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 126 of 301
- View details
program-to-tlaplus-spec-generatorSkillAI & models
Automatically generate TLA+ specifications from program code, repositories, or system implementations. Use when asked to generate TLA+ spec, create TLA+ specification from code, convert program to TLA+, formalize system in TLA+, extract TLA+ model from code, or when working with formal specification
Ready to connect★ 252
- View details
python-repo-quickstartSkillAI & models
Quickly analyzes Python repositories to understand their purpose, structure, and setup requirements. Use when Claude needs to onboard to a new Python codebase, understand project structure, identify entry points, determine dependencies, or generate setup instructions. Trigger when users ask to "anal
Ready to connect★ 252
- View details
python-test-updaterSkillAI & models
Updates Python test code to work with new versions of the code being tested. Use when Claude needs to: (1) Update tests after code changes, (2) Fix broken tests due to signature changes, (3) Update assertions to match new behavior, (4) Add test cases for new functionality, (5) Analyze code differenc
Ready to connect★ 252
- View details
rtl-property-inferenceSkillAI & models
Automatically infer formal correctness properties from Verilog/SystemVerilog RTL code and generate SystemVerilog Assertions (SVA). Identifies control-flow invariants (mutual exclusion, valid-ready handshakes, pipeline ordering, safety properties), liveness expectations, and temporal properties. Use
Ready to connect★ 252
- View details
running-the-proxySkillAI & models
Use when running the `liter-llm api` OpenAI-compatible gateway — virtual keys, per-key rate limits, budgets, cost tracking, and model routing. Covers the TOML config and the 22 REST endpoints.
Ready to connect★ 252
- View details
streaming-responsesSkillAI & models
Use when streaming tokens incrementally from an LLM via liter-llm over SSE or async iterators. Covers chat_stream, delta handling, and null-content chunks.
Ready to connect★ 252
- View details
tool-callingSkillAI & models
Use when defining functions/tools for an LLM to call through liter-llm, or requesting structured JSON outputs. Covers tool schemas, tool_calls handling, and response formats.
Ready to connect★ 252
- View details
ralph-loopSkillAI & models
Run a high-thoroughness end-to-end implementation loop using clean worker worktrees, per-slice planning, implementation, explicit review/fix iteration, orchestrator integration, and final commit/PR drafting. Use when the user explicitly wants a Ralph/Wiggum-style loop, autonomous multi-agent executi
Ready to connect★ 250
- View details
review-orchestrateSkillAI & models
Orchestrate a broad Incan review using specialized reviewer roles, parallel slice reports, and a canonical merged review report. Use when the user asks for delegated review, multi-agent review, or when a broad dirty worktree should be reviewed by specialized passes rather than one generic reviewer.
Ready to connect★ 250
- View details
codedrobe-themeSkillAI & models
Create, inspect, convert, apply, replace, verify, troubleshoot, update, publish, or restore reversible CodeDrobe themes for supported Chromium/Electron AI desktop apps, including OpenAI Codex, Tencent WorkBuddy, QoderWork (CN/global), and TRAE SOLO (global/CN). Use when a user asks to turn an attach
Ready to connect★ 247
- View details
nac-onboardingSkillAI & models
Install and configure Arcee AI nac, get the user into the nac dashboard, and connect their MCP client to nac. Use when a user asks to get started with nac, connect nac to an agent, add MCP servers, or expose nac's MCP server to Claude Code, Codex, OpenCode, or another MCP client.
Ready to connect★ 243
- View details
implement-reviewSkillAI & models
Review loop for staged changes. Detects content type, prepares a review request for Codex (Terminal-relay manual default, opt-in Auto-terminal codex-exec subprocess, or IDE plugin), categorizes feedback, revises, and iterates. Works for code, papers, proposals, or any text-based output.
Ready to connect★ 244
- View details
llm-comparisonSkillAI & models
Analyze and produce a llm comparison with structured process, quality checks, and system integration
Ready to connect★ 244
- View details
my-routerSkillAI & models
Context-aware router that detects work type and dispatches to the right skill. Ships with a minimal default routing table; extend it in a fork, or register project-local skills in a consuming repo via routing-table.local.md or an AGENTS.local.md Routing section.
Ready to connect★ 244
- View details
prompt-engineering-guideSkillAI & models
Practical prompt engineering guide for solopreneurs — working efficiently with Claude and ChatGPT
Ready to connect★ 244
- View details
prompt-template-builderSkillAI & models
Create a prompt template builder with structured process, quality checks, and system integration
Ready to connect★ 244
- View details
grace-setup-subagentsSkillAI & models
Create GRACE 4 worker and reviewer subagent presets that understand .grace artifacts, scopes, assertions, and verification evidence.
