Files
mediator/references/ai-skills.md
2026-08-14 17:34:34 +02:00

355 lines
38 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# External AI agent skills — mediator
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: wshobson/agents
- Repository: [https://github.com/wshobson/agents](https://github.com/wshobson/agents) (commit `6fd3247`, retrieved 2026-07-14)
- License: MIT (c) Seth Hobson
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
| `gdpr-data-handling` | core | Implement GDPR-compliant data handling with consent management, data subject rights, and privacy by design. Use when building systems that process EU personal data, implementing privacy controls, or conducting GDPR compliance reviews. | [source](https://github.com/wshobson/agents/tree/main/plugins/hr-legal-compliance/skills/gdpr-data-handling) |
| `employment-contract-templates` | adjacent | Create employment contracts, offer letters, and HR policy documents following legal best practices. Use when drafting employment agreements, creating HR policies, or standardizing employment documentation. | [source](https://github.com/wshobson/agents/tree/main/plugins/hr-legal-compliance/skills/employment-contract-templates) |
## 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 |
|---|---|---|---|
| `policy-management` | core | Manage corporate policy lifecycle from drafting through compliance | [source](https://github.com/a5c-ai/babysitter/tree/44a5d58b/library/specializations/domains/business/legal/skills/policy-management) |
| `translation-management` | core | Integration with translation management systems and i18n workflows. Connect with Crowdin, Transifex, Weblate, manage translation memory, synchronize glossaries, and automate localization pipelines. | [source](https://github.com/a5c-ai/babysitter/tree/44a5d58b/library/specializations/technical-documentation/skills/translation-management) |
| `gdpr-compliance-automator` | core | GDPR compliance assessment and automation for data mapping, consent management, DSAR handling, and privacy impact assessments | [source](https://github.com/a5c-ai/babysitter/tree/44a5d58b/library/specializations/security-compliance/skills/gdpr-compliance-automator) |
| `interview-questions` | core | Generate competency-based and behavioral interview questions with legal compliance validation | [source](https://github.com/a5c-ai/babysitter/tree/44a5d58b/library/specializations/domains/business/human-resources/skills/interview-questions) |
| `license-compliance-checker` | core | Automated license compliance verification for dependencies to ensure legal compliance during migration | [source](https://github.com/a5c-ai/babysitter/tree/44a5d58b/library/specializations/code-migration-modernization/skills/license-compliance-checker) |
| `cultural-policy-analysis` | core | Analyze cultural policies, assess community cultural needs, and develop evidence-based recommendations for arts funding and cultural development | [source](https://github.com/a5c-ai/babysitter/tree/44a5d58b/library/specializations/domains/social-sciences-humanities/arts-culture/skills/cultural-policy-analysis) |
| `policy-communication` | core | Translate research findings into accessible policy briefs, presentations, and stakeholder communications | [source](https://github.com/a5c-ai/babysitter/tree/44a5d58b/library/specializations/domains/social-sciences-humanities/social-sciences/skills/policy-communication) |
| `accreditation-tracer-simulation` | core | Simulate Joint Commission tracer methodology to assess compliance with accreditation standards across patient care processes and support systems | [source](https://github.com/a5c-ai/babysitter/tree/44a5d58b/library/specializations/domains/social-sciences-humanities/healthcare/skills/accreditation-tracer-simulation) |
| `contract-analyzer` | core | Contract analysis and negotiation support skill with clause extraction and risk identification | [source](https://github.com/a5c-ai/babysitter/tree/44a5d58b/library/specializations/domains/business/supply-chain/skills/contract-analyzer) |
| `evidence-justification-assessment` | core | Evaluate epistemic warrant, assess evidence quality and relevance, apply epistemic standards appropriate to different domains, and identify sources of knowledge | [source](https://github.com/a5c-ai/babysitter/tree/44a5d58b/library/specializations/domains/social-sciences-humanities/philosophy/skills/evidence-justification-assessment) |
