AI Skills Hub - Browse 180,000+ Agent Skills

Generate REST API endpoints for the OctoCAT Supply Chain application following established patterns. Use this skill when creating new CRUD endpoints, adding routes, implementing repository classes, or defining TypeScript models with Swagger documentation. Triggers on requests to add API features, create endpoints, implement data access layers, or extend the Express.js backend.

Expert guidelines for developing, auditing, and optimizing MultiversX Smart Contracts (Rust).

Create MySQL stored procedures with proper syntax, error handling, and security. Use when writing or reviewing stored procedures, functions, or triggers in MySQL.

Integrate and operate the EPOS DB-API Java library for metadata persistence and retrieval. Use when working with db-api entities, AbstractAPI/entity-specific APIs, linked-entity resolution, versioning/status behavior, or DB-API environment configuration and troubleshooting.

Configure and customize Walker on Linux, including `~/.config/walker/config.toml`, provider behavior, keybinds, prefixes, sets, actions, themes, and launch/service setup with Elephant. Use when users ask to install Walker, tune launcher behavior, fix config issues, migrate settings, customize theme/layout XML/CSS, or troubleshoot slow startup and provider integration.

Check if a specific dependency has known vulnerabilities. Provide a package name and optionally a version to get vulnerability information. - MANDATORY TRIGGERS: endor check, check dependency, check package, check vulnerability, is this package safe, endor-check

Comprehensive security scan with full reachability analysis to identify exploitable vulnerabilities. Builds call graphs to determine which vulnerabilities are actually reachable in your code. - MANDATORY TRIGGERS: endor scan full, full scan, deep scan, reachability scan, reachability analysis, comprehensive scan, endor-scan-full

Migrates existing Xcode projects to Tuist generated workspaces with build and run validation, external dependency mapping, and migration checklists. Use when adopting Tuist for an existing app or converting a hand-edited Xcode project to generated projects.

Index skill for VBot quadruped RL training. Routes to specialized skills for curriculum learning, hyperparameter optimization, reward/penalty engineering, and campaign management.

Creates Home Assistant add-ons from existing Docker images with ingress support. Use when user asks to "wrap a Docker app for HA", "create HA add-on from Docker image", "analyze Docker image for add-on", "make ingress add-on", or wants to convert existing containerized applications into Home Assistant add-ons with web UI integration.

Complete guide to creating STARR achievement stories with measurable results. Use when gathering work achievements, building accomplishment stories, or preparing for behavioral interviews. Helps extract metrics, structure narratives, and create evidence-based achievement files.

Complete workflow for analyzing job descriptions, mapping achievements to roles, and generating tailored CVs. Use when applying for jobs, preparing for interviews, or creating targeted resumes. Covers JD analysis, skills mapping with evidence-based matching, and CV generation.

Expert-level Make.com (formerly Integromat) automation development skill covering all built-in functions, syntax rules, and common patterns. Use this skill whenever the user needs help writing Make.com formulas, mapping expressions, scenario logic, data transformations, or debugging Make.com function errors. Triggers include: any mention of "Make.com", "Make scenario", "Make formula", "Make function", Make.com module fields, mapping panel expressions, or questions about formatDate, parseDate, if/switch, get, map, split, replace, or any other Make.com built-in function. Also use when the user is building or debugging Make.com automation workflows that require data transformation expressions.

Implement an approved spec using dynamic agent discovery and strict governance. Use only after a spec is READY.

Coordinate all assimilation phases to scan a repo and generate skills. Use when assimilating a repository, running the full pipeline, or automating skill extraction.

Review and process app submissions for the Pollinations showcase. Parse issues, validate submissions, create PRs, handle user corrections.

Deploy Tinybird pipes and datasources for enter.pollinations.ai observability. Validates and pushes changes to Tinybird Cloud.

This skill should be used when users ask to search for code patterns, find specific language constructs, or locate code with particular structural characteristics using Abstract Syntax Tree (AST) matching. It guides on writing ast-grep rules for structural code search and analysis to perform complex queries that go beyond simple text search.

Domain/DNS ops across Cloudflare, DNSimple, Namecheap for Peter. Use for onboarding zones to Cloudflare, flipping nameservers, setting redirects (Page Rules/Rulesets/Workers), updating redirect-worker mappings, and verifying DNS/HTTP. Source of truth: ~/Developer/manager.

Deep learning for single-cell analysis using scvi-tools. This skill should be used when users need (1) data integration and batch correction with scVI/scANVI, (2) ATAC-seq analysis with PeakVI, (3) CITE-seq multi-modal analysis with totalVI, (4) multiome RNA+ATAC analysis with MultiVI, (5) spatial transcriptomics deconvolution with DestVI, (6) label transfer and reference mapping with scANVI/scArches, (7) RNA velocity with veloVI, or (8) any deep learning-based single-cell method. Triggers include mentions of scVI, scANVI, totalVI, PeakVI, MultiVI, DestVI, veloVI, sysVI, scArches, variational autoencoder, VAE, batch correction, data integration, multi-modal, CITE-seq, multiome, reference mapping, latent space.

