenever the user says "record", "start recording", "capture this meeting", "stop recording", "I'm in a meeting", "take notes on this call", or wants to transcribe live … | [source](https://github.com/silverstein/minutes/tree/3fb2e83/.agents/skills/minutes/minutes-record) |
+
+## Source: snyk/agent-scan
+
+- Repository: [https://github.com/snyk/agent-scan](https://github.com/snyk/agent-scan) (commit `f3a4621`, retrieved 2026-07-14)
+- License: Apache-2.0
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `docx` | core | Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new … | [source](https://github.com/snyk/agent-scan/tree/f3a4621/tests/skills/docx) |
+| `pptx` | core | Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, … | [source](https://github.com/snyk/agent-scan/tree/f3a4621/tests/skills/pptx) |
+| `xlsx` | core | Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new … | [source](https://github.com/snyk/agent-scan/tree/f3a4621/tests/skills/xlsx) |
+
+## Source: staruhub/ClaudeSkills
+
+- Repository: [https://github.com/staruhub/ClaudeSkills](https://github.com/staruhub/ClaudeSkills) (commit `3d4045d`, retrieved 2026-07-14)
+- License: MIT
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `deep-research` | adjacent | Use this skill when the user wants an evidence-based research memo, literature review, market/policy/technical landscape, or a multi-source decision brief with citations, trade-offs, and a clear conclusion. Best for tasks that need … | [source](https://github.com/staruhub/ClaudeSkills/tree/3d4045d/skills/Geek-skills-deep-research) |
+
+## Source: ThinkInAIXYZ/deepchat
+
+- Repository: [https://github.com/ThinkInAIXYZ/deepchat](https://github.com/ThinkInAIXYZ/deepchat) (commit `f275c92`, retrieved 2026-07-14)
+- License: Apache-2.0
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `docx` | core | Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new … | [source](https://github.com/ThinkInAIXYZ/deepchat/tree/f275c92/resources/skills/docx) |
+| `pptx` | core | Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, … | [source](https://github.com/ThinkInAIXYZ/deepchat/tree/f275c92/resources/skills/pptx) |
+| `xlsx` | core | Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new … | [source](https://github.com/ThinkInAIXYZ/deepchat/tree/f275c92/resources/skills/xlsx) |
+
+## Source: transloadit/skills
+
+- Repository: [https://github.com/transloadit/skills](https://github.com/transloadit/skills) (commit `8dd2fd9`, retrieved 2026-07-14)
+- License: no explicit license — referenced by link only
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `transform-transcribe-audio-with-transloadit` | adjacent | One-off transcription of local audio or video files to text or subtitle files using Transloadit via the official `@transloadit/node` CLI. Use when the user wants speech in local media converted to `.txt`, `.json`, `.srt`, or `.webvtt`; … | [source](https://github.com/transloadit/skills/tree/8dd2fd9/skills/transform-transcribe-audio-with-transloadit) |
+
+## Source: vibeeval/vibecosystem
+
+- Repository: [https://github.com/vibeeval/vibecosystem](https://github.com/vibeeval/vibecosystem) (commit `cea9462`, retrieved 2026-07-14)
+- License: MIT
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `minimax-docx` | core | Professional DOCX document creation, editing, and formatting using OpenXML SDK (.NET). Three pipelines: (A) create new documents from scratch, (B) fill/edit content in existing documents, (C) apply template formatting with XSD validation … | [source](https://github.com/vibeeval/vibecosystem/tree/cea9462/skills/minimax-docx) |
+| `harvest-adaptive` | adjacent | Adaptive content summarization - auto-detect content type and produce relevant summary | [source](https://github.com/vibeeval/vibecosystem/tree/cea9462/skills/harvest-adaptive) |
+
+## Source: ViryaZheng/recomby-geo
+
+- Repository: [https://github.com/ViryaZheng/recomby-geo](https://github.com/ViryaZheng/recomby-geo) (commit `530d5e2`, retrieved 2026-07-14)
+- License: MIT
