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: Dev tools

18,403 results · page 449 of 614

  • loom-championSkillDev tools

    Human avatar for final decisions - promotes quality issues to approved status AND auto-merges Judge-approved PRs that meet safety criteria

    Ready to connect★ 63

    github.com/rjwalters/kicad-tools53 stars

    View details
  • loom-curatorSkillDev tools

    Enhances approved issues and prepares them for implementation

    Ready to connect★ 63

    github.com/rjwalters/kicad-tools53 stars

    View details
  • loom-doctorSkillDev tools

    Addresses review feedback on PRs labeled loom:changes-requested

    Ready to connect★ 63

    github.com/rjwalters/kicad-tools53 stars

    View details
  • loom-driverSkillDev tools

    Standard shell environment with no specialized role

    Ready to connect★ 63

    github.com/rjwalters/kicad-tools53 stars

    View details
  • loom-guideSkillDev tools

    Keeps the backlog healthy: tier labels, orphan verification, unblocking, epic tracking, living docs

    Ready to connect★ 63

    github.com/rjwalters/kicad-tools53 stars

    View details
  • loom-hermitSkillDev tools

    Identifies and proposes removal of unnecessary complexity, bloat, and over-engineering

    Ready to connect★ 63

    github.com/rjwalters/kicad-tools53 stars

    View details
  • loom-judgeSkillDev tools

    Reviews PRs labeled loom:review-requested

    Ready to connect★ 63

    github.com/rjwalters/kicad-tools53 stars

    View details
  • loom-loomSkillDev tools

    Tier 2 daemon-mode operator surface: observes the running Rust loom-daemon via MCP tools and dispatches sweeps for multi-account autonomous batches

    Ready to connect★ 63

    github.com/rjwalters/kicad-tools53 stars

    View details
  • loom-probe-protocolSkillDev tools

    Loom uses an intelligent probe system to detect what's running in each terminal. When you receive a probe command, respond according to this protocol.

    Ready to connect★ 63

    github.com/rjwalters/kicad-tools53 stars

    View details
  • mapping-analysisSkillDev tools

    Investigate dismech disease mappings, subtype and grouping alignment, and disagreements between MONDO and external ontologies. Use for Boomer runs, low-confidence or retracted mappings, ICD mapping scope and direction, curated proxy merges, source comparisons, and mapping-correction reports or upstr

    Ready to connect★ 63

    github.com/monarch-initiative/dismech57 stars

    View details
  • merge-reviewSkillDev tools

    Post-merge validation — check that both sides of a merge were fully integrated, nothing was silently dropped, and quality still passes.

    Ready to connect★ 63

    github.com/thalesgroup/fred60 stars

    View details
  • New Law AnalysisSkillDev tools

    New Law Analysis: drafting analysis articles and assessing business impact after new laws are enacted

    Ready to connect★ 63

    github.com/sunyifeisb-art/legalwork56 stars

    View details
  • noncoding-variant-impactSkillDev tools

    Curate or review noncoding variant impact in dismech, including regulatory SNVs and structural variants. Separate physical alteration, sequence overlap, regulatory target, expression consequence, and mechanistic confidence.

    Ready to connect★ 63

    github.com/monarch-initiative/dismech57 stars

    View details
  • Normative Meaning ArgumentationSkillDev tools

    Analyzes the purpose and value orientation of legal norms, and how facts should enter normative evaluation, determining the limits of subsumption; should be appropriately distinguished from purposive interpretation in legal interpretation.

    Ready to connect★ 63

    github.com/sunyifeisb-art/legalwork56 stars

    View details
  • portfolio-prospectingSkillDev tools

    Find companies backed by a specific investor or accelerator, then find contacts and build personalized outbound.

    Ready to connect★ 63

    github.com/getaero-io/gtm-eng-skills63 stars

    View details
  • portlessSkillDev tools

    Set up and use portless for named local dev server URLs (e.g. https://myapp.localhost instead of http://localhost:3000). Use when integrating portless into a project, configuring dev server names, setting up the local proxy, working with .localhost domains, or troubleshooting port/proxy issues.

    Ready to connect★ 63

    github.com/nrjdalal/zerostarter63 stars

    View details
  • Purposive InterpretationSkillDev tools

    A purposive interpretation skill. When the literal interpretation of a legal provision still cannot yield a determinate conclusion, this skill systematically discovers and argues the provision's purpose, selects the most justified meaning within what the text can bear, and forms an adjudicable inter

    Ready to connect★ 63

    github.com/sunyifeisb-art/legalwork56 stars

    View details
  • quality-rootSkillDev tools

    Run make code-quality from the monorepo root, covering all modules. Never run it per-module.

