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 1122 of 1,847

  • meshy-openclawSkillMedia

    Lets your agent create 3D models from text or images, rig and animate characters, and prepare files for 3D printing.

    Ready to connect★ 95

    github.com/meshy-dev/meshy-3d-agent95 stars

    View details
  • migration-ready-schemaSkillCommerce & finance

    Gives your agent rules for designing database schemas so customer data can be imported without missing columns.

    Ready to connect★ 95

    github.com/avelikiy/great_cto95 stars

    View details
  • observability-baselineSkillMonitoring & ops

    Wires error tracking, structured logging, and health check endpoints into your app so it's observable in production.

    Ready to connect★ 95

    github.com/avelikiy/great_cto95 stars

    View details
  • open-loops-advanceSkillDev tools

    Lets your agent use the open claude skill to turn a promoted open loop into a falsifiable hypothesis backed by evidence.

    Ready to connect★ 95

    github.com/real-simple-labs/parker-brain79 stars

    View details
  • open-loops-validateSkillDev tools

    Open Claude skill that runs a hypothesis's test plan and resolves it as validated, invalidated, inconclusive, or lacking evidence.

    Ready to connect★ 95

    github.com/real-simple-labs/parker-brain79 stars

    View details
  • PICT Test Case GeneratorSkillDocs & knowledge

    Lets your agent generate pairwise test cases and PICT models from your requirements or code.

    Ready to connect★ 95

    github.com/omkamal/pypict-claude-skill84 stars

    View details
  • plan-executionSkillProductivity

    Lets your agent execute an implementation plan claude skill task by task, running checks and stopping if the code drifts.

    Ready to connect★ 95

    github.com/thiientv/godmode95 stars

    View details
  • pm-planningSkillDocs & knowledge

    Lets your agent break an approved architecture document into a task list with dependencies, time-boxes, and acceptance criteria.

    Ready to connect★ 95

    github.com/avelikiy/great_cto95 stars

    View details
  • pr-code-reviewerSkillSecurity

    Lets your agent review a GitHub pull request for bugs, security issues, and missing tests before merging.

    Ready to connect★ 95

    github.com/thiientv/godmode95 stars

    View details
  • product-economicsSkillDev tools

    Lets your agent check if a product can be profitable by calculating contribution margin, pricing, and market size with labeled assumptions.

    Ready to connect★ 95

    github.com/avelikiy/great_cto95 stars

    View details
  • propagate-craftSkillFiles & storage

    Lets your agent push updated copies of a shared methodology bundle into project files that hold an older version.

    Ready to connect★ 95

    github.com/real-simple-labs/parker-brain79 stars

    View details
  • prose-styleSkillSecurity

    Makes your agent write reports and docs in a direct, evidence-based style without hedging or marketing language.

    Ready to connect★ 95

    github.com/avelikiy/great_cto95 stars

    View details
  • quant-validationSkillCommerce & finance

    Lets your agent apply rigorous validation checks to financial machine-learning results before trusting them.

    Ready to connect★ 95

    github.com/avelikiy/great_cto95 stars

    View details
  • refresh-contextSkillDocs & knowledge

    Lets your agent find docs that are overdue for review or made stale by upstream changes.

    Ready to connect★ 95

    github.com/real-simple-labs/parker-brain79 stars

    View details
  • research-loopsSkillDev tools

    Lets your agent run weekly research cycles with this research claude skill that answers open strategic questions.

    Ready to connect★ 95

    github.com/real-simple-labs/parker-brain79 stars

    View details
  • rl-checkSkillAI & models

    Checks your Lego-RL training, eval, or inference config for errors before you launch a run.

    Ready to connect★ 95

    github.com/legox/lego-rl71 stars

    View details
  • rl-dashboardSkillCloud & infra

    Lets your agent start or troubleshoot the local RL dashboard Claude skill runs, picking ports, logs and tunnels.

    Ready to connect★ 95

    github.com/legox/lego-rl71 stars

    View details
  • rl-k8s-sandbox-installSkillCloud & infra

    Guides your agent through installing or growing a sandbox Kubernetes cluster for Lego-RL training.

    Ready to connect★ 95

    github.com/legox/lego-rl71 stars

    View details
  • rl-runSkillAI & models

    Lets your agent run claude skill commands to launch training, eval, or infer jobs only after checks pass and you confirm.

    Ready to connect★ 95

    github.com/legox/lego-rl71 stars

    View details
  • rl-statusSkillMonitoring & ops

    Lets your agent check the status of a Lego-RL training run and report progress, logs, metrics, and known failures.

    Ready to connect★ 95

    github.com/legox/lego-rl71 stars

    View details
  • root-cause-debuggingSkillMonitoring & ops

    Lets your agent debug a bug or failing test by reproducing it, testing hypotheses, and finding the root cause.

    Ready to connect★ 95

    github.com/thiientv/godmode95 stars

    View details
  • safe-migrationsSkillFiles & storage

    Lets your agent plan and run safe migrations of APIs, schemas, dependencies, and data with rollback paths.

    Ready to connect★ 95

    github.com/thiientv/godmode95 stars

    View details
  • save-brainSkillFiles & storage

    Lets your agent save, back up, and sync its knowledge files by writing them to a folder that syncs automatically.

    Ready to connect★ 95

    github.com/real-simple-labs/parker-brain79 stars

    View details
  • scriptwritingSkillDev tools

    Lets your agent write spoken-sounding ad scripts adapted to a brand's voice using reference ads.

    Ready to connect★ 95

    github.com/real-simple-labs/parker-brain79 stars

    View details
  • self-improvement-intakeSkillDev tools

    Lets your agent record lessons from your feedback and decisions so it improves over time.

    Ready to connect★ 95

    github.com/real-simple-labs/parker-brain79 stars

    View details
  • serenity-methodSkillDev tools

    Lets your agent apply the Serenity Claude skill stock-analysis method to any ticker, sector, or situation.

    Ready to connect★ 94

    github.com/lanfuli/aleabito-serenity-skills95 stars

    View details
  • serenity-radarSkillDev tools

    Lets your agent use the Serenity Claude skill to read a trader's mention archive and suggest ideas in her style.

    Ready to connect★ 94

    github.com/lanfuli/aleabito-serenity-skills95 stars

    View details
  • set-up-brainSkillDev tools

    Lets your agent set up a new brand workspace by creating its repo and greeting the user.

    Ready to connect★ 95

    github.com/real-simple-labs/parker-brain79 stars

    View details
  • setup-routinesSkillProductivity

    Sets up recurring background routines for your agent, like refreshing context and running research loops, without asking.

    Ready to connect★ 95

    github.com/real-simple-labs/parker-brain79 stars

    View details
  • skeptical-triageSkillAI & models

    Lets your agent double-check its findings by challenging them in rounds to filter out false positives.

    Ready to connect★ 95

    github.com/avelikiy/great_cto95 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.

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.

See how to connect your AI