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
54,680 results · page 639 of 1,823
- View details
the-loopSkillMedia
Lets your agent record and visually critique UIs, animations, or videos to verify they work correctly.
Ready to connect★ 379
- View details
video-memorySkillSearch
Lets your agent search and answer questions across videos you have watched before.
Ready to connect★ 379
- View details
watching-videosSkillFiles & storage
Lets your agent watch videos by downloading them, extracting frames, and transcribing audio to summarize content.
Ready to connect★ 379
- View details
architecture-leadSkillMedia
Lets your agent get architecture advice and decisions on system design, patterns, and component boundaries.
Ready to connect★ 378
- View details
board-of-directorsSkillProductivity
Lets your agent simulate a panel of five experts debating a decision before you commit to it.
Ready to connect★ 378
- View details
conductor-orchestratorSkillCommunication
Lets your agent coordinate multiple sub-agents in parallel workflows, dispatching tasks and aggregating their results.
Ready to connect★ 378
- View details
context-loaderSkillDev tools
Lets your agent load project context files so it understands the codebase without using many tokens.
Ready to connect★ 378
- View details
cto-plan-reviewerSkillAI & models
Lets your agent review a technical plan and critique its architecture, tech choices, and tech debt.
Ready to connect★ 378
- View details
eval-business-logicSkillDev tools
Lets your agent check that code implementing product rules like pricing, state machines, and pipelines behaves correctly.
Ready to connect★ 378
- View details
eval-code-qualitySkillDev tools
Lets your agent grade code quality by checking build integrity, type safety, error handling, tests, and dead code.
Ready to connect★ 378
- View details
eval-integrationSkillDatabases & data
Lets your agent check whether integrations with services like Supabase, Stripe, and Gemini work correctly.
Ready to connect★ 378
- View details
eval-ui-uxSkillMedia
Lets your agent review UI designs for visual consistency, layout quality, and design system compliance.
Ready to connect★ 378
- View details
knowledge-managerSkillAI & models
Loads past solutions and known errors from a knowledge base into your agent's planning so it avoids repeating mistakes.
Ready to connect★ 378
- View details
loop-execution-evaluatorSkillMedia
Routes your agent's work for evaluation by picking the right specialized evaluator based on the task type.
Ready to connect★ 378
- View details
loop-executorSkillProductivity
Lets your agent work through a plan file task by task, writing code, updating the plan, and committing as it goes.
Ready to connect★ 378
- View details
loop-plan-evaluatorSkillProductivity
Lets your agent check a project plan for errors and scope issues before coding starts, returning a pass or fail verdict.
Ready to connect★ 378
- View details
loop-plannerSkillProductivity
Lets your agent create a phased feature plan with tasks, acceptance criteria, and dependencies from your spec.
Ready to connect★ 378
- View details
message-busSkillFiles & storage
Lets your agents coordinate by sending progress updates, task signals, and messages through a shared file queue.
Ready to connect★ 378
- View details
parallel-dispatchSkillMonitoring & ops
Lets your agent run multiple worker tasks at the same time and track their results and failures.
Ready to connect★ 378
- View details
plan-critiquerSkillDocs & knowledge
Lets your agent critique strategic documents like business plans to find blind spots and challenge assumptions.
Ready to connect★ 378
- View details
product-leadSkillDev tools
Lets your agent get product guidance on scope, priorities, and ambiguous requirements within a Conductor project.
Ready to connect★ 378
- View details
python-project-creatorSkillAI & models
Lets your agent set up new Python projects with folder structure, virtual environments, and dependency management.
Ready to connect★ 378
- View details
qa-leadSkillDev tools
Lets your agent act as a QA lead, setting test coverage rules and approving or rejecting quality gates.
Ready to connect★ 378
- View details
retrospective-agentSkillAI & models
Lets your agent review completed work, record lessons learned, and update its knowledge files with patterns and errors.
Ready to connect★ 378
- View details
tech-leadSkillDev tools
Lets your agent get advice on implementation approaches, dependency choices, and coding patterns, approving small dependencies.
Ready to connect★ 378
- View details
track-managerSkillProductivity
Lets your agent manage Conductor tracks, phases, and tasks, including updating task markers and switching between tracks.
Ready to connect★ 378
- View details
using-supaconductorSkillDev tools
Sets up how your agent finds and uses skills by requiring a skill lookup before any response.
Ready to connect★ 378
- View details
banini-trackerSkillCommunication
Lets your agent fetch Banini Facebook posts, analyze contrarian indicators, and send the results to Telegram.
Ready to connect★ 376
- View details
deepdiveSkillSearch
Lets your agent research a question online and produce a cited Q&A report you can save and reuse.
Ready to connect★ 377
- View details
backendSkillDatabases & data
Guides your agent to build Supabase database schemas, API routes, and server-side logic for a feature after the frontend exists.
Ready to connect★ 374
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.
54,249 of the 54,680 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.