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.
Filter by category
55,384 results · page 342 of 1,847
- View details
pcbwaySkillMedia
Guides your agent through ordering PCB fabrication and assembly from PCBWay, including BOM prep and design rules.
Ready to connect★ 1k
- View details
spiceSkillDev tools
Lets your agent run SPICE simulations on KiCad circuits to verify filter cutoffs, divider voltages, opamp gains and resonances.
Ready to connect★ 1k
- View details
ap-arbiterSkillAI & models
Lets your agent make a binding final decision when it hits a fork it cannot resolve, without asking you.
Ready to connect★ 1k
- View details
ap-depth-proberSkillAI & models
Lets your agent independently judge how deep a bug's root cause is, from issue text alone, before trusting a proposed fix.
Ready to connect★ 1k
- View details
ap-execharness-resolverSkillProductivity
Lets your agent resolve the exact execution harness and pass/fail test sets a coding benchmark task will be graded on.
Ready to connect★ 1k
- View details
ap-feature-coordinatorSkillAI & models
Lets your agent manage feature work by moving roadmap tasks through build, review, and verification steps.
Ready to connect★ 1k
- View details
ap-framework-generatorSkillProductivity
Lets your agent generate a custom prompt framework tailored to a task when no existing one fits.
Ready to connect★ 1k
- View details
ap-framework-validatorSkillAI & models
Lets your agent check that a generated workflow framework is correctly built before it runs.
Ready to connect★ 1k
- View details
ap-fresh-verifierSkillAI & models
Lets your agent independently double-check a draft plan against the mission and codebase and return approve or reject.
Ready to connect★ 1k
- View details
ap-implementerSkillAI & models
Lets your agent implement a single feature step by step using test-driven development with real test runs.
Ready to connect★ 1k
- View details
ap-independent-checkerSkillAI & models
Lets your agent independently double-check its own work by running real checks without altering the result.
Ready to connect★ 1k
- View details
ap-intakeSkillAI & models
Lets your agent reconstruct and read old intake artifacts when resuming a previous run.
Ready to connect★ 1k
- View details
ap-janitorSkillFiles & storage
Lets your agent mark a task complete with a DONE file and clean up leftover scratch files after checks pass.
Ready to connect★ 1k
- View details
ap-managerSkillAI & models
Lets your agent coordinate a multi-part task by building small pointer packages and dispatching work to sub-agents without running it itself.
Ready to connect★ 1k
- View details
ap-plannerSkillMedia
Lets your agent plan work by adding detail to roadmap items only when they explicitly need it.
Ready to connect★ 1k
- View details
ap-preflight-probeSkillAI & models
Lets your agent run a diagnostic probe to check model access and report model and effort settings after a cache miss.
Ready to connect★ 1k
- View details
ap-re-anchorSkillFiles & storage
Lets your agent recheck its current mission and roadmap after a session restart or memory compaction.
Ready to connect★ 1k
- View details
ap-researcherSkillAI & models
Lets your agent do bounded web research as a researcher claude skill, stopping at a finished deliverable or search budget.
Ready to connect★ 1k
- View details
ap-roadmap-authorSkillAI & models
Lets your agent write a dependency-ordered roadmap with owners, integration points, and success checks.
Ready to connect★ 1k
- View details
ap-roadmap-scoutSkillAI & models
Lets your agent answer a named planning question with observations tied to the sources it inspected.
Ready to connect★ 1k
- View details
ap-route-analystSkillAI & models
Lets your agent inspect project details and recommend a route with the supporting facts.
Ready to connect★ 1k
- View details
ap-run-coordinatorSkillAI & models
Lets your agent run claude skill that starts only ready, non-overlapping roadmap work and merges returned status.
Ready to connect★ 1k
- View details
ap-scoperSkillAI & models
Lets your agent write an executable ROADMAP.md by inspecting the real repository and scoping work.
Ready to connect★ 1k
- View details
ap-scribeSkillAI & models
Lets your agent log governance records for new runs into PROMPTS.txt, ROADMAP.md, and an append-only gate log.
Ready to connect★ 1k
- View details
ap-work-group-managerSkillAI & models
Lets your agent split an accepted work group among two or more workers with non-overlapping ownership.
Ready to connect★ 1k
- View details
ap-workerSkillAI & models
Lets your agent complete only its assigned task, avoid touching others' work, run checks, and report conflicts exactly.
Ready to connect★ 1k
- View details
autopromptSkillAI & models
Lets your agent run the Autoprompt orchestration loop to coordinate multi-step AI model tasks.
Ready to connect★ 1k
- View details
kill-ai-slopSkillDev tools
Lets your agent use this kill AI slop skill to find and remove the generic, templated AI look from a web project.
Ready to connect★ 1k
- View details
helpersSkillDev tools
Lets your agent find and use JavaScript/TypeScript helper functions when writing SonarJS linting rules.
Ready to connect★ 1k
- View details
new-ruleSkillFiles & storage
Lets your agent scaffold a new claude skill for writing a SonarJS linting rule from scratch.
Ready to connect★ 1k
Popular skills lists
- Best Claude skills for what are
- Best Claude skills for awesome
- Best Claude skills for github
- Best Claude skills for how to use
- Best Claude skills for anthropic
- Best Claude skills for grill me
- Best Claude skills for how to create
- Best Claude skills for caveman
- Best Claude skills for humanizer
- Best Claude skills for remotion
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.
55,384 of the 55,384 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.