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 22 of 152

  • anti-driftSkillDocs & knowledge

    Lets your agent stay on task during long multi-step work by checking progress against a plan at frequent checkpoints.

    Ready to connect★ 2k

    github.com/a5c-ai/babysitter2k stars

    View details
  • code-review-orchestrationSkillDocs & knowledge

    Lets your agent run six parallel code reviews covering architecture, security, performance, testing, quality, and docs with scores.

    Ready to connect★ 2k

    github.com/a5c-ai/babysitter2k stars

    View details
  • cog-knowledge-consolidationSkillDocs & knowledge

    Lets your agent organize scattered notes into structured knowledge frameworks with source attribution.

    Ready to connect★ 2k

    github.com/a5c-ai/babysitter2k stars

    View details
  • decision-documentationSkillDocs & knowledge

    Lets your agent write numbered Architecture Decision Records that capture context, options, and consequences.

    Ready to connect★ 2k

    github.com/a5c-ai/babysitter2k stars

    View details
  • finishing-workSkillDocs & knowledge

    Makes your agent wrap up tasks properly by writing a summary, updating the plan, and checking all goals were met.

    Ready to connect★ 2k

    github.com/a5c-ai/babysitter2k stars

    View details
  • frontmatter-parsingSkillDocs & knowledge

    Lets your agent read, update, and validate the YAML frontmatter at the top of markdown planning documents.

    Ready to connect★ 2k

    github.com/a5c-ai/babysitter2k stars

    View details
  • knowledge-curationSkillDocs & knowledge

    Lets your agent load project context before tasks and save lessons learned into a knowledge base afterward.

    Ready to connect★ 2k

    github.com/a5c-ai/babysitter2k stars

    View details
  • persistent-memorySkillDocs & knowledge

    Lets your agent remember notes, decisions, and findings across sessions and search them later by tags or relevance.

    Ready to connect★ 2k

    github.com/a5c-ai/babysitter2k stars

    View details
  • project-documentationSkillDocs & knowledge

    Lets your agent follow strict step-by-step workflows so complex multi-step tasks stay on track.

    Ready to connect★ 2k

    github.com/a5c-ai/babysitter2k stars

    View details
  • session-memorySkillDocs & knowledge

    Lets your agent save and reload its memory notes so it keeps context after a session reset.

    Ready to connect★ 2k

    github.com/a5c-ai/babysitter2k stars

    View details
  • template-scaffoldingSkillDocs & knowledge

    Lets your agent load templates and fill in variables to generate project documents automatically.

    Ready to connect★ 2k

    github.com/a5c-ai/babysitter2k stars

    View details
  • jsdocsSkillDocs & knowledge

    Lets your agent write, insert, or update JSDoc comments for Effect public APIs to satisfy lint rules.

    Ready to connect★ 2k

    github.com/mapletechlabs/maple2k stars

    View details
  • image-enhancerSkillDocs & knowledge

    Lets your agent improve image quality, like sharpening and upscaling screenshots for docs or posts.

    Ready to connect★ 2k

    github.com/prat011/awesome-llm-skills2k stars

    View details
  • cross-device-diagnoseSkillDocs & knowledge

    Agent Loop for cross-device sync/transfer issues: collect environment fingerprints from BOTH machines first, check memory for known patterns, manage hypotheses with forced falsification, and persist evidence via $wrap. Orchestrates dual-side-debug + local-log-debug + systematic-debugging into a stru

    Ready to connect★ 2k

    github.com/uniclipboard/uniclipboard2k stars

    View details
  • gen-changelogSkillDocs & knowledge

    Generate bilingual, user-facing release changelogs from Git history. Use when the user asks to generate a changelog, prepare release notes, or update `docs/changelog` for a release and provides a base tag or commit.

    Ready to connect★ 2k

    github.com/uniclipboard/uniclipboard2k stars

    View details
  • plan-reviewerSkillDocs & knowledge

    Run an independent adversarial review loop for a Markdown implementation plan. Use when the user asks to review, validate, stress-test, or challenge a plan before implementation, including requests for a second opinion or a plan review loop.

    Ready to connect★ 2k

    github.com/uniclipboard/uniclipboard2k stars

    View details
  • git-notesSkillDocs & knowledge

    Use when adding metadata to commits without changing history, tracking review status, test results, code quality annotations, or supplementing commit messages post-hoc - provides git notes commands and patterns for attaching non-invasive metadata to Git objects.

    Ready to connect★ 2k

    github.com/neolabhq/context-engineering-kit2k stars

    View details
  • setup-context7-mcpSkillDocs & knowledge

    Guide for setup Context7 MCP server to load documentation for specific technologies.

