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
55,055 results · page 677 of 1,836
- View details
- View details
Create IssueSkillAI & models
Lets your agent create a new GitHub issue with a formatted description, labels, and reference links.
★ 335
- View details
creatorSkillDev tools
Lets your agent generate platform-ready content packages like articles and posts from a creator workflow.
Ready to connect★ 335
- View details
curateSkillDocs & knowledge
Lets your agent save developer notes and reasoning into a shared knowledge base for later reference.
Ready to connect★ 335
- View details
damage-controlSkillAI & models
Helps your agent recover after a crash, context overflow, merge conflicts, or corrupted session state.
Ready to connect★ 335
- View details
data-flowSkillMonitoring & ops
Lets your agent create a Mermaid sequence diagram showing how data moves between components.
Ready to connect★ 335
- View details
decision-journalSkillMonitoring & ops
Lets your agent record project decisions, tradeoffs, and lessons learned in a shared journal.
Ready to connect★ 335
- View details
decisive-actionSkillAI & models
Guides your agent to act on its own when intent is clear and only ask you questions when it truly matters.
Ready to connect★ 335
- View details
deferred-captureSkillAI & models
Lets your agent follow a shared contract for capturing deferred items and adding source labels in plugins.
Ready to connect★ 335
- View details
delegation-coreSkillProductivity
Lets your agent hand execution tasks like bulk extraction and summarization to external LLM CLIs while keeping reasoning local.
Ready to connect★ 335
- View details
dependency-graphSkillAI & models
Lets your agent generate a Mermaid diagram of how modules import each other to spot circular dependencies.
Ready to connect★ 335
- View details
dependency-verificationSkillAI & models
Lets your agent check that a software package actually exists before installing or recommending it.
Ready to connect★ 335
- View details
diff-analysisSkillDocs & knowledge
Lets your agent analyze code changes by categorizing them, scoring their risk, and drafting release notes.
Ready to connect★ 335
- View details
digital-garden-cultivatorSkillDocs & knowledge
Lets your agent organize and tend a growing collection of linked notes, tracking maturity and flagging stale or dead content.
Ready to connect★ 335
- View details
DismissSkillAI & models
Lets your agent shut down the egregore gracefully while saving all state.
★ 335
- View details
Do IssueSkillAI & models
Lets your agent implement coding issues from GitHub, GitLab, or Bitbucket through an analyze-specify-plan-implement workflow.
★ 335
- View details
document-conversionSkillDocs & knowledge
Lets your agent convert PDFs, DOCX files, and web pages into markdown text it can read.
Ready to connect★ 335
- View details
dorodangoSkillAI & models
Lets your agent improve already-working code through repeated quality passes before release.
Ready to connect★ 335
- View details
Elegant Code ReviewSkillAI & models
Lets your agent review code changes against a decision ladder and propose deletions.
★ 335
- View details
elegant-codeSkillAI & models
Guides your agent to write minimal code and pick dependencies using a safety checklist.
Ready to connect★ 335
- View details
error-patternsSkillAI & models
Gives your agent standard patterns for classifying errors, retrying failures, and degrading gracefully when things break.
Ready to connect★ 335
- View details
escalation-governanceSkillAI & models
Helps your agent decide when upgrading to a more capable model is actually justified, with a step-by-step decision framework.
Ready to connect★ 335
- View details
evaluation-frameworkSkillAI & models
Gives your agent reusable patterns for scoring things with weighted criteria and making threshold-based decisions.
Ready to connect★ 335
- View details
explainerSkillMedia
Lets your agent create explainer videos with narration and AI-generated visuals from a topic you describe.
Ready to connect★ 335
- View details
Filter LogSkillFiles & storage
Suggests tier-1 filter commands for a log file before compression or pasting.
★ 335
- View details
Fix PrSkillAI & models
Lets your agent read code review comments, make the requested fixes, and resolve the discussion threads.
★ 335
- View details
Fix WorkflowSkillAI & models
Lets your agent review past workflow runs and suggest improvements using learned patterns.
★ 335
- View details
FixitSkillAI & models
Lets your agent fix broken code by analyzing error output and stack traces, then verifying the fix works.
★ 335
- View details
friction-detectorSkillAI & models
Lets your agent spot friction patterns in coding sessions and turn them into rules during retrospectives.
Ready to connect★ 335
- 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.
54,624 of the 55,055 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.