## 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) |
| `hexagonal-architecture` | core | Design, implement, and refactor Ports & Adapters systems with clear domain boundaries, dependency inversion, and testable use-case orchestration across TypeScript, Java, Kotlin, and Go services. | [source](https://github.com/affaan-m/everything-claude-code/tree/ed38744/skills/hexagonal-architecture) |
| `mle-workflow` | core | Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks. | [source](https://github.com/affaan-m/everything-claude-code/tree/ed38744/.agents/skills/mle-workflow) |
## Source: alirezarezvani/claude-skills
- Repository: [https://github.com/alirezarezvani/claude-skills](https://github.com/alirezarezvani/claude-skills) (commit `0241f43`, retrieved 2026-07-14)
- License: MIT
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
| `iso42001-specialist` | core | ISO/IEC 42001:2023 AI Management System (AIMS) specialist for compliance teams running internal audits. Three decisions: (1) Where are the gaps against Clauses 4-10 and what do we close first? (2) What goes in the AI risk register and … | [source](https://github.com/alirezarezvani/claude-skills/tree/0241f43/ra-qm-team/compliance-team-iso42001/skills/iso42001-specialist) |
## Source: basicmachines-co/basic-memory
- Repository: [https://github.com/basicmachines-co/basic-memory](https://github.com/basicmachines-co/basic-memory) (commit `53da71c`, retrieved 2026-07-14)
- License: custom (see upstream LICENSE)
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
| `memory-tasks` | core | Task management via Basic Memory schemas: create, track, and resume structured tasks that survive context compaction. Uses BM's schema system for uniform notes queryable through the knowledge graph. | [source](https://github.com/basicmachines-co/basic-memory/tree/53da71c/skills/memory-tasks) |
## Source: bitwize-music-studio/claude-ai-music-skills
- Repository: [https://github.com/bitwize-music-studio/claude-ai-music-skills](https://github.com/bitwize-music-studio/claude-ai-music-skills) (commit `96446de`, retrieved 2026-07-14)
- License: custom (see upstream LICENSE)
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
| `researchers-legal` | core | Researches court documents, indictments, plea agreements, and sentencing records. Use when the album subject involves legal proceedings or criminal cases. | [source](https://github.com/bitwize-music-studio/claude-ai-music-skills/tree/96446de/skills/researchers-legal) |
## 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 |
|---|---|---|---|
| `law-skills` | core | 9 legal research skills. Trigger: legal research, case law analysis, regulatory compliance. Design: legal databases, citation networks, and judicial analytics tools. | [source](https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/tree/85bf545/skills/43-wentorai-research-plugins/skills/domains/law) |
| `legal-research-guide` | core | Legal research methods, case law analysis, and compliance tools | [source](https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/tree/85bf545/skills/43-wentorai-research-plugins/skills/domains/law/legal-research-guide) |
| `legal-agent-skills-guide` | core | Agent skills collection for legal research and automation | [source](https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/tree/85bf545/skills/43-wentorai-research-plugins/skills/domains/law/legal-agent-skills-guide) |
| `visualize` | core | Create publication-quality figures that meet journal submission standards. APA 7th defaults with journal-specific overrides. Supports interaction plots, mediation path diagrams, forest plots, marginal effects, Johnson-Neyman plots, … | [source](https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/tree/85bf545/skills/61-phdemotions-research-methods/skills/visualize) |
## 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 |
|---|---|---|---|
| `ios-hig-design-guide` | core | Build, update, and apply iOS design specifications using Apple Human Interface Guidelines (HIG) source data. Use when a task asks for iOS UI/UX rules, Apple design standards, component behavior, accessibility constraints, interaction … | [source](https://github.com/davepoon/buildwithclaude/tree/3c94e0c/plugins/all-skills/skills/ios-hig-design-guide) |
## 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 |
|---|---|---|---|