    Ready to connect★ 2k

    github.com/neolabhq/context-engineering-kit2k stars

    View details
  • statusSkillDocs & knowledge

    Display the current state of the FPF knowledge base

    Ready to connect★ 2k

    github.com/neolabhq/context-engineering-kit2k stars

    View details
  • test-skillSkillDocs & knowledge

    Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skill, writing to address failures, iterating to close loopholes

    Ready to connect★ 2k

    github.com/neolabhq/context-engineering-kit2k stars

    View details
  • write-conciselySkillDocs & knowledge

    Apply writing rules to any documentation that humans will read. Makes your writing clearer, stronger, and more professional.

    Ready to connect★ 2k

    github.com/neolabhq/context-engineering-kit2k stars

    View details
  • devtu-optimize-descriptionsSkillDocs & knowledge

    Optimize tool descriptions in ToolUniverse JSON configs for clarity and usability. Reviews descriptions for missing prerequisites, unexpanded abbreviations, unclear parameters, and missing usage guidance. Use when reviewing tool descriptions, improving API documentation, or when user asks to check i

    Ready to connect★ 2k

    github.com/mims-harvard/tooluniverse2k stars

    View details
  • tooluniverse-adverse-outcome-pathwaySkillDocs & knowledge

    Map environmental and industrial chemicals to adverse outcome pathways (AOPs) — molecular initiating event to organ-level toxicity. Uses AOPWiki, GHS classification, IARC carcinogen status, and LD50 data. Use for environmental/industrial chemical risk assessment, regulatory-grade hazard characteriza

    Ready to connect★ 2k

    github.com/mims-harvard/tooluniverse2k stars

    View details
  • tooluniverse-antigravity-pluginSkillDocs & knowledge

    Install, set up, verify, update, pin, uninstall, or troubleshoot the ToolUniverse plugin on Google Antigravity (AGY / Antigravity IDE / Antigravity 2.0). ALWAYS consult this skill for any of those — don't answer from memory, because the exact CLI name (agy), the "agy plugin install <path>" flow, the

    Ready to connect★ 2k

    github.com/mims-harvard/tooluniverse2k stars

    View details
  • tooluniverse-cancer-classificationSkillDocs & knowledge

    Translate free-text tumor descriptions to OncoTree codes and resolve cancer subtypes/tissue hierarchy. Cross-references UMLS/NCI vocabularies. Use for standardizing cancer-type nomenclature in EHR free-text, building cohorts in OncoKB or GDC, mapping tumor-board notes to ontology codes, and ensuring

    Ready to connect★ 2k

    github.com/mims-harvard/tooluniverse2k stars

    View details
  • tooluniverse-codex-pluginSkillDocs & knowledge

    Install, set up, verify, update, pin, uninstall, or troubleshoot the ToolUniverse plugin on OpenAI Codex. ALWAYS consult this skill for any of those — don't answer from memory, because the exact marketplace name (mims-harvard/ToolUniverse), the "codex plugin marketplace add" then "codex plugin add -

    Ready to connect★ 2k

    github.com/mims-harvard/tooluniverse2k stars

    View details
  • tooluniverse-pathway-disease-geneticsSkillDocs & knowledge

    Connect GWAS variants to biological pathways and druggable targets. Maps GWAS hits to causal genes (via fine-mapping/eQTL), then to pathways (Reactome, KEGG, WikiPathways), then to existing drugs hitting those pathways. Use for pathway-level disease mechanisms, druggable-pathway prioritization from

    Ready to connect★ 2k

    github.com/mims-harvard/tooluniverse2k stars

    View details
  • askSkillDocs & knowledge

    Ask the wiki a question, retrieve and synthesize relevant pages, optionally crystallize the answer back into the wiki

    Ready to connect★ 2k

    github.com/skyllwt/autosci2k stars

    View details
  • checkSkillDocs & knowledge

    Scan the full wiki to detect health issues and produce a tiered fix-recommendation report (covers all entity types in runtime/schema/entities.yaml + graph consistency)

    Ready to connect★ 2k

    github.com/skyllwt/autosci2k stars

    View details
  • discoverSkillDocs & knowledge

    Build a ranked shortlist of candidate papers (anchor-driven, topic-driven, or derived from current wiki state) that the user — or an upstream skill — may decide to feed into `/ingest`. Use whenever the user asks "what should I read next", "find papers similar to this one", "recommend related work",

    Ready to connect★ 2k

    github.com/skyllwt/autosci2k 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