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
8,868 results · page 239 of 296
- View details
agent-connectivity-testSkillAI & models
External test agent connectivity workflow for QRClaw. Covers Agent SDK usage, echo/openclaw test agents, full lifecycle verification (create → claim → QR → scan → chat), and troubleshooting.
Ready to connect
- View details
analyzing-conglomerate-discount-dynamicsSkillAI & models
Evaluates conglomerate discount with SOTP analysis, segment-level valuation, and separation benefit quantification. Use when analyzing conglomerate value, building SOTP models, or evaluating break-up scenarios.
Ready to connect
- View details
analyzing-machine-learning-in-investingSkillAI & models
Evaluates ML applications in investment with feature engineering, model selection, and implementation considerations for alpha generation. Use when evaluating ML for investing, designing ML pipelines, or assessing ML strategy feasibility.
Ready to connect
- View details
analyzing-structured-product-ratingsSkillAI & models
Evaluates rating agency methodology application with loss model inputs, correlation assumptions, and tranche-level credit assessment. Use when analyzing structured product ratings, comparing agency methodologies, or assessing rating sensitivity.
Ready to connect
- View details
analyzing-unfunded-commitment-exposureSkillAI & models
Evaluates unfunded commitment obligations with call probability, pacing models, and portfolio-level exposure management. Use when analyzing unfunded exposure, managing commitment pacing, or stress testing capital calls.
Ready to connect
- View details
analyzing-volatility-surface-dynamicsSkillAI & models
Evaluates implied volatility surfaces with skew analysis, term structure dynamics, and surface fitting methodologies. Use when analyzing vol surfaces, assessing skew dynamics, or calibrating volatility models.
Ready to connect
- View details
building-multi-factor-equity-modelsSkillAI & models
Constructs multi-factor models with value, momentum, quality, size, and volatility factor definitions and portfolio construction rules. Use when building factor models, designing systematic strategies, or constructing factor portfolios.
Ready to connect
- View details
building-restructuring-plan-modelsSkillAI & models
Constructs plan of reorganization models with debt-for-equity conversion, new money injection, and emergence capital structure. Use when modeling restructuring plans, designing emergence capital structures, or analyzing plan feasibility.
Ready to connect
- View details
building-statistical-arbitrage-modelsSkillAI & models
Constructs stat arb strategies with pair selection, signal generation, and portfolio optimization under market neutrality constraints. Use when building stat arb models, designing market-neutral strategies, or optimizing pair portfolios.
Ready to connect
- View details
building-venture-return-modelsSkillAI & models
Constructs venture return models with entry valuation, follow-on reserve, multiple scenario exits, and portfolio-level fund math. Use when modeling VC returns, calculating fund economics, or projecting portfolio outcomes.
Ready to connect
- View details
council-policySkillAI & models
Policy for the cross-model council: when to hand off to an installed sibling plugin's own slash command (`/codex:*`) versus dispatching our `delegation-runner` (backend: codex|agy|…), which backend to pick, what permission posture to use, and the fan-out/cost discipline that applies regardless of ba
Ready to connect
- View details
external-contextSkillAI & models
Use when EZ_math_model multi or hybrid mode needs several domain-specialist subagents to gather outside knowledge, industry context, model theory, or sensitivity-analysis references in parallel.
Ready to connect
- View details
glossarySkillAI & models
Build or update a CONTEXT.md domain glossary for the current project. Establishes shared vocabulary with term definitions, avoid-aliases, and relationships so agents use consistent, concise language. This skill should be used when starting a new project, when domain terminology is inconsistent acros
Ready to connect
- View details
handle-reviewSkillAI & models
Analyze, evaluate, and handle pull request review feedback before changing code. Verify each comment against the current PR head, requirements, project constraints, and runtime evidence; then decide with evidence whether to fully adopt, partially adopt, or not adopt it. Prevent minor inconsistencies
Ready to connect
- View details
kb-setup-consultingSkillAI & models
Onboarding workflow for cross-library KB query in a consulting practice. Discovers existing user-scope library registrations, prompts for additions, validates each library, helps activate the relevant ones for the current project, runs a smoke test, and reports a clear "ready" or "issues to fix" ver
Ready to connect
- View details
mindnode-uiSkillAI & models
Build MindNode-inspired mind mapping interfaces — 8 node shapes, 27+ themes, layout algorithms (horizontal, vertical, radial with D3), keyboard shortcuts, focus mode, dual view. React + xyflow/react v12 + Zustand + Tailwind. Triggers on mind map, visual thinking tool, node-based diagram, brainstorm
Ready to connect
- View details
modular-architectureSkillAI & models
Enforces modular domain architecture and clean code standards. Use when creating or refactoring packages, domains, components, services, models, and tests in packages/*.
