claude-skills
Gives developers ready-made guidance for building web apps and APIs, covering animated React components, authentication with JWT and OAuth, API design and contract testing, and changelog writing. Works inside Claude Code.
4,248 plugins. 79,851 skills, agents, commands and MCP servers. 99 get Auto-invokedWhat is this?This plugin ships a FLOW.md router the engine fires, so the matching skill runs itself. No slash command to remember.Learn how →.
Gives developers ready-made guidance for building web apps and APIs, covering animated React components, authentication with JWT and OAuth, API design and contract testing, and changelog writing. Works inside Claude Code.
Runs a smell-first audit on a user-chosen path set: measures structure metrics, applies a named size profile, and reports code…
Entrevista o usuário em até 7 perguntas, escreve o BRIEF.md do vídeo e valida antes de qualquer busca.
A collection of AI agent skills and prompts for OpenClaw (formerly Clawdbot), Claude Code, Codex, and other LLM-based coding assistants. Contributions Welcome! Have a skill that makes your AI agent smarter? We'd love to include it.
考公与事业单位备考导师。用于国考、省考、选调生、事业编的行测、申论、职测(职业能力倾向测验)、综应(综合应用能力)、公基(公共基础知识)、公文知识、结构化面试、时政、报考咨询、学习计划与错题复盘。支持出题、讲题、批改、分类训练。Use for Chinese…
Analyzes .NET project context, requirements, and constraints to recommend architecture approaches, framework choices, and design…
Generate supply schedules for CCA contracts using normalized convex curve
Spawns AI coding agents in isolated git worktrees so Claude Code users can delegate tasks to separate agents or parallelize feature development. Each agent works in its own worktree.
Fetches AI news from smol.ai RSS and generates structured markdown with intelligent summarization and categorization. Optionally…
Sonnet 기반 Fable 5 구조 이식 서브에이전트 — 위임 전용(현재 세션에 직접 적용하는 모드는 itsvff 스킬 사용). 구현·분석·리서치·작문 등 독립 작업을 별도 컨텍스트에서 Sonnet 단가로 처리할 때 위임한다.…
Quick WordPress performance scan - fast triage using critical pattern detection
Searches the documentation for an open source headless commerce and storefront framework.
A self-hosted LLM proxy that routes OpenAI- or Anthropic-style requests from Claude Code to any provider, with skills for installing, configuring, evaluating routes, and running Harbor benchmarks.
Chinese Word document formatting toolkit for .docx/.doc/.wps workflows. Use when Codex needs to diagnose document formatting, fix…
Audits bibliography entries for completeness, consistency, and hygiene — checks .bib files, compiled PDF for unresolved…
The agent's job is to **find the listing from minimal input** — not to interrogate the user. Default behavior: take whatever the…
Source version: 1.8.1. See release notes and Production-oriented ROS 2 engineering guidance for coding agents, with focused references, static validators, regression tests, and multi-distribution CI.
Creates and configures API Platform resources with operations, DTOs, state providers, processors, and security. Handles full…
Langcli is a terminal-based interactive AI coding assistant that is compatible with Claude Code. It includes a verify skill for code verification.
Isolates expensive Swift code search operations to preserve main context. Delegates all exploratory 'where is X', 'find Y',…
Skills for ServiceNow admins that audit CMDB health, triage incidents with suggested resolutions and assignments, and deploy artifacts across instances using update sets and dry-run previews.
After feature work, update the affected documentation to reflect code changes.
Keep a Changelog records what changed. Keep the Why preserves why it changed. Keep the Why is the why layer of repo-native project memory: your repository already holds what the project is, how it works and what changed; this is the agent skill, and the file.
Use when the user needs academic citations, BibTeX, venue/author quality checks, or help filling [CITE] placeholders. Triggers…
Review a phase's worktree against the spec before merging into main.
Develop, debug, and manage Temporal applications across Python, TypeScript, Go, Java, .NET, PHP, Ruby, and Rust. Use when the…
Reads generated documentation for a public repository so the agent can learn a codebase quickly.
TikZ for paper diagrams, without hand-writing TikZ, copyable icons, editable templates, and a Claude Code skill.
Route work into the right maestro tier and drive the SPEC/NOTES/VERIFY bundle lifecycle - open, resume, close, recall.
You are the **Construction Agent** for AI-DLC (AI-Driven Development Life Cycle).
An agent skill that applies Edward Tufte's data visualization principles when generating charts, plots, and graphs.
Generates multi-format documentation (Word, PDF, PPTX, Markdown blog post, JIRA ticket, FAQ, changelog, LaTeX, social snippet,…
Builds inbound contact centers with IVR, agent routing, call recording, voicemail, and metrics using Telnyx Call Control API.…
Generates flowcharts, sequence diagrams and other diagrams from plain text syntax.
Walks the user through Charlie Hills's AI Second Brain + Karpathy Wiki setup from the MarTech AI newsletter. Use whenever the…
Use when a bundle-plugin needs systematic quality audit and security scan against the 10-category checklist. Dispatched by…
Full health sweep chaining token, naming, component, drift, docs-coverage and system-health audits into one report with…
Lets a security engineer run web app and API security tests from the coding agent instead of switching to separate tools, covering runtime vulnerability scanning, fuzzing and API spec validation.
A decision board for evidence-based calls — the human adjudicates, the agent runs the errands. Three layers (sources → ideas →…
General-purpose execution for bounded investigation, editing, and validation; use when work spans capabilities; prefer focused…
Workout Gate - on/off, challenge, stats, presets, settings
A plugin that adds skills for running Claude Code reviews of local git changes, delegating tasks to Claude Code, and tracking, cancelling, or retrieving background jobs in a repository.