Use when working on Claude Code plugins (creating, modifying, testing, releasing, or maintaining) - provides streamlined workflows, patterns, and examples for the complete plugin lifecycle

Use when auditing a codebase for semantic duplication - functions that do the same thing but have different names or implementations. Especially useful for LLM-generated codebases where new functions are often created rather than reusing existing ones.

Swiss International Style for Resume Matcher. Invoke ONLY when designing new UI components or modifying existing component styles.

Run GitHub Copilot CLI for code generation, repository analysis, and development tasks. GitHub OAuth integrated. Use for quick coding tasks, context-aware completions, and repository-wide insights. Preferred for load balancing sub-agent work (30% weight).

Transform FHIR (Fast Healthcare Interoperability Resources) data into relational tables for analytics. Use when parsing FHIR bundles, extracting resources (Patient, Observation, Condition, MedicationRequest, etc.), flattening nested JSON, or loading healthcare data into Snowflake. Triggers include FHIR, HL7, healthcare interoperability, Patient resource, Observation, Condition, Bundle, ndjson, healthcare JSON.

Persistent vector memory for Claude Code. Store decisions, facts, preferences across sessions. Ingest documentation. Triggers: '/cmem', 'remember this', 'recall', 'what did we decide', 'ingest docs', 'store memory', 'project memory'. PROACTIVE: Before architectural decisions, recall relevant memories.

Register and manage AI agent identities on Celo using ERC-8004 (Trustless Agents). Use this skill when the user wants to register an AI agent on-chain, give or read reputation feedback, request validation, or interact with ERC-8004 identity/reputation/validation registries on Celo mainnet or Alfajores testnet.

Register and manage AI agent identities on Avalanche C-Chain using ERC-8004 (Trustless Agents). Use this skill when the user wants to register an AI agent on-chain, give or read reputation feedback, request validation, or interact with ERC-8004 identity/reputation/validation registries on Avalanche mainnet or Fuji testnet.

Advanced SQLModel patterns and comprehensive database migrations with Alembic. Use when creating SQLModel models, defining relationships (one-to-many, many-to-many, self-referential), setting up database migrations, optimizing queries, solving N+1 problems, implementing inheritance patterns, working with composite keys, creating indexes, performing data migrations, or troubleshooting Alembic issues. Triggers include "SQLModel", "Alembic migration", "database model", "relationship", "foreign key", "migration", "N+1 query", "query optimization", "database schema", or questions about ORM patterns.

After you create a git commit, annotate it using the `chronicle_annotate` MCP tool. This captures your intent, reasoning, and constraints as structured metadata stored alongside the commit.

Model Context Protocol (MCP) server setup and integration for Claude and AI agents. Use when user asks to "setup MCP", "configure MCP server", "add MCP tools", "connect to MCP", "create MCP server", or integrate external tools via MCP protocol.

GraphQL schema design, queries, mutations, and tooling. Use when user asks to "write a GraphQL schema", "create a query", "add a mutation", "set up Apollo", "GraphQL resolver", "type definitions", or any GraphQL tasks.

Utility to stitch project files into a single text file for analysis, search, or LLM context loading.

查看 Claude Code 的 token 用量统计。按日期×模型维度拆分，支持按天数、项目过滤。触发词："/cc-usage"、"看看用量"、"token 消耗"、"用量统计"

启动 mycc 小程序后端服务（后台运行）。触发词："/mycc"、"启动 mycc"、"启动小程序后端"、"检查 mycc 状态"

Manage and verify Composio integrations for external tools (Gmail, Google Sheets, Google Maps). Use this skill when the user asks to check connection status, troubleshooting integration errors, or verify if external tools are authorized.

Manage long-running work with a file-based task queue. Use when starting a high-level goal (research, building, investigation), logging progress during work, or marking objectives complete. Also used by heartbeat to detect and resume stalled tasks.

Extract all unique color codes (HEX) from an image and output as CSV with occurrence counts. Use when user wants to analyze colors in an image, extract color palette, count pixel colors, or export color data to CSV/spreadsheet format. Triggers on requests like "extract colors from image", "get color codes", "analyze image colors", "color palette extraction".

Deploy Vite apps (React, Vue, Svelte) to GitHub Pages with GitHub Actions. Handles custom domains, CNAME setup, base path config, and corporate/mixed registry issues. Use when deploying a Vite project to GitHub Pages, setting up a custom domain, or fixing GitHub Pages deployment issues.