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `keyword-research` | adjacent | Discover, analyze, and prioritize keywords for SEO and GEO content strategies. Identifies high-value opportunities based on search volume, competition, intent, and business relevance. Generates topic clusters and content calendars. Use … | [source](https://github.com/ViryaZheng/recomby-geo/tree/530d5e2/plugins/recomby-geo/skills/keyword-research) |
+
+## Source: zebbern/claude-code-guide
+
+- Repository: [https://github.com/zebbern/claude-code-guide](https://github.com/zebbern/claude-code-guide) (commit `d2c5280`, retrieved 2026-07-14)
+- License: MIT
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `dataset-quality-audit` | adjacent | Run comprehensive quality checks on tabular data (CSV/Excel/TSV/JSON), detecting missing values, duplicates, outliers, format issues, and type inconsistencies to produce an overall score, grade, and actionable suggestions. Triggered when … | [source](https://github.com/zebbern/claude-code-guide/tree/d2c5280/skills/dataset-quality-audit) |
+
+## Source: zechenzhangAGI/AI-research-SKILLs
+
+- Repository: [https://github.com/zechenzhangAGI/AI-research-SKILLs](https://github.com/zechenzhangAGI/AI-research-SKILLs) (commit `773a529`, retrieved 2026-07-14)
+- License: MIT
+
+| Skill | Tier | What it adds | Upstream |
+|---|---|---|---|
+| `peft-fine-tuning` | adjacent | Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter … | [source](https://github.com/zechenzhangAGI/AI-research-SKILLs/tree/773a529/03-fine-tuning/peft) |
--- a/references/market.md
+++ b/references/market.md
@@ -0,0 +1,76 @@
+# Market evidence report — scopist
+
+Source: **16 real job ads** (JSearch API, countries: us 16), extracted into the MSSQL evidence store; as of 2026-07-19.
+This report contains extracted, aggregated facts only — no ad text is
+reproduced (copyright / platform terms).
+
+## Seniority distribution
+
+| Seniority | Ads | Share |
+|---|---|---|
+| mid | 10 | 62 % |
+| n/a | 6 | 38 % |
+
+## Tools — full market ranking
+
+| # | Item | Ads | Share |
+|---|---|---|---|
+| 1 | CAT software | 3 | 19 % |
+
+## Hard skills — full market ranking
+
+| # | Item | Ads | Share |
+|---|---|---|---|
+| 1 | editing | 7 | 44 % |
+| 2 | proofreading | 7 | 44 % |
+| 3 | legal transcription | 5 | 31 % |
+| 4 | transcript review | 5 | 31 % |
+| 5 | scoping | 3 | 19 % |
+
+## Methods — full market ranking
+
+| # | Item | Ads | Share |
+|---|---|---|---|
+
+## Responsibilities — full market ranking
+
+| # | Item | Ads | Share |
+|---|---|---|---|
+| 1 | quality assurance | 4 | 25 % |
+| 2 | transcript editing | 4 | 25 % |
+
+## Regional breakdown
+
+> **Corpus note:** 16 relevant ads in total — below the 100-ad target for a fully reliable ranking. Percentages above should be read as indicative.
+
+### US (us)
+
+**Insufficient evidence** — 16 ads (minimum for a regional ranking: 30). No ranking is reported for this region.
+
+### UK (gb)
+
+**Insufficient evidence** — 0 ads (minimum for a regional ranking: 30). No ranking is reported for this region.
+
+### EU/DACH (de, at, ch, nl)
+
+**Insufficient evidence** — 0 ads (minimum for a regional ranking: 30). No ranking is reported for this region.
+
+
+## Job title variants in the market
+
+| Title | Ads |
+|---|---|
+| Scopist, Certified Reporter | 4 |
+| EclipseCAT Legal Transcript Scopist (Contract) | 2 |
+| Certified Reporter Scopist | 1 |
+| Digital Scopist - Legal Transcript Editor / Digital Court Reporter at MGM Trial Services, Inc. Silver Spring, MD | 1 |
+| Experienced Legal Scopist | 1 |
+| Experienced Legal Scopist 8 | 1 |
+| Experienced Scopist for Legal Transcripts | 1 |
+| House of Representatives is hiring: Editor (Scopist) in Washington | 1 |
+| Legal Scopist/Proofreader | 1 |
+| Legal Transcriber/Editor | 1 |
+| Maryland Court Reporters is hiring: Editor (Scopist) in Washington | 1 |
+| Parliamentary Transcripts Editor (Scopist) | 1 |
+
+Methodology: entities extracted per ad ({hard_skills, tools, methods, responsibilities, seniority}), normalized, counted as DISTINCT ads per entity; report threshold ≥ 3 ads. Headline sections in skills.md/tools.md use the stricter ≥ 20 % threshold.