| `microservices-patterns` | core | Master microservices architecture patterns including service boundaries, inter-service communication, data management, and resilience patterns for building distributed systems. | [source](https://github.com/davila7/claude-code-templates/tree/fa79251/cli-tool/components/skills/development/microservices-patterns) |
| `agent-memory-mcp` | core | A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions). | [source](https://github.com/davila7/claude-code-templates/tree/fa79251/cli-tool/components/skills/ai-research/agent-memory-mcp) |
| `internet-court` | core | The trust layer for agent-to-agent commerce — natural-language mandates, delegated permissions (ERC-7710), x402 payments, escrow, and dispute resolution as one open, catch-all skill. Use for agent mandates, delegated permissions, GenLayer … | [source](https://github.com/davila7/claude-code-templates/tree/fa79251/cli-tool/components/skills/development/internet-court) |
| `evaluating-llms-harness` | core | Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by … | [source](https://github.com/davila7/claude-code-templates/tree/fa79251/cli-tool/components/skills/ai-research/evaluation-lm-evaluation-harness) |
| `gptq` | core | Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs | [source](https://github.com/davila7/claude-code-templates/tree/fa79251/cli-tool/components/skills/ai-research/optimization-gptq) |
## 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 |
|---|---|---|---|
| `evaluating-llms-harness` | core | Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by | [source](https://github.com/foryourhealth111-pixel/Vibe-Skills/tree/34429a8/bundled/skills/evaluating-llms-harness) |
## 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 |
|---|---|---|---|
| `125-java-concurrency` | core | Use when you need to apply Java concurrency best practices including thread safety fundamentals, ExecutorService thread pool management, concurrent design patterns like Producer-Consumer, asynchronous programming with CompletableFuture, | [source](https://github.com/jabrena/plinth/tree/065eae8/skills/125-java-concurrency) |
## Source: jeffallan/claude-skills
- Repository: [https://github.com/jeffallan/claude-skills](https://github.com/jeffallan/claude-skills) (commit `e8be415`, retrieved 2026-07-14)
- License: MIT
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
| `microservices-architect` | core | Designs distributed system architectures, decomposes monoliths into bounded-context services, recommends communication patterns, and produces service boundary diagrams and resilience strategies. Use when designing distributed systems, | [source](https://github.com/jeffallan/claude-skills/tree/e8be415/skills/microservices-architect) |
| `fine-tuning-expert` | core | Use when fine-tuning LLMs, training custom models, or adapting foundation models for specific tasks. Invoke for configuring LoRA/QLoRA adapters, preparing JSONL training datasets, setting hyperparameters for fine-tuning runs, adapter | [source](https://github.com/jeffallan/claude-skills/tree/e8be415/skills/fine-tuning-expert) |
## 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 |
|---|---|---|---|
| `shopify-sdk-patterns` | core | Apply production-ready patterns for @shopify/shopify-api including typed GraphQL clients, session management, and retry logic. Use when implementing Shopify integrations, refactoring SDK usage, or establishing team coding standards for | [source](https://github.com/jeremylongshore/claude-code-plugins-plus-skills/tree/e112938a/plugins/saas-packs/shopify-pack/skills/shopify-sdk-patterns) |
| `apollo-data-handling` | core | Apollo.io data management and compliance. Use when handling contact data, implementing GDPR compliance, or managing data exports and retention. Trigger with phrases like "apollo data", "apollo gdpr", "apollo compliance", "apollo data | [source](https://github.com/jeremylongshore/claude-code-plugins-plus-skills/tree/e112938a/plugins/saas-packs/apollo-pack/skills/apollo-data-handling) |
| `flexport-data-handling` | core | Implement data handling for Flexport supply chain data including PII redaction, shipment data retention, GDPR compliance, and secure document management. Trigger: "flexport data handling", "flexport PII", "flexport GDPR", "flexport data | [source](https://github.com/jeremylongshore/claude-code-plugins-plus-skills/tree/e112938a/plugins/saas-packs/flexport-pack/skills/flexport-data-handling) |
