AI Skills Hub - Browse 180,000+ Agent Skills

Write clean, modular, production-ready bash scripts with proper error handling and maintainable structure. Use when creating new shell scripts, refactoring existing bash code, or when user asks for bash/shell scripting help with terms like "write a script", "bash script", "shell script", or "automate with bash".

This skill should be used when users want to migrate from .env files to fnox with 1Password (or another secret provider). It covers installing fnox, creating 1Password items, configuring fnox.toml, and integrating with mise. Use when users mention ".env migration", "fnox setup", "1password secrets", or want to improve their secret management workflow.

Generates and edits images using Google Gemini and OpenAI GPT Image APIs via shell scripts. This skill should be used when the user asks to "generate an image", "create an image", "edit an image", "modify an image", "make a picture", "draw me a", "text to image", "generate with gemini", "generate with openai", "gpt image", or "gemini image".

<instructions>

Creates, edits, and analyzes Word documents with tracked changes, comments, and formatting preservation. Use when working with .docx files for document creation, modification, redlining, or text extraction.

Helps users discover and install agent skills. Use when users ask 'how do I do X', 'find a skill for X', 'is there a skill that can...', 'ccpm', 'claude code skill', 'installed skills', or express interest in extending capabilities.

Creates, edits, and analyzes spreadsheets with formulas, formatting, and data visualization. Use when working with .xlsx, .xlsm, .csv, or .tsv files for creating spreadsheets, reading/analyzing data, modifying files while preserving formulas, or recalculating formula values.

Guides README creation and improvement with audience-matched templates. Use when writing READMEs for open source, personal, internal, or config projects, or when the user mentions documentation, README, or project setup.

Creates, edits, and analyzes PowerPoint presentations with layouts, speaker notes, and design elements. Use when working with .pptx files, creating presentations from topics, modifying slides, or extracting content. Triggers: 'create presentation from topic', 'slide deck from document', 'powerpoint from scratch'.

Repair stale Codex workspace and thread path bindings after a project folder rename by updating local Codex state files and verifying the new path is fully bound.

Write stable, high-signal CLI UX regression tests (stdout/stderr/exit codes) without brittle snapshots.

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

Texas 42 dominoes game development - activates for architecture questions, layer system implementation, testing patterns, URL debugging workflow, game rule clarifications, and codebase navigation. Use when working on game logic, special contracts (nello/splash/plunge/sevens), or debugging game states.

Use when the user asks to add MCP servers, configure .mcp.json, add external tools (browser, docs, github), or wants a plugin-based skill pack system (frontend/cyber/etc). Provides safe, portable MCP setup patterns for Claude Code.

Set up Databricks agent development environment. Use when: (1) First time setup, (2) Configuring Databricks authentication, (3) User says 'quickstart', 'set up', 'authenticate', or 'configure databricks', (4) No .env file exists.

Run and test the agent locally. Use when: (1) User says 'run locally', 'start server', 'test agent', or 'localhost', (2) Need curl commands to test API, (3) Troubleshooting local development issues, (4) Configuring server options like port or hot-reload.

Multi-agent orchestration coordinating Claude Code, Codex, and Gemini CLIs. Use for code review, security audits, architecture decisions, or any task needing multiple AI perspectives.

This skill should be used when the user asks to "debug the electron app", "connect playwright to VoiceTree", "take screenshots of the running app", "interact with the live UI", "inspect the running application", or "test UI elements live". Provides step-by-step instructions for connecting Playwright MCP to a running Electron app for live debugging and automation.

Run and extend AXIOM automated tests for launcher, recipes, UI mod, and plugin testbot. Use when validating changes, adding new tests, or checking recipe balance and UI behavior.

Build and package AXIOM components (plugin, UI mod, launcher, portable client). Use when asked to compile, assemble releases, or produce build artifacts using build.sh, assemble_release.sh, or module-specific Gradle/Maven builds.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Run the benchmark evaluation for one or all framework implementations against a scenario. Use this skill when the user wants to execute benchmarks, run evaluations, or test a framework implementation. Handles execution and result collection.

Clerk authentication integration for Convex. Use when setting up Clerk auth, configuring ConvexProviderWithClerk, implementing Clerk webhooks for user sync, or troubleshooting Clerk-specific auth issues.

