Skills.

Give your AI a better way to work.

A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.

Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.

Category: Docs & knowledge

4,535 results · page 85 of 152

  • ontology-generatorSkillDocs & knowledge

    Generate comprehensive ontological knowledge graphs in [[wikilinks]] syntax for InfraNodus visualization. Use when the user requests to create an ontology, extract entities and relationships from text, or generate knowledge graph structures. Handles both topic-based ontology generation and entity ex

    Ready to connect★ 119

    github.com/infranodus/skills119 stars

    View details
  • readme-reviewerSkillDocs & knowledge

    Review a codebase and generate or update its README.md according to best practices. The skill performs static analysis of the project structure, dependencies, scripts, and existing documentation, then produces a comprehensive, accurate README.

    Ready to connect★ 119

    github.com/espennilsen/pi117 stars

    View details
  • aut-sci-pptSkillDocs & knowledge

    Use when converting academic paper PDFs or structured text into professional, high-standard PowerPoint (PPTX) presentations for defense or seminars.

    Ready to connect★ 117

    github.com/shzhao27208/aut_sci_ppt118 stars

    View details
  • economist-styleSkillDocs & knowledge

    Apply The Economist style guide to written content. Use when editing markdown, HTML, documentation, or any written text that needs professional editing for clarity, precision, and brevity. Detects weasel words, fillers, passive voice, and style issues.

    Ready to connect★ 118

    github.com/tajd/economist-style-guide-plugin118 stars

    View details
  • myceliumSkillDocs & knowledge

    Multi-agent coordination layer with persistent memory. Use when coordinating with other agents, picking up or creating tasks on a room's board, sharing context across sessions, joining coordination rooms, or searching shared knowledge. Triggers on "coordinate", "negotiate", "share memory", "mycelium

    Ready to connect★ 118

    github.com/mycelium-io/mycelium116 stars

    View details
  • recursive-modeSkillDocs & knowledge

    Repository workflow orchestration skill for staged implementation, locked artifacts, late-phase receipts, and durable memory maintenance. Use when executing recursive-mode runs, resuming a run, locking a phase, or verifying locks.

    Ready to connect★ 118

    github.com/try-works/role-model114 stars

    View details
  • recursive-subagentSkillDocs & knowledge

    Use when recursive-mode work may benefit from delegated audit, review, or bounded implementation support. This skill prioritizes phase-auditor, traceability-auditor, code-reviewer, memory-auditor, and test-reviewer roles, with mandatory self-audit fallback when subagents are unavailable.

    Ready to connect★ 118

    github.com/try-works/role-model114 stars

    View details
  • recursive-trainingSkillDocs & knowledge

    Use after completed recursive-mode runs accumulate to extract durable experiential memory into `/.recursive/memory/`, then load it for later runs through the canonical loader.

    Ready to connect★ 118

    github.com/try-works/role-model114 stars

    View details
  • team-modeSkillDocs & knowledge

    Proactively decompose and coordinate substantial development, research, analysis, planning, document, data, and content work with the smallest useful parallel set of custom subagents. Use when independent execution, parallelism, context isolation, or fresh review can improve speed or quality. Keep u

    Ready to connect★ 118

    github.com/oil-oil/codex-team-mode118 stars

    View details
  • article2ticktickSkillDocs & knowledge

    Organizes articles from a tech weekly newsletter into TickTick to-do items, and also supports adding a single article directly. Use this skill when the user provides a weekly newsletter markdown document, asks to add newsletter articles to TickTick, or mentions trigger words like "技术周报", "文章汇总", or

    Ready to connect★ 117

    github.com/balabalabalading/huuuuuuho-skills117 stars

    View details
  • cad-referenceSkillDocs & knowledge

    Index of the Convex Architecture Documents (CADs), the normative specifications for Convex. Use to find which CAD governs a subsystem before changing protocol, encoding, consensus or economic behaviour.

    Ready to connect★ 117

    github.com/convex-dev/convex117 stars

    View details
  • pdf-trad-to-simp-preserve-layoutSkillDocs & knowledge

    Convert traditional Chinese PDFs to simplified Chinese while preserving page size, images, selectable text, and overall layout as much as possible. Use when Codex is asked to directly convert a source PDF from 繁体 to 简体 without rebuilding the book, to keep the original PDF structure and pictures, to

    Ready to connect★ 117

    github.com/superpilot69/pdf-trad-to-simp-preserve-layout-kit117 stars

    View details
  • book-idea-validatorSkillDocs & knowledge

    Stress-test book concepts against existing research before committing to architecture. Use when the user has a Book Concept Document ready for validation, wants to verify their thesis is defensible, needs to understand the competitive intellectual landscape, or wants honest assessment of their idea'

    Ready to connect★ 116

    github.com/robertguss/claude-code-toolkit116 stars

    View details
  • book-ideationSkillDocs & knowledge

    Develop raw book ideas into structured nonfiction book concepts. Use when the user wants to develop a book idea, has brainstorm documents to refine into a book concept, wants to articulate a book's thesis/promise/reader/transformation, or needs to prepare a book concept for validation and market res

    Ready to connect★ 116

    github.com/robertguss/claude-code-toolkit116 stars

    View details
  • book-market-researchSkillDocs & knowledge

    Assess commercial viability of book concepts for Amazon KDP self-publishing. Use when the user has a Book Concept Document and wants to understand market demand, competition, pricing, and positioning before committing to write. Produces a Market Research Report with viability scorecard and Go/No-Go

    Ready to connect★ 116

    github.com/robertguss/claude-code-toolkit116 stars

    View details
  • chapter-architectSkillDocs & knowledge

    Plan and architect a single chapter at beat-level granularity. Use when you have a chapter from the Architecture Document and need to create a detailed outline before drafting. Produces a Chapter Outline Document for use by draft-coach or ghostwriter.