| `instantly-data-handling` | core | Implement Instantly.ai lead data management, GDPR/CAN-SPAM compliance, and list operations. Use when handling lead imports, managing block lists, implementing unsubscribe flows, or ensuring compliance with email regulations. Trigger with | [source](https://github.com/jeremylongshore/claude-code-plugins-plus-skills/tree/e112938a/plugins/saas-packs/instantly-pack/skills/instantly-data-handling) |
| `posthog-data-handling` | core | PostHog PII handling, GDPR compliance, consent management, data deletion, property sanitization, and privacy-safe analytics configuration. Trigger: "posthog data", "posthog PII", "posthog GDPR", "posthog data retention", "posthog privacy", | [source](https://github.com/jeremylongshore/claude-code-plugins-plus-skills/tree/e112938a/plugins/saas-packs/posthog-pack/skills/posthog-data-handling) |
| `supabase-data-handling` | core | Implement GDPR/CCPA compliance with Supabase: RLS for data isolation, user deletion via auth.admin.deleteUser(), data export via SQL, PII column management, backup/restore workflows, and retention policies. Use when handling sensitive | [source](https://github.com/jeremylongshore/claude-code-plugins-plus-skills/tree/e112938a/plugins/saas-packs/supabase-pack/skills/supabase-data-handling) |
| `twinmind-data-handling` | core | 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) |
| `speak-core-workflow-b` | core | Execute Speak secondary workflow: Pronunciation Training with phoneme-level analysis. Use when implementing pronunciation drills, speech scoring, or targeted pronunciation improvement features. Trigger with phrases like "speak | [source](https://github.com/jeremylongshore/claude-code-plugins-plus-skills/tree/e112938a/plugins/saas-packs/speak-pack/skills/speak-core-workflow-b) |
| `adobe-data-handling` | core | Implement data handling for Adobe APIs including PII redaction in logs, Firefly content policy compliance, PDF document data classification, and GDPR/CCPA data subject access requests via Adobe Privacy Service. Trigger with phrases like | [source](https://github.com/jeremylongshore/claude-code-plugins-plus-skills/tree/e112938a/plugins/saas-packs/adobe-pack/skills/adobe-data-handling) |
| `customerio-security-basics` | core | Apply Customer.io security best practices. Use when implementing secure credential storage, PII handling, webhook signature verification, or GDPR/CCPA compliance. Trigger: "customer.io security", "customer.io pii", "secure customer.io", | [source](https://github.com/jeremylongshore/claude-code-plugins-plus-skills/tree/e112938a/plugins/saas-packs/customerio-pack/skills/customerio-security-basics) |
| `design-everyday-things` | core | Apply foundational design principles: affordances, signifiers, constraints, feedback, and conceptual models. Use when the user mentions "why is this confusing", "affordance", "error prevention", "discoverability", "human-centered design", | [source](https://github.com/jeremylongshore/claude-code-plugins-plus-skills/tree/e112938a/plugins/design/wondelai-design-everyday-things) |
| `find-law-firm` | core | Use whenever the user wants to find, shortlist, vet, or enrich US B2B law firms corporate, IP/patent, M&A and securities, employment, commercial litigation, regulatory/compliance, data privacy/cyber, real estate, and tax. Triggers on | [source](https://github.com/jeremylongshore/claude-code-plugins-plus-skills/tree/e112938a/plugins/mcp/servicegraph/skills/find-law-firm) |
## 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 |
|---|---|---|---|
| `clause-explainer` | core | Explain a contract clause in plain English what it means, who it favours, the realistic risk, and what to negotiate. Use when asked what a clause means, to decode legal language, explain a term in a contract, or assess whether a | [source](https://github.com/mohitagw15856/pm-claude-skills/tree/876fa30/plugins/pm-legal/skills/clause-explainer) |
| `microservices-decomposition` | core | Design a microservices decomposition for a monolith or new system, defining service boundaries, ownership, communication patterns, and migration plan. Use when asked to decompose a monolith, define service boundaries, design a | [source](https://github.com/mohitagw15856/pm-claude-skills/tree/876fa30/plugins/pm-engineering/skills/microservices-decomposition) |