Create, update, review, fix, or debug VS Code agent customization files (.instructions.md, .prompt.md, .agent.md, SKILL.md, copilot-instructions.md, AGENTS.md). Use for: saving coding preferences; troubleshooting why instructions/skills/agents are ignored or not invoked; configuring applyTo patterns; defining tool restrictions; creating custom agent modes or specialized workflows; packaging domain knowledge; fixing YAML frontmatter syntax.

Use when setting up parallel development environments or when multiple team members need isolated workspaces. Creates separate working directories from the same repository.

Auto-report fail2ban banned IPs to AbuseIPDB and notify via Telegram. Use when monitoring server security, reporting attackers, or checking banned IPs. Watches fail2ban for new bans, reports them to AbuseIPDB, and sends alerts.

Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.

Backup Clawdbot workspace and config to GitHub with git-crypt encryption. Use for daily automated backups or manual backup/restore operations.

Create professional slide decks from outlines or topics. Use the PPTX skill to turn outlines into slides with high-impact design.

Investigate e2e test failures, diagnose root causes, and generate actionable tasks for /create-task.

Audit recent code changes for coding convention violations. Use after implementing changes to verify they follow project standards.

Test Python module imports to verify correct installation and structure

部署 frp (fatedier/frp) 实现内网穿透，将本地服务暴露到公网。当用户需要配置 frp 反向代理、配置 frpc/frps、通过公网服务器暴露本地 HTTP/TCP 服务、或进行 NAT 穿透/内网穿透时使用此技能。覆盖 Windows 客户端和 Linux 服务端部署。

Provides instructions of how to review a github pull-request (using the GitHub CLI).

Convert Markdown content to Notion blocks using the Martian library.

Supervise Claude Code sessions running in tmux. Uses Claude Code hooks with bash pre-filtering (Option D) and fast LLM triage to detect errors, stuck agents, and task completion. Harness-agnostic — works with OpenClaw, webhooks, ntfy, or any notification backend. Use when: (1) launching long-running Claude Code tasks that need monitoring, (2) setting up automatic nudging for API errors or premature stops, (3) getting progress reports from background coding agents, (4) continuing work after session/context limits reset. Requires: tmux, claude CLI.

Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.

Project-specific Effect service patterns for src/lib/server/services and remote functions. Use for new services, service refactors, or Effect error handling.

Orchestrate all internal and external communications triggered by the Proactive Detection Engine. One signal in, correct messages out to the right people through the right channels.

Create/audit/disable OpenClaw cron jobs safely with guardrails. Use for heartbeat-driven automation.

ORION/SCRIBE checklist for drafting safe, readable, low-spam-risk plain-text emails (AgentMail sender).

Run Datadog Terraform provider acceptance tests with proper RECORD modes and capture output for analysis. This agent is invoked via Task tool and writes results to files.

Invoke this skill when: - `npm run build` or `next build` fails - `pip install` or Python dependency issues occur - TypeScript compilation errors appear - User mentions "build failing" or "deployment error"

Invoke this skill when: - Setting up authentication in FastAPI backend - User mentions "JWT", "token verification", or "auth middleware" - Phase II requires protected API endpoints

Reliable workflow for using the local TalkToFigma MCP server (Cursor ↔ Figma plugin via WebSocket relay).

Create and manage Linear issues from documents, notes, or conversations. Use when asked to create tickets, file issues, or work with Linear.

Create meeting report entries in the Notion meeting reports database. Use when the user asks to create a meeting report, log a meeting, or add a meeting to Notion. Requires Notion MCP.

Conduct deep research using OpenAI's deep research models via API. Use when the user asks for comprehensive analysis, company research, person research, or product research requiring web-sourced citations.

Generates Next.js App Router projects with server components, server actions, and data fetching patterns. This skill should be used when users want to create Next.js projects, set up routing, implement server actions, configure data fetching, or integrate with FastAPI backends. Works with nextjs-ui-pro for components, fullstack-auth for authentication, and neon-db-pro for database integration. ENHANCED: Automatically prevents route group conflicts with root page.tsx and ensures 'use client' directives on interactive components to avoid common App Router pitfalls.

Implements JWT authentication for full-stack apps with Next.js 14+ frontend and FastAPI backend. Uses bcrypt for password hashing, PyJWT for token signing, and localStorage for client token storage. This skill should be used when users need email/password authentication with protected API routes.