--- a/references/profile.md
+++ b/references/profile.md
@@ -0,0 +1,17 @@
+# Occupation profile — scopist
+
+- **ESCO URI:** http://data.europa.eu/esco/occupation/42c769cd-4c60-4bac-94d2-29a492b82b74
+- **ESCO code:** 3343.5
+- **ISCO-08 group:** 3343 — Administrative and executive secretaries
+
+## Description (ESCO)
+
+Scopists edit the transcripts created by court reporters in order to make of them a readable professional legal document. They listen or read to the reports given to them in order to apply punctuation, missing words, format, and improve the accuracy of the document.
+
+## Definition
+
+nan
+
+## Alternative labels
+
+- freelance scopist
--- a/references/skills.md
+++ b/references/skills.md
@@ -0,0 +1,57 @@
+# Competences — scopist
+
+Source: ESCO v1.2.1 occupation-skill relations (http://data.europa.eu/esco/occupation/42c769cd-4c60-4bac-94d2-29a492b82b74).
+
+## Essential
+
+- **apply grammar and spelling rules** (skill/competence)
+- **grammar** (knowledge)
+- **legal terminology** (knowledge)
+- **observe confidentiality** (skill/competence)
+- **provide written content** (skill/competence)
+- **spelling** (knowledge)
+- **stenography** (knowledge)
+- **study court hearings** (skill/competence)
+- **transcription methods** (knowledge)
+- **type error-free documents** (skill/competence)
+- **type texts from audio sources** (skill/competence)
+- **use dictionaries** (skill/competence)
+- **use free typing techniques** (skill/competence)
+
+## Optional
+
+- compile legal documents (skill/competence)
+- court procedures (knowledge)
+- develop documentation in accordance with legal requirements (skill/competence)
+- digitise documents (skill/competence)
+- ensure proper document management (skill/competence)
+- legal case management (knowledge)
+- liaise with typists (skill/competence)
+- manage data for legal matters (skill/competence)
+- perform office routine activities (skill/competence)
+- record court procedures (skill/competence)
+- use shorthand (skill/competence)
+- use shorthand computer program (skill/competence)
+- use stenotype machines (skill/competence)
+- write meeting reports (skill/competence)
+
+<!-- market-evidence -->
+
+## Market evidence (job-ad analysis, 16 ads, as of 2026-07-19)
+
+Share of analyzed job ads mentioning the item (threshold ≥ 20 %). Source: JSearch/Adzuna APIs.
+
+### Hard skills
+
+- editing — **44 %**
+- proofreading — **44 %**
+- legal transcription — **31 %**
+- transcript review — **31 %**
+- scoping — **19 %**
+
+### Responsibilities
+
+- transcript editing — **25 %**
+- quality assurance — **25 %**
+
+<!-- market-evidence -->
--- a/references/tasks.md
+++ b/references/tasks.md
@@ -0,0 +1,57 @@
+# Tasks & work activities — scopist
+
+Source: O*NET 30.3, occupation 43-6011.00 (Executive Secretaries and Executive Administrative Assistants) — manual nearest-occupation mapping via ISCO group 3343; the official ESCO crosswalk has no entry for this ESCO occupation.
+
+## Task statements
+
+- **[Core]** Answer phone calls and direct calls to appropriate parties or take messages.
+- **[Core]** Perform general office duties, such as ordering supplies, maintaining records management database systems, and performing basic bookkeeping work.
+- **[Core]** Prepare agendas and make arrangements, such as coordinating catering for luncheons, for committee, board, and other meetings.
+- **[Core]** Coordinate and direct office services, such as records, departmental finances, budget preparation, personnel issues, and housekeeping, to aid executives.
+- **[Core]** Provide clerical support to other departments.
+- **[Supplemental]** Process payroll information.
+- **[Supplemental]** Supervise and train other clerical staff and arrange for employee training by scheduling training or organizing training material.
+- **[Core]** Manage and maintain executives' schedules.
