skills-core/zoo-curator
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
main
zoo-curator/references/ai-skills.md
skillfactor-pipeline 8f7e5642a6 feat: zoo-curator skill package v0.1.0
2026-08-14 16:42:32 +02:00

38 KiB
Raw Permalink Blame History

External AI agent skills — zoo-curator

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 (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
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

Source: wshobson/agents

Skill Tier What it adds Upstream
team-collaboration-dx-optimizer (agent) adjacent Developer Experience specialist. Improves tooling, setup, and workflows. Use PROACTIVELY when setting up new projects, after team feedback, or when development friction is noticed. source

Source: a5c-ai/babysitter

Skill Tier What it adds Upstream
translation-management adjacent Integration with translation management systems and i18n workflows. Connect with Crowdin, Transifex, Weblate, manage translation memory, synchronize glossaries, and automate localization pipelines. source
vulkan-compute adjacent Vulkan compute shader development and pipeline configuration. Generate GLSL/HLSL compute shaders, compile to SPIR-V, configure compute pipelines, manage descriptor sets and resource bindings, implement memory barriers and synchronization. source
context-engineering adjacent Context window monitoring and budget management. Keeps orchestrator at 15-30% context usage while subagents get full 200k tokens. Provides warnings at thresholds, context-aware summarization triggers, and wave-level budget planning. source
nvenc-nvdec adjacent NVIDIA hardware video encoding/decoding integration. Configure NVENC encoding parameters, set up NVDEC decoding pipelines, handle codec configurations, integrate with CUDA for pre/post processing, and manage video memory surfaces. source
vector-memory adjacent HNSW vector search for pattern similarity retrieval and knowledge graph maintenance with PageRank scoring, community detection, and 3-tier memory management. source

Source: aaron-he-zhu/aaron-marketing-skills

Skill Tier What it adds Upstream
memory-management core Use when the user asks to "remember project context", review saved findings, initialize runtime memory, archive stale work, reconcile notes, or erase a subject; manages authorized HOT/WARM/COLD working memory across all disciplines while … source

Source: affaan-m/everything-claude-code

Skill Tier What it adds Upstream
knowledge-ops adjacent Knowledge base management, ingestion, sync, and retrieval across multiple storage layers (local files, MCP memory, vector stores, Git repos). Use when the user wants to save, organize, sync, deduplicate, or search across their knowledge … source
agentic-os adjacent 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

Source: alirezarezvani/claude-skills

Skill Tier What it adds Upstream
social-media-manager adjacent When the user wants to develop social media strategy, plan content calendars, manage community engagement, or grow their social presence across platforms. Also use when the user mentions 'social media strategy,' 'social calendar,' … source
ceo-advisor adjacent Executive leadership guidance for strategic decision-making, organizational development, and stakeholder management. Use when planning strategy, preparing board presentations, managing investors, developing organizational culture, making … source
founder-coach adjacent Personal leadership development for founders and first-time CEOs. Covers founder archetype identification, delegation frameworks, energy management, CEO calendar audits, leadership style evolution, blind spot identification, imposter … source

Source: basicmachines-co/basic-memory

Skill Tier What it adds Upstream
memory-lifecycle adjacent Manage entity status transitions in Basic Memory: archive completed work, move notes between status folders, update frontmatter, and handle edge cases. Use when marking items complete, archiving old entities, or managing any folder-based … source
memory-schema adjacent Schema lifecycle management for Basic Memory: discover unschemaed notes, infer schemas, create and edit schema definitions, validate notes, and detect drift. Use when working with structured note types (Task, Person, Meeting, etc.) to … source
memory-tasks adjacent 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

Source: brycewang-stanford/Auto-Empirical-Research-Skills

Skill Tier What it adds Upstream
hud core Diverga HUD (Heads-Up Display) management skill. Configure and manage the research project statusline display. Supports multiple presets: research, checkpoint, memory, minimal. Triggers: "hud", "statusline", "display settings source
research-lit core Search and analyze research papers, find related work, summarize key ideas. Use when user says "find papers", "related work", "literature review", "what does this paper say", or needs to understand academic papers. source
diverga-memory core Diverga Memory System v7.0 - Context-persistent research support with checkpoint auto-trigger and cross-session continuity. Triggers: memory, remember, context, recall, checkpoint, decision, persist, 기억, 맥락, 세션, 체크포인트 source

Source: Chachamaru127/claude-code-harness

Skill Tier What it adds Upstream
memory adjacent Manage SSOT, memory, and cross-tool memory search. Guardian of decisions.md and patterns.md. Use when user mentions memory, SSOT, decisions.md, patterns.md, merging, migration, SSOT promotion, sync memory, save learnings, memory search, … source

