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
55,286 results · page 790 of 1,843
- View details
flickSkillMedia
Turn a supplied video, public video URL, or transcript into original short-form scene animations with Remotion. Use when a user says "/flick", "$flick", "animate this", or asks to turn a video, transcript, or script into motion animation. Extract a timestamped transcript first when the source is vid
Ready to connect★ 240
- View details
ga4SkillDatabases & data
Read Google Analytics 4 reporting data through the GA4 Data API. Use for explicit GA4 property metadata, compatible metric/dimension reports, traffic analysis, key events, quotas, and bounded exports.
Ready to connect★ 240
- View details
gallery-scraperSkillWeb & browsing
Bulk download images from login-protected gallery websites using an attached browser session. Use when asked to scrape, download, or save images from authenticated gallery pages, extract full-size images from thumbnails, or batch download from multi-page galleries.
Ready to connect★ 240
- View details
gongSkillDatabases & data
Gong API for searching calls, transcripts, and conversation intelligence. Use when working with Gong call recordings, sales conversations, transcripts, meeting data, or conversation analytics. Supports listing calls, fetching transcripts, user management, and activity stats.
Ready to connect★ 240
- View details
gscSkillSearch
Read Google Search Console properties, Search Analytics, URL Inspection, and sitemaps. Use for explicit Search Console or GSC SEO performance, indexing, and freshness analysis; not for general web search.
Ready to connect★ 240
- View details
mueSkillAI & models
Activate MUE — self-evolving AI agent. Type /mue to become MUE.
Ready to connect★ 240
- View details
munger-observerSkillAI & models
Review a specific decision, plan, or artifact using bounded evidence, counterevidence, alternatives, opportunity cost, and verifiable next checks. Use for a "Munger review", decision review, premortem, or blind-spot review. Do not automatically scan history or assess a person's character, intent, or
Ready to connect★ 240
- View details
nudocsSkillDocs & knowledge
Upload, edit, and export documents via Nudocs.ai. Use when creating shareable document links for collaborative editing, uploading markdown/docs to Nudocs for rich editing, or pulling back edited content. Triggers on "send to nudocs", "upload to nudocs", "edit in nudocs", "pull from nudocs", "get the
Ready to connect★ 240
- View details
nutrient-openclawSkillDocs & knowledge
Use the pinned Nutrient OpenClaw plugin to convert, OCR, extract, redact, watermark, sign, or inspect the last-known local credit record for documents. Route only OpenClaw document-processing requests to its declared tools. Treat processing as an external, credit-consuming DWS transfer that requires
Ready to connect★ 240
- View details
parallel-taskSkillFiles & storage
Coordinate plan files by launching multiple parallel subagents for unblocked tasks. Triggers on explicit "/parallel-task" commands.
Ready to connect★ 240
- View details
pclSkillDev tools
Delete stale git branches (local + remote) that have no open PR, and prune worktrees.
Ready to connect★ 240
- View details
plannerSkillProductivity
Create structured plans for multi-task projects that can be used by the task-orchestrator skill. Use when breaking down complex work into parallel and sequential tasks with dependencies.
Ready to connect★ 240
- View details
senior-engineeringSkillAI & models
Engineering principles for building software like a senior engineer. Load when tackling non-trivial development work, architecting systems, reviewing code, or orchestrating multi-agent builds. Covers planning, delivery, quality gates, and LLM-specific patterns.
Ready to connect★ 240
- View details
setup-spaSkillCommunication
SPA (Spawn's Personal Agent) — Slack bot that pipes threads into Claude Code sessions
Ready to connect★ 240
- View details
skill-syncSkillAI & models
Sync skills between local installation and the GitHub source-of-truth repository. Use when asked to install, update, list, or push skills.
Ready to connect★ 240
- View details
spawnSkillAI & models
Create child cloud VMs with AI coding agents using the spawn CLI
Ready to connect★ 240
- View details
task-orchestratorSkillMonitoring & ops
Autonomous multi-agent task orchestration with dependency analysis, parallel tmux/Codex execution, and self-healing heartbeat monitoring. Use for large projects with multiple issues/tasks that need coordinated parallel execution.
Ready to connect★ 240
- View details
todo-trackerSkillFiles & storage
Persistent TODO scratch pad for tracking tasks across sessions. Use when the user asks to add, list, complete, remove, or summarize tasks in a portable workspace Markdown file. Uses stable task IDs and exact matching; heartbeat reporting is opt-in and count-only.
Ready to connect★ 240
- View details
- View details
ZendeskSkillAI & models
Manage Zendesk tickets, users, and support workflows through the Zendesk API. Use when searching tickets, updating support state, checking users, or exporting queue data.
Ready to connect★ 240
- View details
claude-skillSkillWeb & browsing
Use when work should be delegated to Claude Code CLI, especially headless `claude -p` runs, automation scripts, CI jobs, resumable sessions, or requests to use Claude/Claude Code for a task.
Ready to connect★ 239
- View details
minimax-image-skillSkillMedia
Generate images with the MiniMax Image API. Use when the user asks for MiniMax image generation, image-01, image-01-live, or an image from a text prompt through MiniMax.
Ready to connect★ 239
- View details
script-exec-blockedSkillDocs & knowledge
Sandbox approval policy blocks execute_code and python3 -c; use read_file/write_file + manual transforms instead of retrying both runners.
Ready to connect★ 239
- View details
search-miss-binarySkillSearch
ripgrep/search_files silently skips binary-detected files — verify empty search results with grep -a / file / xxd before concluding 'not found'.
Ready to connect★ 239
- View details
spec-literal-executionSkillDocs & knowledge
Apply ONLY the spec clauses literally — no aggregation, dedup, or cleanup transforms; each input record maps to its own output line.
Ready to connect★ 239
- View details
trace-harness-launch-failureSkillDocs & knowledge
Empty session traces mean launch failure, not agent behavior — verify api_call_count/tool_call_count and stdout.txt before analyzing.
Ready to connect★ 239
- View details
verify-output-readbackSkillDocs & knowledge
After write_file, re-read the deliverable (or ls + hexdump/line-print) and re-check the last format clauses before finishing.
Ready to connect★ 239
- View details
wikiskill-evolveSkillDocs & knowledge
Run the WikiSkill self-evolution loop (arXiv 2608.27454) on a Hermes workspace — raw→maintainer→proposer→gate with strict R_val > R_best gating.
Ready to connect★ 239
- View details
wikiskill-maintainerSkillDocs & knowledge
Consolidate traces into the persistent wiki (WikiSkill).
Ready to connect★ 239
- View details
wikiskill-proposerSkillDocs & knowledge
Propose skills from wiki patterns and traces (WikiSkill).
Ready to connect★ 239
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.
54,855 of the 55,286 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.