ahel is live on Product Hunt today. Upvote

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 92 of 296

  • pr-reviewSkillAI & models

    Multi-dimensional review of a PR or feature branch in microsoft/win-dev-skills. Activate on "review my PR / changes / branch", "vet before pushing", "PR review", "is this ready to merge". Fans out parallel sub-agents over skill content, the skill-vs-tool boundary (solution hierarchy), tool correctne

    Ready to connect★ 435

    github.com/microsoft/win-dev-skills435 stars

    View details
  • winui-session-reportSkillAI & models

    Analyze the current or a recent agent session (GitHub Copilot CLI or Claude Code) and generate a diagnostic report. Use only when the user explicitly asks for session feedback, agent debugging, or a review of what happened during a build session. Do not inspect session data automatically.

    Ready to connect★ 435

    github.com/microsoft/win-dev-skills435 stars

    View details
  • swift-testing-proSkillAI & models

    Writes, reviews, and improves Swift Testing code using modern APIs and best practices. Use when reading, writing, or reviewing projects that use Swift Testing.

    Ready to connect★ 433

    github.com/twostraws/swift-testing-agent-skill312 stars

    View details
  • koe-setupSkillAI & models

    Guide users through Koe's initial setup and ongoing configuration, including installation, ASR/LLM credential setup, personalized dictionary generation, system prompt customization, and hotkey configuration.

    Ready to connect★ 429

    github.com/missuo/koe425 stars

    View details
  • claude-code-debugSkillAI & models

    Troubleshoot Claude Code extensions and behavior. Triggers on: debug, troubleshoot, not working, skill not loading, hook not running, agent not found.

    Ready to connect★ 423

    github.com/aiskillstore/marketplace427 stars

    View details
  • claude-code-templatesSkillAI & models

    Boilerplate templates for Claude Code extensions. Triggers on: create agent, new skill, command template, hook script, extension scaffold.

    Ready to connect★ 423

    github.com/aiskillstore/marketplace427 stars

    View details
  • igce-builder-ffpSkillAI & models

    Trigger for: FFP IGCE, firm-fixed-price estimate, FFP cost model, proposed FFP rate validation, wrap-rate analysis, Agency BPA rate comparison, price-reasonableness memo, or fair-and-reasonable analysis. Build auditable Firm-Fixed-Price federal estimates using BLS OEWS wages, layered fringe/overhead

    Ready to connect★ 423

    github.com/aiskillstore/marketplace427 stars

    View details
  • mcp-patternsSkillAI & models

    Model Context Protocol (MCP) server patterns for building integrations with Claude Code. Triggers on: mcp server, model context protocol, tool handler, mcp resource, mcp tool.

    Ready to connect★ 423

    github.com/aiskillstore/marketplace427 stars

    View details
  • review-agentSkillAI & models

    Perform a read-only, defect-first review of a specified code change and return every actionable finding. Use when another agent delegates review of uncommitted changes, a base-branch diff, a commit, or custom review instructions.

    Ready to connect★ 423

    github.com/aiskillstore/marketplace427 stars

    View details
  • routeSkillAI & models

    Manually route a query to the optimal Claude model (Haiku/Sonnet/Opus)

    Ready to connect★ 423

    github.com/aiskillstore/marketplace427 stars

    View details
  • router-statsSkillAI & models

    Display Claude Router usage statistics and cost savings

    Ready to connect★ 423

    github.com/aiskillstore/marketplace427 stars

    View details
  • claude-md-dependency-rescanSkillAI & models

    Re-detect this project's tech stack from package.json / requirements.txt / pyproject.toml / go.mod / Cargo.toml and diff it against the Tech Stack section of every CLAUDE.md. Read-only — returns added / removed / renamed dependencies, never edits.

    Ready to connect★ 425

    github.com/alirezarezvani/claudeforge424 stars

    View details
  • karpathy-guidelinesSkillAI & models

    Behavioral guardrails for LLM-assisted coding. Use when writing, reviewing, or refactoring code in any project to avoid overcomplication, keep changes surgical, surface assumptions early, and execute against verifiable success criteria.

    Ready to connect★ 425

    github.com/alirezarezvani/claudeforge424 stars

    View details
  • grimoireSkillAI & models

    Use when the user says 'update context', 'update claude', 'save library', or after significant project changes.

    Ready to connect★ 421

    github.com/cwinvestments/memstack419 stars

    View details
  • token-optimizationSkillAI & models

    Use when the user says 'token optimization', 'save tokens', 'context window', 'reduce tokens', 'token stack', or 'TokenStack', or asks about extending context window capacity. Covers TokenStack, the built-in compression proxy that shrinks Claude Code tool output before it reaches the Anthropic API.

    Ready to connect★ 421

    github.com/cwinvestments/memstack419 stars

    View details
  • adr-consultationSkillAI & models

    Multi-agent consultation for architecture decisions.

    Ready to connect★ 419

    github.com/notque/vexjoy-agent420 stars

    View details
  • agent-comparisonSkillAI & models

    A/B test agent variants for quality and token cost.

    Ready to connect★ 419

    github.com/notque/vexjoy-agent420 stars

    View details
  • architecture-deepeningSkillAI & models

    Improve architecture across modules by deepening interfaces.

    Ready to connect★ 419

    github.com/notque/vexjoy-agent420 stars

    View details
  • bluesky-readerSkillAI & models

    Read public Bluesky feeds via AT Protocol API.

    Ready to connect★ 419

    github.com/notque/vexjoy-agent420 stars

    View details
  • code-lintingSkillAI & models

    Run Python (ruff) and JavaScript (Biome) linting.

    Ready to connect★ 419

    github.com/notque/vexjoy-agent420 stars

    View details
  • codebase-analyzerSkillAI & models

    Statistical rule discovery from Go codebase patterns.

    Ready to connect★ 419

    github.com/notque/vexjoy-agent420 stars

    View details
  • codebase-overviewSkillAI & models

    Systematic codebase exploration and architecture mapping.

    Ready to connect★ 419

    github.com/notque/vexjoy-agent420 stars

    View details
  • comment-qualitySkillAI & models

    Review and fix temporal references in code comments.

    Ready to connect★ 419

    github.com/notque/vexjoy-agent420 stars

    View details
  • condenseSkillAI & models

    Maximize information density: preserve all instructions, remove prose filler.

    Ready to connect★ 419

    github.com/notque/vexjoy-agent420 stars

    View details
  • condition-based-waitingSkillAI & models

    Polling, retry, and backoff patterns.

    Ready to connect★ 419

    github.com/notque/vexjoy-agent420 stars

    View details
  • content-engineSkillAI & models

    Repurpose source assets into platform-native social content.

    Ready to connect★ 419

    github.com/notque/vexjoy-agent420 stars

    View details
  • create-voiceSkillAI & models

    Create voice profiles from writing samples.

    Ready to connect★ 419

    github.com/notque/vexjoy-agent420 stars

    View details
  • cron-automationSkillAI & models

    Audit and create cron jobs with reliability and safety.

    Ready to connect★ 419

    github.com/notque/vexjoy-agent420 stars

    View details
  • data-analysisSkillAI & models

    Decision-first data analysis with statistical rigor gates.

    Ready to connect★ 419

    github.com/notque/vexjoy-agent420 stars

    View details
  • decision-helperSkillAI & models

    Weighted decision scoring for architectural choices.

    Ready to connect★ 419

    github.com/notque/vexjoy-agent420 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