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

Automated photogrammetry-to-print pipeline. Trigger with "process my scan" or "scan and print". Fetches images from OpenScan Mini, uploads to OpenScanCloud for photogrammetry, decimates mesh in Blender headless, slices with OrcaSlicer, and prints on Bambu X1-Carbon via LAN. Sends Telegram status at each stage.

NCAA college basketball analytics and March Madness prediction tools. Use when analyzing college basketball games, finding betting edges, building bracket predictions, or accessing NCAAB data. Includes tools for CBBpy (ESPN data), Barttorvik T-Rank, DRatings predictions, NCAA NET rankings, Massey composite ratings, Warren Nolan metrics, Kaggle tournament data, Haslametrics, StatMuse (natural language queries), Sports-Reference.com, SportsData.io API, FantasyPros projections, and multi-source odds comparison. All data sources are FREE.

Security standards for the skill agent codebase. Covers secrets management, input validation, path traversal prevention, OWASP adapted for Python/Pydantic AI.

Manage Supabase for this project — auth, database connection, SQL migrations, environment setup, and the Supabase dashboard. Use when the user mentions Supabase, auth, login, sessions, cookies, RLS, or running SQL in the Supabase dashboard.

Manage GitHub operations for this project using the gh CLI and git. Use when the user asks to commit, push, create repos, open PRs, change repo settings, or perform any GitHub-related task.

JavaScript/TypeScript integration with Noir circuits. Covers compilation, witness generation, proving, and verification using noir_js and bb.js.

Test Noir circuits using nargo test. Covers test attributes, assertions, and organization patterns.

Manage liquid nitrogen tank inventory YAML. Use when adding frozen entries, recording thaw/取出, querying by cell line/plasmid/box/position, listing empty slots, viewing statistics, recommending positions, or validating ln2_inventory.yaml.

Search past findings and observations from Code Sentinel memory

Automated multi-agent orchestrator that spawns CLI subagents in parallel, coordinates via MCP Memory, and monitors progress

Built on UniTask for non-blocking async operations with automatic object pooling.

Analyze test coverage by running scripts/test-coverage.sh and writing reports/logs under .codex/.

Identify and safely remove dead code by running scripts/refactor-clean.sh, logging artifacts under .codex/, and verifying before/after changes.

Cheminformatics toolkit for fine-grained molecular control. SMILES/SDF parsing, descriptors (MW, LogP, TPSA), fingerprints, substructure search, 2D/3D generation, similarity, reactions. For standard workflows with simpler interface, use datamol (wrapper around RDKit). Use rdkit for advanced control, custom sanitization, specialized algorithms.

Query FRED (Federal Reserve Economic Data) API for 800,000+ economic time series from 100+ sources. Access GDP, unemployment, inflation, interest rates, exchange rates, housing, and regional data. Use for macroeconomic analysis, financial research, policy studies, economic forecasting, and academic research requiring U.S. and international economic indicators.

Guides proposing, negotiating, and publishing API contract changes. Use when modifying contracts/, adding endpoints, or changing schemas.

Pull latest changes from skills repository git remote.

Offline OpenClaw documentation with vector search and RAG capabilities

Build MCP (Model Context Protocol) servers from hello world to production systems. This skill should be used when users want to create MCP servers that expose tools, resources, or prompts to AI applications like Claude. Covers TypeScript and Python implementations, stdio and HTTP transports, OAuth 2.1 security, and production patterns.

Serialize PostGIS geometry rows into a GeoJSON FeatureCollection for map display (4326, Feature + properties).

Create buffer geometries with ST_Buffer, with correct units and safe patterns for geometry vs geography.

Spatial joins and point-in-polygon with ST_Intersects, including index-friendly bbox prefilter patterns.

Reproject PostGIS geometry using ST_Transform with correct SRID handling and safe usage patterns.

No description available

No description available

No description available

Check the status of video indexing tasks. Use when user asks about indexing progress, says "is my video ready?", "how long until indexing is done?", or wants to know if they can search/analyze yet.

Search indexed videos using natural language. Use when the user wants to find specific content, moments, or scenes in their indexed videos. Triggers on phrases like "find the part where...", "search for...", "look for...", "where does...", "when does...".