    Ready to connect★ 116

    github.com/robertguss/claude-code-toolkit116 stars

    View details
  • doc-refreshSkillDocs & knowledge

    Refresh a repo's documentation for a live production system — audit stale docs, rebuild a focused doc set with diagrams, update AI-agent knowledge bases, and improve code-level docstrings

    Ready to connect★ 116

    github.com/robertguss/claude-code-toolkit116 stars

    View details
  • ebook-concept-developmentSkillDocs & knowledge

    Develop ebook ideas into structured concepts ready for architecture. Use when the user has an ebook idea (from a brainstorm document, existing content to repurpose, a book section to extract, or a fresh concept) and wants to develop it into a clear, validated concept. Produces an Ebook Concept Docum

    Ready to connect★ 116

    github.com/robertguss/claude-code-toolkit116 stars

    View details
  • expression-language-injectionSkillDocs & knowledge

    Expression Language injection playbook. Use when Java EL, SpEL, OGNL, or MVEL expressions may evaluate attacker-controlled input in Spring, Struts2, Confluence, or similar frameworks.

    Ready to connect★ 116

    github.com/langbyyi/cyberstrikeai-src110 stars

    View details
  • ghost-writerSkillDocs & knowledge

    Produce first drafts that match a writer's authentic voice using their Voice DNA Document. Consumes DNA documents from writing-dna-discovery skill. Generates 2 meaningfully different drafts with headlines, confidence assessment, decision notes, and DNA refinement suggestions. Collaborative partner t

    Ready to connect★ 116

    github.com/robertguss/claude-code-toolkit116 stars

    View details
  • pragmatic-writingSkillDocs & knowledge

    This skill should be used when writing technical content in the style of Hunt/Thomas (The Pragmatic Programmer) and Joel Spolsky (Joel on Software). It applies when creating technical essays, documentation, tutorials, or explanatory content that needs to be clear, engaging, and actionable.

    Ready to connect★ 116

    github.com/robertguss/claude-code-toolkit116 stars

    View details
  • simple-tasksSkillDocs & knowledge

    Install a fast local task workflow for single-project planning with `scripts/task.sh` (claim, done, status, reporting) backed by `tasks/TASKS.md` and optional `tasks/details/` notes. Use for lightweight in-progress task coordination, not full team issue tracking.

    Ready to connect★ 116

    github.com/robertguss/claude-code-toolkit116 stars

    View details
  • voice-captureSkillDocs & knowledge

    This skill should be used when extracting voice profiles from sample text, creating voice documentation, or matching a specific writing style. It applies when users provide sample text and want to capture the voice for future use.

    Ready to connect★ 116

    github.com/robertguss/claude-code-toolkit116 stars

    View details
  • writing-dna-discoverySkillDocs & knowledge

    Capture a writer's voice DNA through collaborative interview and sample analysis. Use when someone wants to document their writing voice for use with a ghost writer skill. Produces a Voice DNA Document with patterns, anti-patterns, and actionable guidance. Handles one register/mode per session, supp

    Ready to connect★ 116

    github.com/robertguss/claude-code-toolkit116 stars

    View details
  • xslt-injectionSkillDocs & knowledge

    XSLT injection testing: processor fingerprinting, XXE and document() SSRF, EXSLT write primitives, PHP/Java/.NET extension RCE surfaces. Use when user-controlled XSLT/stylesheet input or transform endpoints are in scope.

    Ready to connect★ 116

    github.com/langbyyi/cyberstrikeai-src110 stars

    View details
  • alignmentSkillDocs & knowledge

    Use when verifying that requirements/specs/PRDs and their implementation plans match — before starting work, after a spec or plan update, or when suspecting coverage gaps, scope creep, or design drift between intent and action documents. Needs both documents; not for checking code against a spec.

    Ready to connect★ 115

    github.com/ovid/paad115 stars

    View details
  • asanSkillDocs & knowledge

    Build and run the vlink-test unit tests with AddressSanitizer (ENABLE_TEST_SANITIZE=ON) to reproduce the CI's ASan gate. Use when the user asks to "run asan", "memory detection tests", or troubleshoot sanitize failures in ci-test.

    Ready to connect★ 115

    github.com/thun-res/vlink115 stars

    View details
  • nature-writing-studioSkillDocs & knowledge

    Rewrite scientific text into Nature Portfolio English using a knowledge base distilled from 657 Nature family papers via per-paper LLM observation (87.6% coverage), now extended with 5 deterministic AI-observation TSVs (gap_transitions / opener_distribution / cross_section_linkers / hedge_verbs / re

    Ready to connect★ 115

    github.com/mumdark/nature-writing-studio85 stars

    View details
  • rethinkSkillDocs & knowledge

    EXPERIMENTAL. Use when options, a recommendation, or an already-chosen approach are on the table and the reasoning under them has not been independently checked — especially when the case rests on cited documentation, remembered behavior, or premises nobody verified. Not for generating alternatives,

    Ready to connect★ 115

    github.com/ovid/paad115 stars

    View details
  • sync-agentSkillDocs & knowledge

    Audits and syncs AGENTS.md, AI-POLICY.md, Copilot instructions, .agents routing/index/language volumes/CI notes, skill frontmatter, agents/openai.yaml, and README listings based on facts from the current VLink code, docs, directory, tools, and GitHub workflows. Use when the user asks to "sync Agent

    Ready to connect★ 115

    github.com/thun-res/vlink115 stars

    View details

What is a skill?

A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.

54,764 of the 55,196 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.

Install one and every AI you use gets it

Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.

Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.

See how to connect your AI