| `nda-analyser` | core | Analyses a Non-Disclosure Agreement clause by clause and flags unusual terms, one-sided provisions, and negotiation points. Use when reviewing an NDA, mutual NDA, confidentiality agreement, or non-disclosure deed before signing or | [source](https://github.com/mohitagw15856/pm-claude-skills/tree/876fa30/plugins/pm-legal/skills/nda-analyser) |
| `vendor-contract-checklist` | core | Review a vendor/SaaS contract against a practical checklist before you sign. Use when asked to review a vendor contract, check a SaaS/MSA/subscription agreement, flag risky terms, or prepare negotiation points before signing. Produces a | [source](https://github.com/mohitagw15856/pm-claude-skills/tree/876fa30/plugins/pm-operations/skills/vendor-contract-checklist) |
## 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-outlook-pst-for-email-forensics` | core | Analyze Microsoft Outlook PST and OST files for email forensic evidence including message content, headers, attachments, deleted items, and metadata using libpff, pst-utils, and forensic email analysis tools for legal investigations and | [source](https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/673da1f/skills/analyzing-outlook-pst-for-email-forensics) |
| `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) |
| `implementing-iso-27001-information-security-management` | core | ISO/IEC 27001:2022 is the international standard for establishing, implementing, maintaining, and continually improving an Information Security Management System (ISMS). This skill covers the complete | [source](https://github.com/mukul975/Anthropic-Cybersecurity-Skills/tree/673da1f/skills/implementing-iso-27001-information-security-management) |
## Source: muratcankoylan/Agent-Skills-for-Context-Engineering
- Repository: [https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering](https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering) (commit `c578e85`, retrieved 2026-07-14)
- License: MIT
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
| `memory-systems` | core | This skill should be used for persistent semantic memory in agent systems: cross-session knowledge retention, entity tracking, temporal validity, graph or vector retrieval, memory consolidation, and memory benchmark selection. Route | [source](https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering/tree/c578e85/skills/memory-systems) |
## 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 |
|---|---|---|---|
| `hps-bauhaus` | core | A visual-design fundamentals course for new brand designers grid, type, color, and the exercises that build the eye. Built as a decision-grade professional training deck for junior designers, new hires. | [source](https://github.com/nexu-io/open-design/tree/4b66023/plugins/_official/examples/hps-bauhaus) |
| `html-ppt-zhangzara-stencil-tablet` | core | A workplace-safety compliance review for a manufacturing regulator findings, the evidence chain, and the corrective mandate. Built as a decision-grade policy briefing deck for regulator, plant leadership. | [source](https://github.com/nexu-io/open-design/tree/4b66023/design-templates/html-ppt-zhangzara-stencil-tablet) |
## 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 |
|---|---|---|---|
| `evaluating-llms-harness` | core | Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by | [source](https://github.com/OpenRaiser/NanoResearch/tree/7144364/skills/vendor-ai-research/lm-evaluation-harness) |
## 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 |
|---|---|---|---|
| `evaluating-llms-harness` | core | Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by | [source](https://github.com/Orchestra-Research/AI-research-SKILLs/tree/773a529/11-evaluation/lm-evaluation-harness) |
| `gptq` | core | Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs | [source](https://github.com/Orchestra-Research/AI-research-SKILLs/tree/773a529/10-optimization/gptq) |
## Source: oubakiou/mdxg-redline
- Repository: [https://github.com/oubakiou/mdxg-redline](https://github.com/oubakiou/mdxg-redline) (commit `716ddb1`, retrieved 2026-07-14)
- License: MIT
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
| `md-review` | core | Run the standard markdown review loop end-to-end with the mdxg-redline CLI: send a markdown document to a human reviewer, wait (via Bash polling) for the feedback.json they export, then apply their location-aware inline comments back into | [source](https://github.com/oubakiou/mdxg-redline/tree/716ddb1/skills/md-review) |
