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
54,017 results · page 218 of 1,801
- View details
loopySkillAI & models
Lets your agent find, review, and build repeatable AI-agent loops for recurring coding work.
Ready to connect★ 3k
- View details
cacSkillProductivity
Guides your agent to build and fix command-line tools using the CAC JavaScript library.
Ready to connect★ 3k
- View details
breezingSkillAI & models
Lets your agent run tasks in a team execution mode that coordinates work across multiple agents.
Ready to connect★ 3k
- View details
cc-update-reviewSkillAI & models
Reviews code changes to catch feature entries that were documented but never actually implemented.
Ready to connect★ 3k
- View details
ciSkillCloud & infra
Lets your agent diagnose and fix CI pipeline failures like build errors and failing tests.
Ready to connect★ 3k
- View details
cursor-askSkillMedia
Lets your agent ask a second AI (Cursor) read-only questions to get opinions, investigate code, and sanity-check decisions.
Ready to connect★ 3k
- View details
cursor-doSkillFiles & storage
Lets your agent delegate a single code write or refactor task to Cursor Composer and review the resulting changes.
Ready to connect★ 3k
- View details
cursor-reviewSkillAI & models
Lets your agent get a second-opinion code review from Cursor while your main agent still makes the final call.
Ready to connect★ 3k
- View details
cursor-setupSkillAI & models
Lets your agent configure and check whether Cursor is ready as the local default backend for Claude Code Harness.
Ready to connect★ 3k
- View details
failure-codifierSkillMonitoring & ops
Lets your agent analyze workflow logs to find recurring failure patterns and propose rules with confidence scores.
Ready to connect★ 3k
- View details
harness-acceptSkillFiles & storage
Generates a single-file HTML demo page showing whether each stored acceptance criterion passed before a ship decision.
Ready to connect★ 3k
- View details
harness-loopSkillProductivity
Lets your agent keep working on long-running tasks across scheduled wake-ups with fresh context each time.
Ready to connect★ 3k
- View details
harness-planSkillProductivity
Lets your agent create task plans, manage a Plans.md file, and track progress as work gets done.
Ready to connect★ 3k
- View details
harness-plan-briefSkillFiles & storage
Lets your agent create an HTML plan brief summarizing a project's goals, options, risks, and acceptance criteria before coding.
Ready to connect★ 3k
- View details
harness-progressSkillFiles & storage
Lets your agent create a single-file HTML dashboard showing task progress, costs, and estimated time from your Plans.md.
Ready to connect★ 3k
- View details
harness-releaseSkillAI & models
Lets your agent automate a project release: update the changelog, merge to main, tag, and publish a GitHub Release.
Ready to connect★ 3k
- View details
harness-reviewSkillSecurity
Lets your agent review code, plans, and scope from multiple angles for security and quality issues.
Ready to connect★ 3k
- View details
harness-setupSkillDocs & knowledge
Lets your agent initialize a new project: set up tools, agent config, memory, and sync skill mirrors.
Ready to connect★ 3k
- View details
harness-syncSkillAI & models
Lets your agent compare its implementation progress against Plans.md and report drift or updates.
Ready to connect★ 3k
- View details
harness-workSkillProductivity
Lets your agent execute tasks from a Plans.md file, running one task or several in parallel.
Ready to connect★ 3k
- View details
japanese-writing-drafterSkillAI & models
Lets your agent turn your Japanese phrasing corrections into pending writing-rule proposals saved to a file for review.
Ready to connect★ 3k
- View details
maintenanceSkillFiles & storage
Lets your agent clean up and archive cluttered planning notes, session logs, and old state files.
Ready to connect★ 3k
- View details
memorySkillSearch
Lets your agent save and search remembered decisions and patterns across your tools and sessions.
Ready to connect★ 3k
- View details
session-sendSkillCommunication
Lets your agent send messages to other agent sessions to notify them or hand off a task.
Ready to connect★ 3k
- View details
mono-colorSkillMedia
Lets your agent create one- or two-ink editorial posters and images from a theme, sentence, or photo.
Ready to connect★ 3k
- View details
designSkillDocs & knowledge
Guides your agent to follow the project's conventions when writing or editing design documents.
Ready to connect★ 3k
- View details
dynamodb-testsSkillDev tools
Guides your agent to correctly run tests against DynamoDB databases.
Ready to connect★ 3k
- View details
sync-docsSkillMonitoring & ops
Lets your agent update project documentation to match recent code changes by reviewing the git log.
Ready to connect★ 3k
- View details
azure-ai-agents-persistent-dotnetSkillSearch
Lets your agent create and manage AI agents with conversation threads, messages, runs, and tools in .NET.
Ready to connect★ 3k
- View details
azure-ai-agents-persistent-javaSkillCommunication
Lets your Java applications create and manage AI agents with threads, messages, runs and tools.
Ready to connect★ 3k
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.