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
- View details
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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- View details
routeSkillAI & models
Manually route a query to the optimal Claude model (Haiku/Sonnet/Opus)
Ready to connect★ 423
- View details
router-statsSkillAI & models
Display Claude Router usage statistics and cost savings
Ready to connect★ 423
- 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
- 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
- View details
grimoireSkillAI & models
Use when the user says 'update context', 'update claude', 'save library', or after significant project changes.
Ready to connect★ 421
- 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
- View details
adr-consultationSkillAI & models
Multi-agent consultation for architecture decisions.
Ready to connect★ 419
- View details
agent-comparisonSkillAI & models
A/B test agent variants for quality and token cost.
Ready to connect★ 419
- View details
architecture-deepeningSkillAI & models
Improve architecture across modules by deepening interfaces.
Ready to connect★ 419
- View details
- View details
- View details
codebase-analyzerSkillAI & models
Statistical rule discovery from Go codebase patterns.
Ready to connect★ 419
- View details
codebase-overviewSkillAI & models
Systematic codebase exploration and architecture mapping.
Ready to connect★ 419
- View details
comment-qualitySkillAI & models
Review and fix temporal references in code comments.
Ready to connect★ 419
- View details
condenseSkillAI & models
Maximize information density: preserve all instructions, remove prose filler.
Ready to connect★ 419
- View details
- View details
content-engineSkillAI & models
Repurpose source assets into platform-native social content.
Ready to connect★ 419
- View details
- View details
cron-automationSkillAI & models
Audit and create cron jobs with reliability and safety.
Ready to connect★ 419
- View details
data-analysisSkillAI & models
Decision-first data analysis with statistical rigor gates.
Ready to connect★ 419
- View details
decision-helperSkillAI & models
Weighted decision scoring for architectural choices.
Ready to connect★ 419
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.