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: AI & models

8,868 results · page 262 of 296

  • agentclash-prompt-eval-playgroundSkillAI & models

    Use when scaffolding, validating, or running prompt eval YAML configs and managing playground experiments, test cases, and prompt variants via the AgentClash CLI.

    Ready to connect

    github.com/agentclash/agentclash28 stars

    View details
  • agentclash-scorecard-readerSkillAI & models

    Use when interpreting AgentClash rankings, scorecards, replay timelines, artifacts, LLM judge results, or failure-review evidence into source-backed findings and next actions.

    Ready to connect

    github.com/agentclash/agentclash28 stars

    View details
  • assessSkillAI & models

    Assess a codebase's readiness for AI agent contributors using the layered contract model, and generate a complexity hotspot SVG treemap (size = LOC, hue = cyclomatic complexity, saturation = recent git churn). TRIGGER when the user types /assess, asks for an AI-readiness review, wants a complexity h

    Ready to connect

    github.com/bjcoombs/ai-native-toolkit30 stars

    View details
  • change-briefSkillAI & models

    Turn a pull request into a concise, self-contained HTML decision brief with business logic, diagrams when useful, conditional UI/mobile screenshots, API cURL request/response evidence, risks, verification, and representative before/after code. Use when the user asks to "explain this change as HTML",

    Ready to connect

    github.com/rlajous/claude-code-commands30 stars

    View details
  • clean-goneSkillAI & models

    Delete local Git branches whose upstream was deleted on the remote ("[gone]"), and remove any worktrees attached to them. Use when the user asks to clean up merged/stale branches, prune gone branches, tidy local branches after merging PRs, or "delete branches that are gone on the remote".

    Ready to connect

    github.com/rlajous/claude-code-commands30 stars

    View details
  • delegation-parallelismSkillAI & models

    Invoke when deciding whether to split work across parallel agents/sessions or do it inline — tests scope independence, weighs coordination cost against the parallelism win, and sets an observation cadence for delegated work.

    Ready to connect

    github.com/rlaope/ultraprompt30 stars

    View details
  • detect-objectsSkillAI & models

    Run pre-trained AI models on geospatial imagery. Detect buildings, cars, ships, solar panels, agriculture fields, or use text-prompted segmentation with GroundedSAM. Requires GPU for best performance.

    Ready to connect

    github.com/opengeos/geoai-skills30 stars

    View details
  • exploration-strategySkillAI & models

    Build an accurate mental model of an unfamiliar codebase or problem before making any edit — structural scan, entry-point location, one end-to-end trace, and an explicit known-vs-assumed ledger.

    Ready to connect

    github.com/rlaope/ultraprompt30 stars

    View details
  • failure-mode-enumerationSkillAI & models

    Systematically enumerate how code can break — boundaries, concurrency, partial failure, malicious input, time, resource exhaustion — before writing defenses, then convert the list into tests and guards while pruning paranoia that does not pay rent.

    Ready to connect

    github.com/rlaope/ultraprompt30 stars

    View details
  • fhir-r6-guardrailsSkillAI & models

    HealthClaw Guardrails (healthclaw.io) — FHIR agent guardrails for clinical data access via MCP. Supports FHIR R4 US Core v9 (stable) and FHIR R6 ballot3 (experimental). Use when: (1) Reading patient data through MCP tools with automatic PHI redaction, (2) Writing clinical resources with two-phase pr

    Ready to connect

    github.com/aks129/healthclawguardrails30 stars

    View details
  • fhir-upstream-proxySkillAI & models

    Connect to real FHIR servers through the MCP guardrail proxy. Use when: (1) Connecting to HAPI FHIR, SMART Health IT, or Epic sandbox servers, (2) Proxying AI agent requests to production EHR systems with guardrails, (3) Ensuring upstream server URLs never leak to clients, (4) Understanding how reda

    Ready to connect

    github.com/aks129/healthclawguardrails30 stars

    View details
  • finishSkillAI & models

    Create a pull request with comprehensive description following repo best practices

    Ready to connect

    github.com/rlajous/claude-code-commands30 stars

    View details
  • goga-define-challengeSkillAI & models

    Goga is an AI engineering platform for building software with AI agents. Combine engineering knowledge, AI tools, and pipelines into repeatable development processes — from specification to implementation, review, and delivery.

    Ready to connect

    github.com/qarium/goga30 stars

    View details
  • goga-define-constraintsSkillAI & models

    Goga is an AI engineering platform for building software with AI agents. Combine engineering knowledge, AI tools, and pipelines into repeatable development processes — from specification to implementation, review, and delivery.

    Ready to connect

    github.com/qarium/goga30 stars

    View details
  • goga-define-experienceSkillAI & models

    Goga is an AI engineering platform for building software with AI agents. Combine engineering knowledge, AI tools, and pipelines into repeatable development processes — from specification to implementation, review, and delivery.