    Ready to connect★ 63

    github.com/thalesgroup/fred60 stars

    View details
  • remotion-uiSkillDev tools

    Work with the RemotionUI monorepo — registry authoring, CLI commands, remotion-ui.json config, and copy-paste component distribution. Use when adding primitives/scenes/compositions or running remotion-ui CLI.

    Ready to connect★ 63

    github.com/riaz37/remotion-ui63 stars

    View details
  • research-routesSkillDev tools

    Compare multiple research routes with explicit Claims, Evidence, unknowns, failure regimes, and reversible probes. Use when a person needs route-neutral exploration before implementation, experiment authorization, HumanDecision, or canonical-state promotion.

    Ready to connect★ 63

    github.com/zenx0x/allinluna63 stars

    View details
  • research-routes-exploreSkillDev tools

    Explore open-ended scientific or product questions through multiple concurrent Research Routes branches, probes, experiments, observations, evidence polarity, failure regimes, unknowns, and mature-method comparators. Use for research exploration or hybrid discovery from any starting point while keep

    Ready to connect★ 63

    github.com/zenx0x/allinluna63 stars

    View details
  • research-routes-planSkillDev tools

    Plan software, research-exploration, or hybrid work from a repository, question, problem, frame, or arbitrary starting point. Use when Codex needs a route-neutral map, shared backbone, concurrent routes and branches, explicit claims and hypotheses, provenance, evidence polarity, lifecycle recovery,

    Ready to connect★ 63

    github.com/zenx0x/allinluna63 stars

    View details
  • research-routes-runSkillDev tools

    Execute an approved Research Routes context across software, research-exploration, or hybrid journeys with concurrent route owners, shared control-plane resources, CounterPilot read-only boundaries, explicit evidence and provenance, lifecycle recovery, and HumanDecision seams. Use when implementatio

    Ready to connect★ 63

    github.com/zenx0x/allinluna63 stars

    View details
  • shadcn-syncSkillDev tools

    Run and reconcile the shadcn component sync (`bun run shadcn:update`). Use when refreshing shadcn components, or when a sync regresses a local customization or breaks the build.

    Ready to connect★ 63

    github.com/nrjdalal/zerostarter63 stars

    View details
  • Strategic Risk PrioritizationSkillDev tools

    When legal analysis involves multiple possible conclusions, risk points, or disputed issues, these risks need to be systematically ranked by probability of occurrence and severity of impact, helping decision-makers focus on the most critical risks and allocate resources appropriately. This skill is

    Ready to connect★ 63

    github.com/sunyifeisb-art/legalwork56 stars

    View details
  • Systematic InterpretationSkillDev tools

    Systematic interpretation addresses disputes over the meaning or scope of application that arise after interpreting the literal wording of a legal norm. It takes into account the position of the norm within the legal system (e.g., which law, part, chapter, or section it belongs to), the meaning of r

    Ready to connect★ 63

    github.com/sunyifeisb-art/legalwork56 stars

    View details
  • Team Knowledge SharingSkillDev tools

    Team knowledge sharing: knowledge organization tables, Q&A-style knowledge capture, and in-team sharing mechanisms.

    Ready to connect★ 63

    github.com/sunyifeisb-art/legalwork56 stars

    View details
  • test-gapsSkillDev tools

    Identify new code paths added in the current branch that have no test coverage. Reports gaps; does not write tests.

    Ready to connect★ 63

    github.com/thalesgroup/fred60 stars

    View details
  • Timeline GenerationSkillDev tools

    Case timeline generation: extracts event time points from case materials and generates a structured, visualized timeline

    Ready to connect★ 63

    github.com/sunyifeisb-art/legalwork56 stars

    View details
  • topic-briefSkillDev tools

    Generate a topic-focused briefing in HTML from public news sources. Use when user asks for a briefing / observation / digest / 简报 / 观察 on any subject — region (Middle East, ASEAN, India), industry (semiconductors, EV supply chain, AI), policy issue (AI regulation, critical minerals, cross-border pay

    Ready to connect★ 63

    github.com/genli-ai/market-research-skills63 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.

59,937 of the 59,937 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 workspace 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