+- **[Core]** Prepare invoices, reports, memos, letters, financial statements, and other documents, using word processing, spreadsheet, database, or presentation software.
+- **[Core]** Read and analyze incoming memos, submissions, and reports to determine their significance and plan their distribution.
+- **[Core]** Open, sort, and distribute incoming correspondence, including faxes and email.
+- **[Core]** File and retrieve corporate documents, records, and reports.
+- **[Core]** Greet visitors and determine whether they should be given access to specific individuals.
+- **[Core]** Prepare responses to correspondence containing routine inquiries.
+- **[Core]** Make travel arrangements for executives.
+- **[Core]** Conduct research, compile data, and prepare papers for consideration and presentation by executives, committees, and boards of directors.
+- **[Supplemental]** Compile, transcribe, and distribute minutes of meetings.
+- **[Core]** Attend meetings to record minutes.
+- **[Supplemental]** Meet with individuals, special interest groups, and others on behalf of executives, committees, and boards of directors.
+- **[Supplemental]** Set up and oversee administrative policies and procedures for offices or organizations.
+- **[Supplemental]** Review operating practices and procedures to determine whether improvements can be made in areas such as workflow, reporting procedures, or expenditures.
+- **[Supplemental]** Interpret administrative and operating policies and procedures for employees.
+
+## Detailed work activities
+
+- Answer telephones to direct calls or provide information.
+- Compile data or documentation.
+- Confer with coworkers to coordinate work activities.
+- Coordinate operational activities.
+- Develop organizational policies or programs.
+- Distribute incoming mail.
+- Execute sales or other financial transactions.
+- Explain regulations, policies, or procedures.
+- File documents or records.
+- Greet customers, patrons, or visitors.
+- Inspect operational processes.
+- Maintain medical records.
+- Make travel, accommodations, or entertainment arrangements for others.
+- Manage clerical or administrative activities.
+- Order materials, supplies, or equipment.
+- Perform administrative or clerical tasks.
+- Prepare business correspondence.
+- Prepare documentation for contracts, transactions, or regulatory compliance.
+- Prepare research or technical reports.
+- Read materials to determine needed actions.
+- Record information from meetings or other formal proceedings.
+- Schedule operational activities.
+- Sort mail.
+- Supervise clerical or administrative personnel.
+- Train personnel.
+- Transcribe spoken or written information.
--- a/references/tools.md
+++ b/references/tools.md
@@ -0,0 +1,107 @@
+# Tools & technology — scopist
+
+Source: O*NET 30.3, occupation 43-6011.00 (Executive Secretaries and Executive Administrative Assistants) — manual nearest-occupation mapping via ISCO group 3343; the official ESCO crosswalk has no entry for this ESCO occupation.
+
+| Software | Category | Hot technology |
+|---|---|---|
+| Adobe Acrobat | Document management software | yes |
+| Adobe Illustrator | Graphics or photo imaging software | yes |
+| Adobe InDesign | Desktop publishing software | yes |
+| Adobe Photoshop | Graphics or photo imaging software | yes |
+| Apple macOS | Operating system software | yes |
+| Cisco Webex | Video conferencing software | yes |
+| Facebook | Web page creation and editing software | yes |
+| Google Docs | Word processing software | yes |
+| Google Workspace software | Office suite software | yes |
+| Intuit QuickBooks | Accounting software | yes |
+| Microsoft Access | Data base user interface and query software | yes |
+| Microsoft Excel | Spreadsheet software | yes |
+| Microsoft Office software | Office suite software | yes |
+| Microsoft Outlook | Electronic mail software | yes |
+| Microsoft PowerPoint | Presentation software | yes |
+| Microsoft Project | Project management software | yes |
+| Microsoft SharePoint | Document management software | yes |
+| Microsoft Team Foundation Server | Project management software | yes |
+| Microsoft Visio | Process mapping and design software | yes |
+| Microsoft Word | Word processing software | yes |
+| Oracle PeopleSoft | Enterprise resource planning ERP software | yes |
+| Oracle Primavera Enterprise Project Portfolio Management | Project management software | yes |
