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
9,019 results · page 103 of 301
- View details
coding-backend-claude-codeSkillAI & models
Runtime prompt layer for Claude Code coding agent runs.
Ready to connect★ 372
- View details
coding-backend-codexSkillAI & models
Runtime prompt layer for Codex coding agent runs.
Ready to connect★ 372
- View details
coding-backend-cursorSkillAI & models
Runtime prompt layer for Cursor Agent CLI coding agent runs.
Ready to connect★ 372
- View details
coding-backend-opencodeSkillAI & models
Runtime prompt layer for OpenCode coding agent runs.
Ready to connect★ 372
- View details
coding-backend-piSkillAI & models
Runtime prompt layer for pi.dev (pi CLI) coding agent runs.
Ready to connect★ 372
- View details
evalSkillAI & models
Plan and run conversational AI agent evaluations with test generation and analysis.
Ready to connect★ 372
- View details
install-rhoSkillAI & models
Install and configure Rho from scratch (Doom-style init.toml + sync). Only prereq: a coding agent that can run shell commands.
Ready to connect★ 372
- View details
update-piSkillAI & models
Update the pi-coding-agent npm package to the latest version. Use when the user wants to update pi, upgrade pi, or get the latest version of the coding agent.
Ready to connect★ 372
- View details
pydanticai-docsSkillAI & models
Use this skill whenever the user is working with the Pydantic AI framework — including building AI agents, defining structured outputs with Pydantic models, wiring up tools/function calling, configuring model providers (OpenAI, Anthropic, Gemini, etc.), managing dependencies via agent context, handl
Ready to connect★ 371
- View details
automate-meSkillAI & models
Use for \"automate me\", \"create/update/refresh my -mode skill\", \"turn/capture my preferences or working style into a skill\", or wanting agents to follow how the user works. Drafts or revises a personal -mode skill via plugin-dev:skill-development + unslop, optionally pulling fresh evidence from
Ready to connect★ 341
- View details
babysitSkillAI & models
Watch an open PR — fix failing CI, handle the straightforward review comments, and drive it to a mergeable state. Claude Code analog of Cursor's built-in /babysit. Use after opening a PR when the user wants the agent to shepherd it without re-prompting.
Ready to connect★ 341
- View details
blast-radiusSkillAI & models
Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code instead of writing it up. Use for 'blast radius of X', 'what could this break', reviewing a small diff you don't trust, or a brief that asserts something a
Ready to connect★ 341
- View details
create-verification-skillSkillAI & models
Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, \"make a control skill for this repo\", or when a project has no scripted way to prove UI/CLI/service behavior.
Ready to connect★ 341
- View details
- View details
fix-merge-conflictsSkillAI & models
Resolve merge conflicts non-interactively, validate build and tests, and finalize conflict resolution
Ready to connect★ 341
- View details
interrogateSkillAI & models
Use for \"interrogate\", \"adversarial review\", \"multi-model review\", \"challenge this\", \"stress test this code\", \"find blind spots\", or \"tear this apart\". Multiple LLM reviewers challenge changes from independent angles.
Ready to connect★ 341
- View details
maintain-verification-skillSkillAI & models
Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature, at most one PR of proven corrections. Use for /maintain-verification-skill or \"audit the verify skill\".
Ready to connect★ 341
- View details
make-pr-easy-to-reviewSkillAI & models
Prepare PRs for review by cleaning noisy history, improving PR descriptions, and adding reviewer guidance without changing code behavior. Use for "make this easy to review", "tidy this PR", "clean up commits", or "annotate the diff".
Ready to connect★ 341
- View details
no-commentsSkillAI & models
Spawn the comment-sicko subagent, fix accepted findings, and offer encodings for claimed constraints.
Ready to connect★ 341
- View details
poteto-modeSkillAI & models
poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for poteto, /poteto-mode, or requests to work in this style.
Ready to connect★ 341
- View details
principle-attack-the-premiseSkillAI & models
Apply when two or more fixes that share one premise have failed the same gate. Take a census of which actors hold the imbalance before the next fix, then question the premise instead of writing another fix that assumes it.
Ready to connect★ 341
- View details
principle-boundary-disciplineSkillAI & models
Apply when wiring validation, error handling, or framework adapters. Concentrate guards at system boundaries (CLI, config, network, external APIs); trust internal types and keep business logic in pure functions.
Ready to connect★ 341
- View details
principle-build-the-leverSkillAI & models
Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can rerun.
Ready to connect★ 341
- View details
principle-encode-lessons-in-structureSkillAI & models
Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction. Encode the rule as a lint, metadata flag, runtime check, or script instead of more text.
Ready to connect★ 341
- View details
principle-experience-firstSkillAI & models
Apply when product, UX, or feature-scope tradeoffs come up. Choose user delight over implementation convenience; ship fewer polished features over more rough ones.
Ready to connect★ 341
- View details
principle-fix-root-causesSkillAI & models
Apply when debugging. Trace each symptom to its root cause and fix it there; reproduce first, ask why until you reach it, resist nil-check guards that silence crashes.
Ready to connect★ 341
- View details
principle-foundational-thinkingSkillAI & models
Apply before writing logic: choosing core types and data structures, sequencing scaffold-vs-feature work, asking what concurrent actors share. Get the data structures right so downstream code becomes obvious.
Ready to connect★ 341
- View details
principle-laziness-protocolSkillAI & models
Apply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading. Bias toward deletion and the smallest change that solves the problem.
Ready to connect★ 341
- View details
principle-make-operations-idempotentSkillAI & models
Apply when designing commands, lifecycle steps, or processing loops that run amid crashes, restarts, and retries. Converge to the same end state regardless of partial prior runs.
Ready to connect★ 341
- View details
principle-migrate-callers-then-delete-legacy-apisSkillAI & models
Apply when introducing a new internal API while old callers still exist. Migrate callers and delete the old API in the same wave instead of preserving compatibility layers.
Ready to connect★ 341
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.