根据产品描述和参考图智能推荐设计风格并生成Landing Page，根据产品自动解析配置，专为Coze平台设计，支持对话式持续修改、上下文配置管理、文件自动生成，交付可直接部署的完整网站包（HTML + 图片资源）。AI 深度理解 2025 三大核心设计趋势（物理质感回归、网格化与模块化、展示即交互），自动匹配最佳风格，生成高品质页面

Patterns for reliable external service integration: env validation, health checks, error handling, observability.

Analyzes pipeline coverage, tracks forecast accuracy with MAPE, and calculates GTM efficiency metrics for SaaS revenue optimization

Monitors customer health, predicts churn risk, and identifies expansion opportunities using weighted scoring models for SaaS customer success

Performs financial ratio analysis, DCF valuation, budget variance analysis, and rolling forecast construction for strategic decision-making

Analyzes campaign performance with multi-touch attribution, funnel conversion, and ROI calculation for marketing optimization

Browser automation CLI for AI agents. Use for visual testing after frontend changes.

Package entire code repositories into single AI-friendly files using Repomix. Capabilities include pack codebases with customizable include/exclude patterns, generate multiple output formats (XML, Markdown, plain text), preserve file structure and context, optimize for AI consumption with token counting, filter by file types and directories, add custom headers and summaries. Use when packaging codebases for AI analysis, creating repository snapshots for LLM context, analyzing third-party libraries, preparing for security audits, generating documentation context, or evaluating unfamiliar codebases.

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

Implement animations using the Motion library. Use when adding motion, transitions, gestures, scroll effects, or interactive animations to components. Triggered by implementation requests, not conceptual discussions.

Generate comprehensive markdown documentation for source code files using the OpenAI LLM API. Use this skill when the user asks to generate docs, document a file, create documentation, or write docs for source code.

Review CLI command files and generated documentation for quality, correctness, and adherence to project conventions. Use this skill when the user asks to review code, check quality, audit a command, or validate that best practices are followed.

Automatiza pruebas y diagnósticos del sistema SmartK et sin perder tiempo

Development skill for Rust GUI applications using GPUI framework (Zed's UI framework). Use when working on GPUI-based desktop applications - creating views, managing state, handling actions, writing idiomatic Rust code, structuring projects, or reviewing/refactoring existing code. Triggers on Rust GUI development, GPUI views, Entity/Context usage, terminal emulators, code editors, or any desktop app built with GPUI.

Install the DataSurface Python package from GitLab PyPI registry.

Configure Kubernetes to pull DataSurface images from GitLab registry.

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Search and retrieve CSS components, SVG icons, design patterns, and visual inspiration from the web. Use when the user asks to find, look up, or search for CSS snippets, SVG icons, UI components, loading spinners, animations, design inspiration, or any visual/frontend design resource. Triggers on requests like "find me a CSS button", "look up an SVG spinner", "search for a card component", "find a wave divider SVG", or "get design inspiration for a dashboard".

Search memories and decisions to answer questions about past learnings, choices, and context

Capture key learnings, patterns, gotchas, or context as persistent memories

Generate or edit images using the Gemini API (Nano Banana / Nano Banana Pro). Use when you need to select Gemini image models, craft text-to-image or image-to-image requests, set response modalities and imageConfig (aspect ratio/size), send inline or File API images, parse inlineData/base64 outputs, and save images to files via REST or SDKs.

Follow fast feedback loops for Go development workflow

Comprehensive ArcGIS Python API expertise for ArcGIS Online and Enterprise. Use when writing Python code for Feature Layers, Web Maps, geocoding, routing, spatial analysis, raster operations, portal administration, content management, or any arcgis package operations. Covers authentication patterns, Spatially Enabled DataFrames, geometry operations, batch editing, publishing workflows, and performance optimization.

Write Python code for ArcGIS Online Notebooks. Use when asked to query, update, or manage Feature Layers, manipulate Web Maps, export data, or perform any arcgis API operations in a hosted notebook environment. Covers authentication, pagination, Spatially Enabled DataFrames, edit_features batching, and content management.

Always wrap API calls in try/except and provide meaningful error messages:

Multi-pass strategic reasoning with expansion, compression, and critique cycles. Analyzes complex strategic questions through iterative exploration and structured synthesis. Use when facing ambiguous problems requiring deep analysis, thesis validation, or confidence-calibrated recommendations.

After you create a git commit, annotate it to capture your intent, reasoning, and constraints as structured metadata stored alongside the commit.

Interact with the EventHub MCP server at https://demo.manifest.build/servers/eventhub/mcp to take actions and retrieve information (e.g. booking tables). Use this skill whenever the user wants to perform an action or get information related to EventHub — such as booking a restaurant table, checking availability, or any EventHub-related request. This skill should be the PRIMARY method for taking actions; only fall back to browsing the human website if the MCP server does not expose the needed capability.