+| SAP Concur | Accounting software | yes |
+| SAP software | Enterprise resource planning ERP software | yes |
+| Slack | Cloud-based data access and sharing software | yes |
+| Zoom | Video conferencing software | yes |
+| Adobe Contribute | Web page creation and editing software |  |
+| Aestiva Purchase Order | Procurement software |  |
+| Airtable | Data base user interface and query software |  |
+| Apple Keynote | Presentation software |  |
+| Appointment scheduling software | Calendar and scheduling software |  |
+| Blackbaud The Raiser's Edge | Customer relationship management CRM software |  |
+| Corel WordPerfect Office Suite | Office suite software |  |
+| Database software | Data base user interface and query software |  |
+| Dropbox | Cloud-based data access and sharing software |  |
+| Eko | Desktop communications software |  |
+| Epicor Vantage ERP | Enterprise resource planning ERP software |  |
+| Evernote | Word processing software |  |
+| Exact Software Macola ES | Enterprise resource planning ERP software |  |
+| FileMaker Pro | Data base user interface and query software |  |
+| Fishbowl Warehouse | Inventory management software |  |
+| Geac MPC Production | Enterprise resource planning ERP software |  |
+| Google Drive | Cloud-based data access and sharing software |  |
+| Google Meet | Video conferencing software |  |
+| Google Sites | Web page creation and editing software |  |
+| Google Slides | Presentation software |  |
+| Graphics software | Graphics or photo imaging software |  |
+| Human resource management software HRMS | Human resources software |  |
+| IBM Notes | Electronic mail software |  |
+| Inetsoft | Data base reporting software |  |
+| Intrado SchoolMessenger | Mobile messaging service software |  |
+| JamBoard | Graphics or photo imaging software |  |
+| KAPES | Analytical or scientific software |  |
+| LexisNexis | Information retrieval or search software |  |
+| LinkedIn | Web page creation and editing software |  |
+| LogMeIn GoToMeeting | Video conferencing software |  |
+| LogMeIn GoToWebinar | Network conferencing software |  |
+| Maynard PlanStaff Manager | Enterprise resource planning ERP software |  |
+| Micro Estimating FabPlan | Analytical or scientific software |  |
+| Microsoft Dynamics | Enterprise resource planning ERP software |  |
+| Microsoft Dynamics GP | Enterprise resource planning ERP software |  |
+| Microsoft OneNote | Word processing software |  |
+| Microsoft Publisher | Desktop publishing software |  |
+| Microsoft SharePoint Server | Document management software |  |
+| MicroStrategy Report Services | Enterprise resource planning ERP software |  |
+| MTI Systems Costimator JS | Analytical or scientific software |  |
+| Oracle E-Business Suite Financials | Financial analysis software |  |
+| Oracle PeopleSoft Financials | Enterprise resource planning ERP software |  |
+| ParentSquare | Desktop communications software |  |
+| PCC EHR | Medical software |  |
+| PCC Pediatric Partner | Medical software |  |
+| PRONTO Xi | Enterprise resource planning ERP software |  |
+| ProQuest RefWorks | Data base user interface and query software |  |
+| ProQuest RefWorks RefShare | Web page creation and editing software |  |
+| Questek Humanis | Human resources software |  |
+| Records management systems | Document management software |  |
+| Sage 50 Accounting | Accounting software |  |
+| Sage Peachtree Premium Accounting for Manufacturing | Accounting software |  |
+| Slido interaction software | Network conferencing software |  |
+| SmugMug Flickr | Graphics or photo imaging software |  |
+| Social media sites | Web page creation and editing software |  |
+| SYSPRO business software | Enterprise resource planning ERP software |  |
+| Transcription software | Word processing software |  |
+| Web browser software | Internet browser software |  |
+| Web conferencing software | Video conferencing software |  |
+| Work Technology WorkTech Time | Time accounting software |  |
+| Workbrain Employee Scheduling | Calendar and scheduling software |  |
+| Workbrain Time and Attendance | Time accounting software |  |
+| Workflow International Deskflow Enterprise | Human resources software |  |
+
+<!-- market-evidence -->
+
+## Market evidence (job-ad analysis, 16 ads, as of 2026-07-19)
+
+Share of analyzed job ads mentioning the item (threshold ≥ 20 %). Source: JSearch/Adzuna APIs.
+
+### Tools
+
+- CAT software — **19 %**
+
+<!-- market-evidence -->