Submits and manages FastFold protein folding jobs via the Jobs API. Covers authentication, creating jobs, polling for completion, and fetching CIF/PDB URLs, metrics, and viewer links. Use when folding protein sequences with FastFold, calling the FastFold API, or scripting fold-and-wait workflows.

Build terminal user interfaces (TUIs) in Rust with Ratatui (v0.30). Use this skill whenever working with the ratatui crate for creating interactive terminal applications, including: (1) Setting up a new Ratatui project, (2) Creating or modifying terminal UI layouts, (3) Implementing widgets (lists, tables, charts, text, gauges, etc.), (4) Handling keyboard/mouse input and events, (5) Structuring TUI application architecture (TEA, component-based, or monolithic patterns), (6) Writing custom widgets, (7) Managing application state in a TUI context, (8) Terminal setup/teardown and panic handling, (9) Testing TUI rendering with TestBackend. Also triggers for questions about crossterm event handling in a Ratatui context, tui-input, tui-textarea, or any ratatui-* ecosystem crate.

Detect exposed secrets, API keys, credentials, and tokens in code. Use before commits, on file saves, or when security is mentioned. Prevents accidental secret exposure. Triggers on file changes, git commits, security checks, .env file modifications.

Ask users questions via the UI. Use when you need clarification, user preferences, or confirmation before proceeding. The user CANNOT see CLI output - this tool is the ONLY way to communicate with them.

Test and debug web UIs using Chrome DevTools MCP. Use when verifying form submissions, debugging API calls from the browser, testing navigation flows, or inspecting page state. Triggers on "test the UI", "check if the form works", "debug the API call", "verify the page", "browser testing", or when Chrome DevTools MCP tools are available and UI verification is needed.

Manage tmux-watch subscriptions and interpret stable-output alerts.

获取微信公众号文章链接，提取正文内容并生成保留图片和排版的 PDF，通过 tmc/nlm CLI 上传到 NotebookLM。适用于“公众号文章转 PDF”“保存微信公众号到 NLM/NotebookLM”“把公众号文章放进 NotebookLM”“选择 notebook 并上传”等场景。

将网页 URL 转为 PDF，使用 headless 浏览器并支持自动滚动以加载懒加载资源。适用于“保存网页为 PDF / 保留排版和图片 / 从指定选择器生成正文 PDF”等需求。

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.

Generate exhaustive test scripts for Amazon Connect IVR flows and Lex bots covering all call paths, error conditions, and edge cases. Trigger on test scripts, test scenarios, IVR testing, or call flow testing.

Check the health of all agent servers

Comprehensive OpenTUI skill for building terminal user interfaces. Covers the core imperative API, React reconciler, and Solid reconciler. Use for any TUI development task including components, layout, keyboard handling, animations, and testing.

Smart background process detection for run_shell_command - prevents long-running services from blocking the conversation.

Use when creating, updating, or reviewing PMBOK artifacts in `senior-pmbok-pm/reference/PM_DOCS_PT_BR` (Portuguese) or `senior-pmbok-pm/reference/PM_DOC_EN` (English), ensuring each document follows the provided templates, inputs, and documentation guidance.

Claiming work is complete without verification is dishonesty, not efficiency.

Helps author concise, discoverable skills using TDD-style testing. Use when creating, editing, or verifying skills before deployment.

Use Composio Tool Router to access 800+ external tools (Gmail, Slack, GitHub, etc.) with managed authentication and a remote code interpreter.

Defines the format, structure, and quality standards for SPEC.md documents. Used by the spec-writer agent in Phase 1 to transform RESEARCH.md into a precise, testable specification with requirements, interfaces, behavior scenarios, and traceability.

Defines the format, structure, and quality standards for fix plans and FIX_REPORT.md documents. Used by the fixer agent in Phase 7a to diagnose validation failures, propose targeted fixes, and document what was changed and why.

Defines the format, structure, numbering, and quality standards for Architecture Decision Records (ADRs). Used by the architect agent in Phase 3 to document non-obvious design decisions with full rationale, alternatives, and tradeoffs.

Defines the Git branching strategy, commit conventions, and merge procedures for the workflow. Used by architect, developer, QA engineer, and fixer agents to maintain consistent Git history with requirement traceability.