## Source: ruvnet/claude-code-flow
- Repository: [https://github.com/ruvnet/claude-code-flow](https://github.com/ruvnet/claude-code-flow) (commit `73914bd`, retrieved 2026-07-14)
- License: MIT
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
| `Hooks Automation` | core | Automated coordination, formatting, and learning from Claude Code operations using intelligent hooks with MCP integration. Includes pre$post task hooks, session management, Git integration, memory coordination, and neural pattern training | [source](https://github.com/ruvnet/claude-code-flow/tree/73914bd/.agents/skills/hooks-automation) |
| `memory-management` | core | AgentDB memory system with HNSW vector search. Provides 150x-12,500x faster pattern retrieval, persistent storage, and semantic search capabilities for learning and knowledge management. Use when: need to store successful patterns, | [source](https://github.com/ruvnet/claude-code-flow/tree/73914bd/.agents/skills/memory-management) |
| `AgentDB Memory Patterns` | core | Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants. | [source](https://github.com/ruvnet/claude-code-flow/tree/73914bd/.agents/skills/agentdb-memory-patterns) |
## Source: ruvnet/ruflo
- Repository: [https://github.com/ruvnet/ruflo](https://github.com/ruvnet/ruflo) (commit `73914bd`, retrieved 2026-07-14)
- License: MIT
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
| `Hooks Automation` | core | Automated coordination, formatting, and learning from Claude Code operations using intelligent hooks with MCP integration. Includes pre$post task hooks, session management, Git integration, memory coordination, and neural pattern training | [source](https://github.com/ruvnet/ruflo/tree/73914bd/.agents/skills/hooks-automation) |
| `memory-management` | core | AgentDB memory system with HNSW vector search. Provides 150x-12,500x faster pattern retrieval, persistent storage, and semantic search capabilities for learning and knowledge management. Use when: need to store successful patterns, | [source](https://github.com/ruvnet/ruflo/tree/73914bd/.agents/skills/memory-management) |
| `AgentDB Memory Patterns` | core | Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants. | [source](https://github.com/ruvnet/ruflo/tree/73914bd/.agents/skills/agentdb-memory-patterns) |
## Source: samber/cc-skills-golang
- Repository: [https://github.com/samber/cc-skills-golang](https://github.com/samber/cc-skills-golang) (commit `4881c01`, retrieved 2026-07-14)
- License: MIT
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
| `golang-security` | core | Security best practices and vulnerability prevention for Golang. Covers injection (SQL, command, XSS), cryptography, filesystem safety, network security, cookies, secrets management, memory safety, and logging. Apply when writing, | [source](https://github.com/samber/cc-skills-golang/tree/4881c01/skills/golang-security) |
## Source: sboghossian/master-claude-for-legal
- Repository: [https://github.com/sboghossian/master-claude-for-legal](https://github.com/sboghossian/master-claude-for-legal) (commit `b5dde5f`, retrieved 2026-07-14)
- License: MIT
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
| `master-claude-for-legal` | core | Master skill for legal teams using Claude. Loads the right reference for the user's question (privilege configuration, MCP hardening, MCP connector catalog, practice-area plugins, Microsoft 365 surfaces, managed agents, cold-start | [source](https://github.com/sboghossian/master-claude-for-legal/tree/b5dde5f) |
## Source: secondsky/claude-skills
- Repository: [https://github.com/secondsky/claude-skills](https://github.com/secondsky/claude-skills) (commit `c4889f6`, retrieved 2026-07-14)
- License: MIT
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
| `microservices-patterns` | core | Design microservices architectures with service boundaries, event-driven communication, and resilience patterns. Use when building distributed systems, decomposing monoliths, or implementing microservices. | [source](https://github.com/secondsky/claude-skills/tree/c4889f6/plugins/microservices-patterns/skills/microservices-patterns) |