Gmail API integration with managed OAuth. Read, send, and manage emails, threads, labels, and drafts. Use this skill when users want to interact with Gmail.

An OpenClaw skill for local genetic data analysis.

Manage Google Docs, Google Sheets, and Google Drive with full document operations, spreadsheet editing, and file workflows. Includes Markdown support for headings, bold, italic, lists, tables, and checkboxes plus Drive upload/download/share/search and advanced Sheets operations.

Internal skill for syncing agent brain to Arweave. Invoked only via /markdown-provenance-brain command.

Gemini APIを使用して画像を生成します。テキストプロンプトからの画像生成が可能です。

Internal skill for uploading markdown to Arweave. Invoked only via /markdown-provenance command.

ブラウザゲームを自動プレイするスキル。agent-browserを使ってローカルまたはオンラインのHTML/JSゲームをプレイします。倉庫番、オセロ、五目並べなど。

Use when training prediction models, extracting metrics, configuring algorithms, or deploying models

Use when working with data collections, dataset metadata, tags, meanings, or AI-generated descriptions

Use when building datasets, running multi-step pipelines, managing dependencies, or orchestrating recipe execution order

User registration, login, and password hashing with bcrypt for local authentication flows.

Design normalized PostgreSQL schemas from tech specs, with proper constraints, naming conventions, and standard columns.

Translate natural-language requirements into structured, prioritized specifications with clear acceptance criteria.

Turn structured requirements into a system architecture with defined components, boundaries, API contracts, and data storage strategy.

Break a system architecture into implementable work packages with clear tasks, dependencies, and integration contracts.

Set up a Flask application using the app factory pattern with blueprints, extensions, and environment-specific configuration.

The environment-config skill standardizes how agents manage environment variables, secrets, and application configuration across local development and deployed environments.

Manage sequential and parallel execution across specialist agents, maximizing throughput while respecting task dependencies.

Decompose requirements into discrete tasks and delegate them to the most appropriate specialist agents based on their capabilities.

Quality gates and output validation — verify that agent deliverables meet acceptance criteria, maintain cross-agent consistency, and are ready for integration.

Execute this repository's RLM (Repo-Document Workflow) end-to-end with strict phase gates, artifact locking, addenda, traceability, and single-command auto-resume behavior. Use when a request mentions "Implement requirement run-id", asks to run a specific RLM phase, requires creating or updating files in .codex/rlm/run-id/, needs an ExecPlan-grade phase 3 plan under .agent/PLANS.md, or asks to continue a paused run after manual QA.

Verify the authenticity of literature references and detect hallucinations. Use when users need to check if a citation is real, verify a DOI, confirm a paper/article/book exists, cross-check author-title-journal-year metadata, detect fabricated references, validate URLs of online articles, or audit a reference list for accuracy. Covers journal papers, conference papers, preprints, books, monographs, newspaper articles, magazine articles, web articles, and any other published works.

Secure credential management for trading platforms

Only read if you need to display player specific world state

Only read if you're struggling with debugging weird string formatting

For serializing and deserializing data to/from JSON strings.

Read and write macOS Notes.app using Python. Create, read, update, and delete notes with Markdown support. Markdown is converted to/from Notes.app HTML format. Use when users ask to "write a memo", "take notes", "save to Notes", "add to reminder", "create a note", "メモする", "メモを書いて", "ノートに保存", "覚え書き", or want to save information to Notes.app.

Valida que un docker-compose.yml cumpla con todas las reglas obligatorias de Coolify (sin ports en web, sin network_mode host, credenciales en variables, versiones fijas, restart policies, healthchecks, expose definido, volúmenes persistentes, etc.)

--- name: my_writer description: Generates content (Blog, X, Mail) Strictly adhering to My persona and writing style. input: topic: (required) The topic or theme to write about. ---

Consult a member of your Board of Directors one-on-one. Use when asking "what would Naval think", "ask Socrates about", "consult with Ray Dalio", or similar requests to get advice from a specific board member.

Maps and documents codebases of any size by orchestrating parallel subagents. Creates docs/CODEBASE_MAP.md with architecture, file purposes, dependencies, and navigation guides. Updates CLAUDE.md with a summary. Use when user says "map this codebase", "cartographer", "/cartographer", "create codebase map", "document the architecture", "understand this codebase", or when onboarding to a new project. Automatically detects if map exists and updates only changed sections.

Transform Markdown/HTML into premium web pages and publish to a global URL.

Create new Agent Skills for GitHub Copilot from prompts or by duplicating this template. Use when asked to "create a skill", "make a new skill", "scaffold a skill", or when building specialized AI capabilities with bundled resources. Generates SKILL.md files with proper frontmatter, directory structure, and optional scripts/references/assets folders.