Source: davepoon/buildwithclaude

Skill Tier What it adds Upstream
google-calendar-automation adjacent Automate Google Calendar events, scheduling, availability checks, and attendee management via Rube MCP (Composio). Create events, find free slots, manage attendees, and list calendars programmatically. source
googlesheets-automation adjacent Automate Google Sheets operations (read, write, format, filter, manage spreadsheets) via Rube MCP (Composio). Read/write data, manage tabs, apply formatting, and search rows programmatically. source
outlook-calendar-automation adjacent Automate Outlook Calendar tasks via Rube MCP (Composio): create events, manage attendees, find meeting times, and handle invitations. Always search tools first for current schemas. source

Source: davila7/claude-code-templates

Skill Tier What it adds Upstream
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
optimizing-attention-flash core Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster … source
quantizing-models-bitsandbytes core Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit … source
unsloth core Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization source
treatment-plans adjacent Generate concise (3-4 page), focused medical treatment plans in LaTeX/PDF format for all clinical specialties. Supports general medical treatment, rehabilitation therapy, mental health care, chronic disease management, perioperative care, … source
it-operations adjacent Manages IT infrastructure, monitoring, incident response, and service reliability. Provides frameworks for ITIL service management, observability strategies, automation, backup/recovery, capacity planning, and operational excellence … source
agent-memory-mcp adjacent A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions). source
c-pro adjacent Write efficient C code with proper memory management, pointer source
context-window-management adjacent Strategies for managing LLM context windows including summarization, trimming, routing, and avoiding context rot Use when: context window, token limit, context management, context engineering, long context. source

Source: eduardo-sl/go-agent-skills

Skill Tier What it adds Upstream
go-troubleshooting core Diagnose runtime problems in Go programs: panics and stack traces, deadlocks, goroutine leaks, memory leaks, OOM kills, race reports, and debugging with delve and pprof. Use when: "debug this panic", "read this stack trace", "deadlock", … source

Source: foryourhealth111-pixel/Vibe-Skills

Skill Tier What it adds Upstream
unsloth core Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization source
treatment-plans adjacent Generate concise (3-4 page), focused medical treatment plans in LaTeX/PDF format for all clinical specialties. Supports general medical treatment, rehabilitation therapy, mental health care, chronic disease management, perioperative care, … source

Source: giuseppe-trisciuoglio/developer-kit

Skill Tier What it adds Upstream
memory-md-management adjacent Provides comprehensive memory file management capabilities including auditing, quality assessment, and targeted improvements for files such as CLAUDE.md. Use when user asks to check, audit, update, improve, fix, maintain, or validate … source

Source: googleworkspace/cli

Skill Tier What it adds Upstream
gws-calendar adjacent Google Calendar: Manage calendars and events. source

Source: jeremylongshore/claude-code-plugins-plus-skills

Skill Tier What it adds Upstream
hyperflow-status core Hyperflow project status. Use to see current hyperflow state — "what is hyperflow doing", "show task progress", "where are we". Read-only — reports in-flight tasks, memory count, and progress. Never modifies state or runs work. source
windsurf-cascade-context adjacent Manage Cascade context window and memory for complex projects. Activate when users mention "cascade context", "ai memory", "context management", "large codebase navigation", or "multi-session development". Handles context optimization and … source
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
presentation-slide-outliner adjacent Manage presentation slide outliner operations. Auto-activating skill for Visual Content. Triggers on: presentation slide outliner, presentation slide outliner Part of the Visual Content skill category. Use when working with presentation … source
apify-cost-tuning adjacent Optimize Apify platform costs through memory tuning, compute unit management, and proxy budgeting. Use when analyzing Apify billing, reducing Actor run costs, or implementing usage monitoring and budget alerts. Trigger: "apify cost", … source
cursor-performance-tuning adjacent Optimize Cursor IDE performance: reduce memory usage, speed up indexing, tune AI features, and manage extensions for large codebases. Triggers on "cursor performance", "cursor slow", "cursor optimization", "cursor memory", "speed up … source
gamma-core-workflow-b adjacent Generate from templates, retrieve exports, and manage sharing via Gamma API. Use when creating content from template gammas, downloading PDF/PPTX/PNG exports, or configuring sharing and folder organization. Trigger: "gamma template", … source
notion-load-scale adjacent High-volume Notion operations: parallel requests within 3 req/sec, worker queues, database pagination at scale, incremental sync for large workspaces, and memory management for bulk operations. Trigger with phrases like "notion scale", … source
cursor-context-management adjacent Optimize context window usage in Cursor with @-mentions, context pills, and conversation strategy. Triggers on "cursor context", "context window", "context limit", "cursor memory", "context management", "@-mentions", "context pills". source

