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.
Category: AI & models
9,019 results · page 101 of 301
- View details
claude-md-updaterSkillAI & models
Scans the session for lessons and workflows, then proposes scoped CLAUDE.md edits. Use for save this lesson or add to context.
Ready to connect★ 393
- View details
content-accessSkillAI & models
Legal methods for paywalled and geo-blocked content. Use for paywalls, academic papers, or open access via Unpaywall.
Ready to connect★ 393
- View details
context-engineering-fundamentalsSkillAI & models
Manages attention and evidence in long agent sessions. Use for lost instructions, dropped evidence, or large multi-agent contexts.
Ready to connect★ 393
- View details
crisis-communicationsSkillAI & models
Crisis communication and rapid-response workflows. Use when covering breaking news or coordinating fast fact-checking on deadline.
Ready to connect★ 393
- View details
data-journalismSkillAI & models
Acquire, clean, analyze, verify, visualize, and explain data for journalism. Use for reproducible data reporting, statistical analysis, maps, or public methodology.
Ready to connect★ 393
- View details
digital-archiveSkillAI & models
Digital archiving with AI enrichment and entity extraction. Use when building content archives or knowledge graphs.
Ready to connect★ 393
- View details
directorSkillAI & models
Directs the current request through configured lower-tier agents. Use only for explicit /director or /dev-toolkit:director invocation.
Ready to connect★ 393
- View details
electron-devSkillAI & models
Electron desktop apps with React, TypeScript, and Vite. Use for IPC, window/tray, PTY terminals, WebRTC, and packaging.
Ready to connect★ 393
- View details
executing-plansSkillAI & models
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Ready to connect★ 393
- View details
fact-check-workflowSkillAI & models
Structured fact-checking workflow. Use when verifying claims for publication, rating claims, or setting pre-publication checks.
Ready to connect★ 393
- View details
finishing-a-development-branchSkillAI & models
Presents options for merge, PR, or cleanup. Use when work is complete, tests pass, and you must decide how to integrate.
Ready to connect★ 393
- View details
foia-requestsSkillAI & models
FOIA and public records workflows. Use when drafting requests, tracking submissions, checking exemptions, or appealing denials.
Ready to connect★ 393
- View details
interview-prepSkillAI & models
Interview preparation and recording-consent law. Use for research, question frameworks, one-party or all-party consent rules.
Ready to connect★ 393
- View details
master-debateSkillAI & models
Use when user explicitly asks for an adversarial / multi-round dialectic between masters — 祖师辩论, 各执一词, 谁更对, debate, 应成 vs 顿悟, 顿渐之争. Differs from /compare-masters (parallel single-round) by being adversarial multi-round via fresh-subagent orchestration. Topics 空有 / 禅净 / 性相 / 戒律 vs 内观 — trigger is adv
Ready to connect★ 393
- View details
mobile-debuggingSkillAI & models
Remote JavaScript console and debugging on mobile. Use for phone/tablet console errors, responsive testing, Eruda, and vConsole.
Ready to connect★ 393
- View details
newsroom-styleSkillAI & models
Enforces AP Style and newsroom conventions. Use when writing news, editing drafts, creating headlines, or tightening copy.
Ready to connect★ 393
- View details
one-way-doorSkillAI & models
Flags irreversible decisions before commit. Use for data models, infra, auth boundaries, API contracts, event schemas, CI/CD.
Ready to connect★ 393
- View details
python-pipelineSkillAI & models
Python data pipelines with modular architecture. Use for content workflows, batch jobs, or Google Sheets/Drive integration.
Ready to connect★ 393
- View details
receiving-code-reviewSkillAI & models
Verifies review feedback with technical rigor, not blind agreement. Use when receiving review before implementing suggestions.
Ready to connect★ 393
- View details
rlmSkillAI & models
Recursive Language Model (RLM) loop for processing a context that is too large to read into the conversation directly. Loads the context as a variable in a persistent Python REPL and answers the query by writing code that probes, chunks, and programmatically sub-queries a cheap LLM (`llm_query`) ove
Ready to connect★ 392
- View details
story-pitchSkillAI & models
Crafts story pitches for different outlets. Use when pitching editors, writing query letters, or shaping feature or op-ed angles.
Ready to connect★ 393
- View details
systematic-debuggingSkillAI & models
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Ready to connect★ 393
- View details
template-selectorSkillAI & models
Selects the correct CLAUDE.md or LESSONS.md template via decision trees. Use when starting a project or unsure which fits.
Ready to connect★ 393
- View details
test-first-bugsSkillAI & models
Enforces a test-driven bug-fixing workflow. Use when a user reports a bug, failing code, an error, or asks to fix something.
Ready to connect★ 393
- View details
using-git-worktreesSkillAI & models
Creates isolated git worktrees with smart directory selection and safety checks. Use when starting isolated feature work.
Ready to connect★ 393
- View details
using-superjawnSkillAI & models
Establishes how to find and use skills, requiring Skill tool invocation before any response. Use when starting any conversation.
Ready to connect★ 393
- View details
verification-before-completionSkillAI & models
Runs verification commands and confirms output before success claims. Use before claiming work done or committing or PRs.
Ready to connect★ 393
- View details
vibe-codingSkillAI & models
AI-assisted coding with Claude Code, Cursor, Copilot, Codex, Aider, or Windsurf. Use to build or debug generated code.
Ready to connect★ 393
- View details
web-archivingSkillAI & models
Web archiving and retrieval via Wayback Machine and Archive.today. Use to preserve content, reach dead pages, or save evidence.
Ready to connect★ 393
- View details
web-ui-best-practicesSkillAI & models
Signs of taste in web UI. Use when building or reviewing web interfaces, dashboards, SaaS apps, or internal tools.
Ready to connect★ 393
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.
54,764 of the 55,196 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.