| `recommendation-system` | core | Deploy production recommendation systems with feature stores, caching, A/B testing. Use for personalization APIs, low latency serving, or encountering cache invalidation, experiment tracking, quality monitoring issues. | [source](https://github.com/secondsky/claude-skills/tree/c4889f6/plugins/recommendation-system/skills/recommendation-system) |
| `api-contract-testing` | core | Verifies API contracts between services using consumer-driven contracts, schema validation, and tools like Pact. Use when testing microservices communication, preventing breaking changes, or validating OpenAPI specifications. | [source](https://github.com/secondsky/claude-skills/tree/c4889f6/plugins/api-contract-testing/skills/api-contract-testing) |
## Source: Sushegaad/Claude-Skills-Governance-Risk-and-Compliance
- Repository: [https://github.com/Sushegaad/Claude-Skills-Governance-Risk-and-Compliance](https://github.com/Sushegaad/Claude-Skills-Governance-Risk-and-Compliance) (commit `71d8920`, retrieved 2026-07-14)
- License: MIT
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
| `gdpr-compliance` | core | Expert GDPR compliance assistant covering all four core workflows: (1) auditing code and systems for GDPR violations, (2) drafting GDPR-compliant documents such as privacy policies, Data Processing Agreements (DPAs), and consent notices, | [source](https://github.com/Sushegaad/Claude-Skills-Governance-Risk-and-Compliance/tree/71d8920/plugins/gdpr-compliance/skills/gdpr-compliance) |
## 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 |
|---|---|---|---|
| `compliance-patterns` | core | GDPR data handling, audit logging, data classification, retention policies, and consent management for regulatory compliance. | [source](https://github.com/vibeeval/vibecosystem/tree/cea9462/skills/compliance-patterns) |
| `gdpr-compliance` | core | GDPR compliance - data subject rights, lawful basis, DPIA, privacy by design, breach notification, consent management, cross-border transfers, PII masking | [source](https://github.com/vibeeval/vibecosystem/tree/cea9462/skills/gdpr-compliance) |
| `kvkk-compliance` | core | KVKK and GDPR compliance patterns - consent management, right to erasure, breach notification, audit logging, cookie consent, and data classification. | [source](https://github.com/vibeeval/vibecosystem/tree/cea9462/skills/kvkk-compliance) |
## Source: wondelai/skills
- Repository: [https://github.com/wondelai/skills](https://github.com/wondelai/skills) (commit `326b380`, retrieved 2026-07-14)
- License: MIT
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
| `design-everyday-things` | core | Apply foundational design principles: affordances, signifiers, constraints, feedback, and conceptual models. Use when the user mentions "why is this confusing", "affordance", "error prevention", "discoverability", "human-centered design", | [source](https://github.com/wondelai/skills/tree/326b380/design-everyday-things) |
## Source: yaojingang/yao-meta-skill
- Repository: [https://github.com/yaojingang/yao-meta-skill](https://github.com/yaojingang/yao-meta-skill) (commit `4eb11f9`, retrieved 2026-07-14)
- License: MIT
| Skill | Tier | What it adds | Upstream |
|---|---|---|---|
| `incident-command-governor` | core | Build governed incident command packets. Use when asked to standardize incident review, run severity assessment, or assemble incident communication. | [source](https://github.com/yaojingang/yao-meta-skill/tree/4eb11f9/examples/governed-incident-command/generated-skill) |
## 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 |
|---|---|---|---|
| `regulatory-audit-generator` | core | Builds compliance checklists for business scenarios involving GDPR, PIPL, or advertising/data laws. Outputs a structured checklist with check items, legal basis, risk levels, and actionable recommendations. Triggered by requests like \"run | [source](https://github.com/zebbern/claude-code-guide/tree/d2c5280/skills/regulatory-audit-generator) |
## 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 |
|---|---|---|---|
| `evaluating-llms-harness` | core | Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by | [source](https://github.com/zechenzhangAGI/AI-research-SKILLs/tree/773a529/11-evaluation/lm-evaluation-harness) |
| `gptq` | core | Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs | [source](https://github.com/zechenzhangAGI/AI-research-SKILLs/tree/773a529/10-optimization/gptq) |