Ready to connect
- View details
new-serviceSkillAI & models
Scaffold a new go-zero microservice (rpc + api + model) under apps/. Triggered when the user says new service, add microservice, or scaffold service.
Ready to connect
- View details
open-interpreterSkillAI & models
Desktop GUI automation via OpenInterpreter — mouse, keyboard, screenshot, and OCR control for native macOS/Linux applications. Three modes: Library (Claude reasons, OI executes), OS subprocess (full autonomous computer use), and Local agent (Ollama, offline). This skill should be used when interacti
Ready to connect
- View details
openrouter-usageSkillAI & models
Query OpenRouter API costs, credits, and usage breakdown by model, provider, and date for the last 30 days. Triggers on API spending, check costs, openrouter usage, how much have I spent.
Ready to connect
- View details
orchestrating-swarmsSkillAI & models
Coordinate multi-agent swarms for parallel and pipeline workflows. Use when coordinating multiple agents, running parallel reviews, building pipeline workflows, or implementing divide-and-conquer patterns with subagents.
Ready to connect
- View details
paper-orchestraSkillAI & models
EZMM writer-stage adapter for the vendored PaperOrchestra skill pack. Use by default during pipeline/04-paper-writing for outline-first paper drafting, literature-review planning, section writing, and refinement discipline. The adapter maps EZMM runtime artifacts to PaperOrchestra-style inputs, runs
Ready to connect
- View details
pitfallsSkillAI & models
Use PITFALLS.md to prevent repeated environment, tool, permission, sandbox, and tool-invocation failures, and maintain it with verified context-dependent guidance. Use before project tool work, when a matching operational pitfall occurs, after confirming a reusable new pitfall, or when explicitly in
Ready to connect
- View details
proxelarSkillAI & models
Intercept, inspect, and modify HTTP/HTTPS traffic via a Rust MITM proxy with Lua scripting hooks. Supports API debugging, LLM call capture for evals, endpoint mocking, CORS/auth header injection, latency simulation, and telemetry blocking. Triggers on 'proxy', 'intercept traffic', 'inspect requests'
Ready to connect
- View details
refine-promptSkillAI & models
Transforms vague prompts into precise, structured AI instructions. Use when asked to refine, improve, or sharpen a prompt, do prompt engineering, write a system prompt, or make AI instructions more effective.
Ready to connect
- View details
rocaille-shaderSkillAI & models
Generate Rocaille-style domain warping shaders, mouse-reactive liquid logo effects, depth-map parallax heroes (Astryx-style hover-reactive statues), and stable fluid simulations over live DOM. Four modes — rocaille, liquid-logo, astryx-statue, fluid-dom. Triggers on shader art, depth parallax, hover
Ready to connect
- View details
simplifying-codeSkillAI & models
Simplifies, polishes, and declutters code without changing behavior. Use when asked to simplify, clean up, refactor, declutter, remove dead code or AI slop, or improve readability. For analysis-only reports without code changes, use code-simplicity-reviewer agent.
Ready to connect
- View details
skill-toggleSkillAI & models
Enable, disable, and manage Claude Code skills. Use when the user asks to enable/disable/toggle/manage skills, check skill status, list skills, manage skill collections, or clean up the skills directory.
Ready to connect
- View details
speak-responseSkillAI & models
Vocalize Claude's last response using local Qwen3-TTS. Default voice is the Oracle (deep, resonant Dune narrator). Use --preset for emotion-controlled preset speakers.
Ready to connect
- View details
stop-slopSkillAI & models
Strip AI writing patterns from prose across five registers — casual, professional, academic, technical, and narrative. Applies 200+ pattern rules to eliminate predictable LLM tells. Triggers on clean up writing, remove AI slop, edit prose, make this sound less AI.
Ready to connect
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.
53,585 of the 54,017 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.