Source: jezweb/claude-skills

Skill Tier What it adds Upstream
shopify-products adjacent Create and manage Shopify products via the Admin GraphQL API or CSV import. Workflow: gather data, choose method, execute, verify. Use whenever the user wants to add products to Shopify, bulk-import a catalog from CSV/spreadsheet/URL, … source

Source: K-Dense-AI/claude-scientific-skills

Skill Tier What it adds Upstream
treatment-plans adjacent Generate concise (3-4 page), focused medical treatment plans in LaTeX/PDF format for all clinical specialties. Supports general medical treatment, rehabilitation therapy, mental health care, chronic disease management, perioperative care, … source

Source: K-Dense-AI/scientific-agent-skills

Skill Tier What it adds Upstream
treatment-plans adjacent Generate concise (3-4 page), focused medical treatment plans in LaTeX/PDF format for all clinical specialties. Supports general medical treatment, rehabilitation therapy, mental health care, chronic disease management, perioperative care, … source

Source: memvid/claude-brain

Skill Tier What it adds Upstream
memory adjacent Claude Mind - Search and manage Claude's persistent memory stored in a single portable .mv2 file source
mind adjacent Claude Mind - Search and manage Claude's persistent memory stored in a single portable .mv2 file source

Source: mohitagw15856/pm-claude-skills

Skill Tier What it adds Upstream
professional-brain core Maintain a durable, local markdown memory ('brain') of your product context, decisions, hypotheses, and stakeholders that other skills read from and write back to. Use when asked to set up a brain, ingest notes/artifacts into memory, … source

Source: mukul975/Anthropic-Cybersecurity-Skills

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

Source: nexu-io/open-design

Skill Tier What it adds Upstream
pptx core Read, generate, and adjust PowerPoint slides, layouts, and templates. Useful for executive decks, training material, and product reviews. source

Source: OpenRaiser/NanoResearch

Skill Tier What it adds Upstream
unsloth core Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization source

Source: Orchestra-Research/AI-research-SKILLs

Skill Tier What it adds Upstream
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
optimizing-attention-flash core Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster … source
pytorch-fsdp2 core Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use when models exceed single-GPU memory or when you need DTensor-based sharding with … source
quantizing-models-bitsandbytes core Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit … source
unsloth core Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization source

Source: rohitg00/skillkit

Skill Tier What it adds Upstream
handoff-protocols core Manages work transitions between team members or agents by creating structured handoff documents, summarizing project status, documenting key decisions, blockers, and open questions, and generating onboarding briefs. Use when someone needs … source

Source: ruvnet/claude-code-flow

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
memory-management adjacent 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
rvf-manage adjacent Manage RVF (Ruflo Vector Format) files for portable agent memory and cross-platform transfer source
AgentDB Memory Patterns adjacent 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

Source: ruvnet/ruflo

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
memory-management adjacent 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
rvf-manage adjacent Manage RVF (Ruflo Vector Format) files for portable agent memory and cross-platform transfer source
AgentDB Memory Patterns adjacent 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

Source: samber/cc-skills-golang

Skill Tier What it adds Upstream
golang-security adjacent 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

Source: sanjay3290/ai-skills

Skill Tier What it adds Upstream
gmail adjacent Interact with Gmail - search emails, read messages, send emails, create drafts, and manage labels. Use when user asks to: search email, read email, send email, create email draft, mark as read, archive email, star email, or manage Gmail … source
google-slides adjacent Read and write Google Slides presentations - get text, find presentations, create presentations, add slides, replace text, and manage slide content. Use when user asks to: read a presentation, create slides, find slides, add a slide, … source

Source: silverstein/minutes

Skill Tier What it adds Upstream
minutes-cleanup adjacent Manage old recordings — find large files, archive old meetings, delete processed originals. Use when the user says "clean up recordings", "how much space are meetings using", "delete old recordings", "archive meetings", "manage meeting … source

Source: wanshuiyin/Auto-claude-code-research-in-sleep

Skill Tier What it adds Upstream
research-lit core Search and analyze research papers, find related work, summarize key ideas. Use when user says "find papers", "related work", "literature review", "what does this paper say", or needs to understand academic papers. source

Source: zechenzhangAGI/AI-research-SKILLs

Skill Tier What it adds Upstream
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
optimizing-attention-flash core Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster … source
pytorch-fsdp2 core Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use when models exceed single-GPU memory or when you need DTensor-based sharding with … source
quantizing-models-bitsandbytes core Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit … source
unsloth core Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization source