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 114 of 301
- View details
war-room-checkpointSkillAI & models
Assesses decision reversibility and risk at critical checkpoints. Use when a workflow reaches a high-stakes branch needing escalation check.
Ready to connect★ 337
- View details
workflow-diagramSkillAI & models
Generates a Mermaid workflow diagram showing process steps, decisions, and state transitions. Use when documenting CI/CD pipelines or lifecycle processes.
Ready to connect★ 337
- View details
claude-paper-webuiSkillAI & models
Start the Claude Paper web viewer to browse and study papers
Ready to connect★ 336
- View details
cola-avatar-packSkillAI & models
Generate pixel-art self-portrait, profile card (自画像卡), emoji GIFs, and meme stickers. Use when: "生成形象"、"画头像"、"avatar"、"self-portrait"、"表情包"、"梗图"、"贴纸"、"sticker"、"换一个"、"重新生成"、"不喜欢"、"regenerate". Also use when: Cola wakes up — display existing avatar or prompt user to generate. Also use when: repairing
Ready to connect★ 336
- View details
omniSkillAI & models
Wire a Genie agent to an Omni channel in one canonical flow — register the host, bind the instance, route chats to a repo, verify the round-trip.
Ready to connect★ 336
- View details
webuiSkillAI & models
Start the Claude Paper web viewer to browse and study papers
Ready to connect★ 336
- View details
code-migrationSkillAI & models
Run a large-scale language migration with the six-step process: create the map and the rules, stress-test the rules, translate everything, compile, run it, match behavior. Use when the user wants to migrate, port, or rewrite a codebase from one language to another ("migrate this to Rust", "port our
Ready to connect★ 334
- View details
agent-business-canvasSkillAI & models
Use when evaluating, designing, or pressure-testing the business model of an AI agent product. Triggers on "agent business model", "agent economics", "agent canvas", "evaluate agent product", "agent pricing", "agent unit economics", "agentic business", "AI agent company", "agent cost structure".
Ready to connect★ 332
- View details
fleet-managerSkillAI & models
Use when the user asks to check on agents, manage their fleet, babysit panes, see what needs attention, get a status report, or when they say "check on my agents", "what needs action", "fleet status", "babysit", "brief me". Requires the control MCP server to be registered and the daemon running.
Ready to connect★ 332
- View details
roborev-fixSkillAI & models
Use only for a current operative request that explicitly invokes $roborev-fix, or a direct Agent Hook instruction; do not invoke from literal syntax in quoted, pasted, or historical text
Ready to connect★ 332
- View details
context-auditSkillAI & models
Audit the instructions an agent already carries — CLAUDE.md, AGENTS.md, skills, tool descriptions — for contradictions, over-constraint, and duplication, then propose a cut list. Use when an agent ignores its own instructions, when a CLAUDE.md has grown bloated, or when the user asks to audit or rig
Ready to connect★ 331
- View details
designing-the-analysisSkillAI & models
Use when you have an approved research question and need a concrete analysis plan, before touching outcome data or fitting any model
Ready to connect★ 331
- View details
executing-analysisSkillAI & models
Use when you have a pre-registered analysis plan to execute inline in this session with review checkpoints, on a platform without subagents
Ready to connect★ 331
- View details
investigating-anomalous-resultsSkillAI & models
Use when a result is surprising, impossible, contradicts a sanity check, a pipeline fails, a model won't converge, or a replication fails - before adjusting anything
Ready to connect★ 331
- View details
subagent-driven-analysisSkillAI & models
Use when executing a pre-registered analysis plan with mostly independent steps in the current session
Ready to connect★ 331
- View details
architecture-decisionSkillAI & models
Create Architecture Decision Records (ADRs) documenting major technical decisions along with their context, alternatives considered, and consequences. Every significant technical choice should have a corresponding ADR.
Ready to connect★ 329
- View details
asset-auditSkillAI & models
A Claude Code architecture for indie game development with 48 collaborative agents (Chinese localized version)
Ready to connect★ 329
- View details
balance-checkSkillAI & models
48 — A Claude Code architecture for collaborative agent management of indie game development (Chinese localized version)
Ready to connect★ 329
- View details
bug-reportSkillAI & models
Create structured bug reports from descriptions, or analyze code to identify potential bugs. Ensure each bug report includes complete reproduction steps, severity assessment, and context information.
Ready to connect★ 329
- View details
gate-checkSkillAI & models
Claude Code architecture where 48 collaborating agents manage indie game development (Chinese localized version)
Ready to connect★ 329
- View details
hotfixSkillAI & models
Claude Code architecture for 48 collaborative agents managing indie game development (Chinese localized version)
Ready to connect★ 329
- View details
launch-checklistSkillAI & models
A Claude Code architecture with 48 collaborating agents for managing indie game development (Chinese localized version)
Ready to connect★ 329
- View details
localizeSkillAI & models
Runs the localization workflow: extracts strings, validates localization readiness, checks for hardcoded text, and generates string tables ready for translation.
Ready to connect★ 329
- View details
perf-profileSkillAI & models
A structured performance profiling workflow. Identify bottlenecks, measure against performance budgets, and generate prioritized optimization recommendations.
Ready to connect★ 329
- View details
project-stage-detectSkillAI & models
Automatically analyzes project status, detects the development stage, identifies missing items, and recommends next steps based on existing artifacts.
Ready to connect★ 329
- View details
release-checklistSkillAI & models
Generates a comprehensive pre-release verification checklist covering build validation, compliance requirements, store metadata, and release readiness.
Ready to connect★ 329
- View details
retrospectiveSkillAI & models
Generates Sprint or milestone retrospectives by analyzing completed work, velocity, blockers, and patterns. Produces actionable insights to guide the next iteration.
Ready to connect★ 329
- View details
scope-checkSkillAI & models
Analyzes scope creep in a feature or sprint by comparing the current scope against the original plan. Flags added items, quantifies the bloat, and recommends cuts.
Ready to connect★ 329
- View details
setup-engineSkillAI & models
Configure the project's game engine and version. Locks the engine into CLAUDE.md, detects knowledge gaps, and uses WebSearch to fill in engine reference docs when the version is beyond the LLM's training data.
Ready to connect★ 329
- View details
startSkillAI & models
First-time onboarding guide — asks which stage you are currently at, then guides you into the correct workflow. Makes no assumptions.
Ready to connect★ 329
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.