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
9,032 results · page 229 of 302
- View details
cm-reactorSkillAI & models
Strategic codebase re-direction when requirements change, architecture doesn't fit, or tech debt blocks progress. TRIZ-powered pivot protocol for large codebases.
Ready to connect★ 53
- View details
cm-safe-i18nSkillAI & models
Safe i18n: multi-pass batching, parallel-per-language dispatch, 8 audit gates, HTML integrity. Use for translating or mass-converting hardcoded strings to t() calls.
Ready to connect★ 53
- View details
cm-second-opinion-cliSkillAI & models
[Deprecated] engineering bridge merged. Use `cm-mcp-engineering` instead.
Ready to connect★ 53
- View details
cm-skill-evolutionSkillAI & models
Repair or extend CodyMaster skills with a three-mode loop: FIX, DERIVED, and CAPTURED, grounded in current repo tooling.
Ready to connect★ 53
- View details
cm-skill-healthSkillAI & models
[Deprecated] skill lifecycle merged. Use `cm-skill-evolution` instead.
Ready to connect★ 53
- View details
cm-skill-indexSkillAI & models
Progressive Disclosure skill index — efficient skill loading in 3 layers. Layer 1 (index, ~100 tokens) always loaded. Layer 2 (summary, ~300 tokens) loaded on context need. Layer 3 (full SKILL.md) loaded on execution only.
Ready to connect★ 53
- View details
cm-skill-masterySkillAI & models
[Deprecated] discovery and meta-skill merged. Use `cm-skill-index` instead.
Ready to connect★ 53
- View details
cm-skill-shareSkillAI & models
[Deprecated] skill lifecycle merged. Use `cm-skill-evolution` instead.
Ready to connect★ 53
- View details
cm-startSkillAI & models
Start the CM Workflow to execute your objective from idea to production code.
Ready to connect★ 53
- View details
cm-tddSkillAI & models
Use when implementing any feature or bugfix. Routes to the core Red-Green-Refactor loop, test quality guidance, rationalization handling, examples, or stuck-state recovery.
Ready to connect★ 53
- View details
cm-test-gateSkillAI & models
[Deprecated] quality gate now covers tests + canary. Use `cm-quality-gate` instead.
Ready to connect★ 53
- View details
coherence-engineSkillAI & models
The LLM as consistency maintainer and orchestrator
Ready to connect★ 53
- View details
emacsSkillAI & models
GNU Emacs as a stateful Lisp machine for agents — daemon, moo-* protocol, emacs.py router, emacs:// URLs, spoken grammar, play-learn-lift.
Ready to connect★ 53
- View details
openai-agentsSkillAI & models
Build AI applications with OpenAI Agents SDK - text agents, voice agents, multi-agent handoffs, tools with Zod schemas, guardrails, and streaming. Prevents 11 documented errors.
Ready to connect★ 53
- View details
openai-apiSkillAI & models
Build with OpenAI stateless APIs - Chat Completions (GPT-5.2, o3), Realtime voice, Batch API (50% savings), Embeddings, DALL-E 3, Whisper, and TTS. Prevents 16 documented errors.
Ready to connect★ 53
- View details
- View details
refine-codeSkillAI & models
Improve existing code at any scale — from cleaning up a single function to restructuring an entire module hierarchy to proving what can safely be deleted. Use this skill whenever the user wants to simplify code, refactor for readability, find architectural improvements, consolidate tightly-coupled m
Ready to connect★ 53
- View details
sdlc-config-reviewSkillAI & models
Scans the Java code diff of the current branch against the baseline branch (master/main) and extracts items that require manual handling outside the code before release — ① Config center (Apollo/Nacos) keys: @Value single values, @ConfigurationProperties prefixes, and ${...} placeholders in any anno
Ready to connect
- View details
sdlc-guardrailsSkillAI & models
Deterministic guardrail engine that enforces "write-it-and-it's-wrong" red-lines at write time - a PostToolUse hook runs engine/check.py on every Write/Edit and blocks violations per project-defined guardrails.yaml rules (forbid / require / require_if / count_ge), with pre-commit fallback and --chec
Ready to connect
- View details
society-of-mindSkillAI & models
Intelligence emerges from many simple agents (Minsky)
Ready to connect★ 53
- View details
sub-agent-patternsSkillAI & models
Comprehensive guide to sub-agents in Claude Code: built-in agents (Explore, Plan, general-purpose), custom agent creation, configuration, and delegation patterns.
Ready to connect★ 53
- View details
ts-agent-sdkSkillAI & models
Generate typed TypeScript SDKs for AI agents to interact with MCP servers. Converts JSON-RPC curl commands to clean function calls. Auto-generates types, client methods, and example scripts from MCP tool definitions.
Ready to connect★ 53
- View details
30x-seo-localSkillAI & models
Local SEO audit and optimization for Google Business Profile, Google Maps, and Gemini Ask Maps. Covers GBP completeness, NAP consistency, review strategy, local schema, competitor benchmarking, GeoGrid visibility, multi-location, AI Local Pack readiness, and GBP suspension prevention. Use when user
Ready to connect★ 52
- View details
account-selectionSkillAI & models
Select and prioritize target accounts for ABM programs — scoring models, tier assignment, TAM segmentation. Triggers on: "account selection", "target account list", "tier accounts", "prioritize accounts", "TAM segmentation".
Ready to connect★ 52
- View details
add-connectorSkillAI & models
Onboard a `deus connect` connector — a way to route Claude Code sessions to non-Claude models (e.g. GPT via CLIProxyAPI) alongside normal Claude access. Generic orchestrator over whichever connector is selected.
Ready to connect★ 52
- View details
add-listen-hotkeySkillAI & models
Install a global hotkey that triggers `deus listen` from anywhere on the OS. Also installs sox, whisper-cli, and a whisper model.
Ready to connect★ 52
- View details
add-llama-cppSkillAI & models
Install and verify a local llama.cpp server for optional Deus local-generation experiments. Keeps Ollama as the required default for embeddings and judge work.
Ready to connect★ 52
- View details
aer-identificationSkillAI & models
Use when selecting, implementing, or stress-testing the causal identification strategy for an empirical economics manuscript — difference-in-differences (including staggered designs), instrumental variables (including weak-IV-robust inference), regression discontinuity, synthetic control, or shift-s
Ready to connect★ 52
- View details
churn-predictionSkillAI & models
Build churn prediction models — leading indicators, risk scoring, early warning systems, intervention playbooks. Triggers on: "churn prediction", "predict churn", "churn model", "early warning", "risk scoring".
Ready to connect★ 52
- View details
codeSkillAI & models
Implement production changes with or without new test coverage.
Ready to connect★ 52
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.