NERV Operations Console v2 — Evangelion-inspired UI component library. Data-driven Three.js MAGI visualization (yield surface…
Free, open-source memory for Claude Code. Your own database, no cloud, no subscription.
Generate a structured bug report for GitHub issues based on conversation context about bugs, errors, or broken functionality
Use for architecture decisions, boundaries, and technical tradeoffs before implementation.
Tier-A lean commit — only your paths, no changelog.d/push in same turn
You execute and monitor code-based experiments. Your job is to run user-specified commands, watch for problems in real-time, and…
Decompose complex tasks into detailed, actionable todos. Each todo has a rich description that is executable from the description…
Talk to your ComfyUI workflows. Comfy Pilot gives Claude Code direct access to see, edit, and run your workflows, with an embedded terminal right inside ComfyUI.
Use when creating, validating, backtesting, deploying, sizing, or troubleshooting Aerodrome/Base spot trading strategies through…
Reasons about low-privilege-to-Domain-Admin paths in an authorized Active Directory assessment. Takes the enumerator's inventory…
Connect CodeRabbit MCP for remote tools and set up the standalone CLI for local reviews. The connector and CLI use separate…
Personal skill collection for Claude Code, Gemini CLI, and OpenAI Codex, by @LichAmnesia. Telegraph-style, opinionated, no filler. Engineering judgment skills plus high-leverage utility tools. 中文版:README-zh.md.
Determine the best Anthropic architecture for your project by analyzing requirements and recommending the optimal combination of…
Assesses AI agent configurations, MCP servers, and LLM-integrated applications for security risks. Use when auditing AI agents,…
A file-based kanban board that Claude Code agents and human supervisors can use to track and coordinate project tasks. It runs locally as a single binary with no database, server, or account needed.
Design claim-driven test plans for distributed or stateful systems with persistence, replication, consensus, retries,…
Diagnoses a red CI run, traces it to the responsible task, hands a concrete fix task to the SWE, and re-verifies green. Owns…
Python SDK for healthcare AI, typed, validated FHIR tools for agents, real-time EHR connectivity, production deployment.
Academic literature discovery as a Skill. Built natively for Claude Code; runs in Codex and any agent that loads the SKILL.md format.
Design Apple-style iOS/macOS interfaces following Human Interface Guidelines. Creates HIG-compliant components with SF Symbols,…
Generates dense, exam-ready LaTeX cheatsheets from course materials such as PDF, PPTX, Markdown, and image files. Students and educators can use it to condense lecture notes and slides into a printable reference sheet.
Decomposes a research question into a structured investigation plan with sub-questions, search angles, and output format…
Use when Claude Code needs a second opinion, verification, or deeper research on technical matters. This includes researching how…
A Claude Code skill for memory-lancedb-pro, a long-term memory plugin for OpenClaw AI agents. It covers installing, configuring, and using the plugin's features.
Guide for working with Splitrail's MCP server. Use when adding tools, resources, or modifying the MCP interface.
A deterministic thinking partner that challenges assumptions and applies 150+ mental models to sharpen decisions, solve problems, and think more clearly. Built on the open Agent Skills standard.
Transform saved links, papers, articles, posts, videos, and reference collections into approachable AI teaching artifacts for…
Claude skills for Computational Designers.
The official Alpha Vantage API MCP server enables LLMs and agentic workflows to seamlessly interact with real-time and historical stock market data through the Model Context Protocol (MCP).
Delegate bounded investigation, review, or implementation tasks to Antigravity CLI from a supervising agent. Includes a…
Template video giáo dục ngắn (TikTok/Reels/Shorts) dựng trên HyperFrames, mỗi video so sánh một cặp khái niệm hay bị nhầm lẫn, theo đúng một layout/nhịp cố định, chỉ đổi nội dung.
Operate CodeKanban workflows, terminal sessions, and web sessions through the installable `codekanban-cli` command. Use when the…
xxg-portrait-rebuild-light is an image-edit skill for existing portrait photos. It reconstructs the key light, fill, shadows, and background atmosphere with a director-led lighting workflow while restoring clean, healthy, low-contrast photographic skin microtexture.
Break down full ARR (ACL Rolling Review) reviewer responses into structured rebuttal units. Use when input contains ARR reviewer…
Elves is a skill for handing planned development or research work to a separate worker for unattended runs, without tying the run to one model provider. It includes a kernel for long unattended Grok Bot jobs.
A Claude Code skill for working with .pptx files, covering reading and extracting presentation content, editing text, images and styles, and generating or verifying decks. It uses a single deck.py command line tool that applies JSON patches and lints the results.
Fix a broken OpenAPI spec in jentic-public-apis with an OpenAPI Overlay, validate it (spectral lint + idempotency check), and…
Skills for building smart contracts with OpenZeppelin Contracts libraries across Solidity, Cairo on Starknet, Stellar/Soroban and Sui Move. They help set up projects, integrate token and access components, and review integrations before shipping.
Generate Xiaohongshu (XHS / RedNote) cover images using GPT Image 2 / Codex image generation first, with the legacy Gemini CLI as…
Gives your AI coding agent a routine for keeping a repo healthy: scanning for dependency and security risks, clearing lint and type debt, fixing flaky tests, and syncing docs with the code, so you stop doing that upkeep by hand.
Builds, edits or analyzes Agent Skills through conversational discovery. Use when the user requests to "Create an Agent",…
Use when the user needs to work with single-cell RNA-seq data using CellWhisperer: processing datasets for the interactive web…
Source of truth for Firecrawl workflow skills, outcome-focused skills for AI coding agents: research reports, SEO audits, QA reports, knowledge bases, lead lists, and agent-ready website design systems.
Decomposes vague, high-level project requirements into well-scoped planning units for /deep-plan. Use when starting a new project…