Ready to connect★ 241
- View details
a-share-dcfSkillAI & models
A-share DCF valuation model / discounted cash flow. Triggers when the user says "DCF", "discounted cash flow", "DCF valuation", "intrinsic value", "intrinsic value", "help me calculate"
Ready to connect★ 242
- View details
a-share-deep-learning-alphaSkillAI & models
A-share deep learning alpha signals / neural network quant. Triggered when the user says "深度学习", "deep learning", "神经网络量化", "DL alpha", "CNN选股", or "深度因子". Uses cn-stock-data to fetch data and build deep learning alpha models. Supports both formal and brief output styles.
Ready to connect★ 242
- View details
a-share-ensemble-modelSkillAI & models
A-share ensemble model / multi-model fusion strategy. Triggered when the user says "集成模型" (ensemble model), "ensemble", "模型融合" (model fusion), "stacking", "blending", "多模型" (multi-model), or "模型组合" (model combination). Fetches data via cn-stock-data and builds multi-model ensemble strategies. Suppor
Ready to connect★ 242
- View details
a-share-explainable-aiSkillAI & models
Explainable AI / model attribution analysis for A-shares. Triggered when the user says "可解释AI", "XAI", "SHAP", "模型解释", "模型归因", "explainable", or "为什么模型这样预测". Fetches data via cn-stock-data and runs explainability analysis on quantitative models. Supports two output styles: formal and brief.
Ready to connect★ 242
- View details
a-share-graph-networkSkillAI & models
A-share graph neural network / relationship graph quantification. Triggered when the user says "图神经网络", "GNN", "graph network", "知识图谱", "关联图谱", "股票关系网络", or "供应链图谱". Uses cn-stock-data to fetch data and build stock relationship graphs and GNN models. Supports formal and brief output styles.
Ready to connect★ 242
- View details
a-share-lstm-forecastSkillAI & models
A-share LSTM time-series forecasting / sequence modeling. Triggered when the user says "LSTM", "时序预测", "序列模型", "RNN预测", "GRU", "循环神经网络", or "LSTM预测股价". Fetches data via cn-stock-data and builds an LSTM time-series forecasting model. Supports both formal and brief output styles.
Ready to connect★ 242
- View details
a-share-ml-stock-predictSkillAI & models
A-share ML stock price / return prediction. Triggered when the user says "ML预测", "机器学习预测", "股价预测", "收益率预测", "预测模型", or "ML选股". Fetches data via cn-stock-data and builds an ML prediction model. Supports both formal and brief output styles.
Ready to connect★ 242
- View details
a-share-model-riskSkillAI & models
A-share model risk / backtest overfitting analysis. Triggers when the user says "模型风险", "model risk", "过拟合", "overfitting", "回测失真", "样本外失效", or "模型验证". Uses cn-stock-data to fetch data and evaluate overfitting and model risk in quantitative models. Supports both formal and brief output styles.
Ready to connect★ 242
- View details
a-share-optimal-executionSkillAI & models
A-share optimal execution / Almgren-Chriss model. Triggered when the user says "最优执行", "optimal execution", "Almgren-Chriss", "执行优化", "最优拆单", or "execution frontier". Uses cn-stock-data to fetch data and solve for the optimal execution strategy. Supports formal/brief output styles.
Ready to connect★ 242
- View details
a-share-option-pricingSkillAI & models
A-share option pricing / BSM model analysis. Triggered when the user says "期权定价" (option pricing), "BSM", "Black-Scholes", "期权估值" (option valuation), "理论价格" (theoretical price), "定价模型" (pricing model), or "二叉树定价" (binomial pricing). Uses cn-stock-data to fetch data and perform option pricing and val
Ready to connect★ 242
- View details
a-share-price-impact-modelSkillAI & models
A-share price impact model / Kyle Lambda analysis. Triggers when the user says "价格冲击模型", "Kyle Lambda", "lambda", "冲击系数", "价格影响模型", or "订单流冲击". Fetches data via cn-stock-data and estimates price impact model parameters. Supports both formal and brief output styles.
Ready to connect★ 242
- View details
autoresearchSkillAI & models
Autonomous AI agent that modifies and iteratively improves a GPT language model training setup, running experiments within a 5-minute time budget to optimize validation bits-per-byte.
Ready to connect★ 242
- View details
bioreason_proSkillAI & models
Multimodal reasoning LLM for protein function prediction integrating protein embeddings with biological context to generate structured reasoning traces and functional annotations.
Ready to connect★ 242
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.