    Ready to connect

    github.com/qarium/goga30 stars

    View details
  • goga-define-goalsSkillAI & models

    Goga is an AI engineering platform for building software with AI agents. Combine engineering knowledge, AI tools, and pipelines into repeatable development processes — from specification to implementation, review, and delivery.

    Ready to connect

    github.com/qarium/goga30 stars

    View details
  • goga-define-problemSkillAI & models

    Goga is an AI engineering platform for building software with AI agents. Combine engineering knowledge, AI tools, and pipelines into repeatable development processes — from specification to implementation, review, and delivery.

    Ready to connect

    github.com/qarium/goga30 stars

    View details
  • goga-define-projectSkillAI & models

    Goga is an AI engineering platform for building software with AI agents. Combine engineering knowledge, AI tools, and pipelines into repeatable development processes — from specification to implementation, review, and delivery.

    Ready to connect

    github.com/qarium/goga30 stars

    View details
  • goga-define-requirementsSkillAI & models

    Goga is an AI engineering platform for building software with AI agents. Combine engineering knowledge, AI tools, and pipelines into repeatable development processes — from specification to implementation, review, and delivery.

    Ready to connect

    github.com/qarium/goga30 stars

    View details
  • goga-define-resolveSkillAI & models

    Goga is an AI engineering platform for building software with AI agents. Combine engineering knowledge, AI tools, and pipelines into repeatable development processes — from specification to implementation, review, and delivery.

    Ready to connect

    github.com/qarium/goga30 stars

    View details
  • goga-define-scopeSkillAI & models

    Goga is an AI engineering platform for building software with AI agents. Combine engineering knowledge, AI tools, and pipelines into repeatable development processes — from specification to implementation, review, and delivery.

    Ready to connect

    github.com/qarium/goga30 stars

    View details
  • goga-define-successSkillAI & models

    Goga is an AI engineering platform for building software with AI agents. Combine engineering knowledge, AI tools, and pipelines into repeatable development processes — from specification to implementation, review, and delivery.

    Ready to connect

    github.com/qarium/goga30 stars

    View details
  • goga-define-usersSkillAI & models

    Goga is an AI engineering platform for building software with AI agents. Combine engineering knowledge, AI tools, and pipelines into repeatable development processes — from specification to implementation, review, and delivery.

    Ready to connect

    github.com/qarium/goga30 stars

    View details
  • gpai-pflichtenSkillAI & models

    Prüfung der Pflichten von Anbietern von KI-Modellen mit allgemeinem Verwendungszweck (GPAI) nach Art. 53 KI-VO und der Zusatzpflichten bei systemischem Risiko Art. 55 KI-VO – technische Dokumentation, Urheberrechtsstrategie, Praxisleitfäden (Codes of Practice). Use when ein Anbieter eines GPAI-Model

    Ready to connect

    github.com/borghei/ai-skills-german-law30 stars

    View details
  • handelsvertretervertragSkillAI & models

    Entwurf und Prüfung eines Handelsvertretervertrags nach §§ 84 ff. HGB inkl. Abgrenzung zu Vertragshändler/Kommissionsagent/Franchisenehmer, Provisionsregelung §§ 87 ff. HGB, Kündigung § 89 HGB, Ausgleichsanspruch § 89b HGB und nachvertragliches Wettbewerbsverbot § 90a HGB. Use when ein Unternehmer e

    Ready to connect

    github.com/borghei/ai-skills-german-law30 stars

    View details
  • honest-reportingSkillAI & models

    Invoke when writing any status, completion, or result report — calibrates claims to the evidence actually gathered, marks the unmeasured as open, reports failures plainly, and distinguishes "verified at layer X" from "should work".

    Ready to connect

    github.com/rlaope/ultraprompt30 stars

    View details
  • hypothesis-managementSkillAI & models

    Debug by maintaining 2-4 competing hypotheses with explicit evidence and kill criteria, choosing each probe to maximally discriminate between them instead of confirming a favorite.

    Ready to connect

    github.com/rlaope/ultraprompt30 stars

    View details
  • incremental-safetySkillAI & models

    Decompose a large or risky change into a sequence of independently safe intermediate states, so the system stays green at every step and any step can be reverted alone.

    Ready to connect

    github.com/rlaope/ultraprompt30 stars

    View details
  • indicatorSkillAI & models

    Parallel TDD swarm that ships a new market indicator end to end. Usage - /indicator <data-source> <indicator-name>. Researches the source, writes a spec plus failing tests, fans out three worktree implementer subagents (ingestion, API, chart tab), merges, runs the full suite, screenshots the live ta

    Ready to connect

    github.com/joemccann/radon29 stars

    View details
  • install-geoaiSkillAI & models

    Verify that the geoai Python package is installed and functional. If not, provide installation instructions. Optionally check extra dependencies for deep learning models.

    Ready to connect

    github.com/opengeos/geoai-skills30 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.

53,585 of the 54,017 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