Agent Skills Registry
Browse agent skills published on npm with the agent-skill keyword.
JS API for Yahoo Finance
Extract design tokens (colors, typography, spacing, border radius, shadows) from any public website. Generates JSON and CSS custom properties for local projects. Available as an AI agent skill (Claude, Cursor, Codex) and standalone CLI.
Zero-setup durable creative-media CLI for agents (image + video + audio + 3D): guide-first creation, model and cost inspection, owned URLs, JSON recovery, payments, reusable assets, and feedback.
18 Google Maps tools for AI agents — geocode, search, directions, weather, air quality, local rank tracking, map images via MCP server or standalone CLI
Brand-driven short-form marketing content kit: seven agent skills (start-here router + brand builder, design guide, carousel generator, storyboard prompt, video prompt, shorts editor) sharing one brand profile + assets. Installable from skills.sh (any SKI
AI context and rules sync CLI for Claude.md, Claude Code, Cursor, and Copilot instructions, with privacy-safe context receipts that prove what memory, tools, skills, compactions, and security findings crossed agent boundaries without logging raw content.
Agent skill that routes image generation, image editing, image prompts, prompt examples, templates, and PPT visuals through Yali AI GPT-Image2.
观远 BI 命令行工具 - 通过 API 操作 ETL、数据集、页面、表单等资源，并提供 ChatBI 问数/洞察能力
Customizable react components.
CLI and agent skills for managing GitHub PR review comments. List, filter, reply, and watch for bot findings.
Opinionated skills, hooks, and workflows for AI agents
Install the Parley Deck vendor-neutral AI cooperation skill into local AI agent runtimes or a custom skill directory.
🔍 Blast radius & caller analysis for legacy Java. Heuristic-ranked impact audit — npm-installable agent skill for OpenCode, Codex, Claude Code, Copilot, Gemini & DeepCode.
cue — Agent Profile Manager for Claude Code & Codex. Pick a profile, launch with the right skills, MCPs, and plugins.
Handcrafted Agent Skills for browser-authenticated Jira and Confluence ingestion, LLM wiki workflows, and developer automation.
VeyraSkills — A curated collection of Claude Code skills for founders, developers and AI builders
Install the api2img skill for relay-API-based image generation and editing across Codex and other agents.
Agent Skill for building and debugging games with public 1Game packages
Generate agent skills from llms.txt sources
Your agent writes ugly UI. This catches it. A static-analysis CLI for React UX/UI that scores your codebase 0-100 and installs as an agent skill for Claude Code, Codex, Cursor, and Copilot. Tuned for Rails+Inertia and TanStack stacks.
Fhiron MCP connector — validación FHIR contra CL Core v1.9.4 con skill `fhiron-cl` embebida (operating contract + 17 recursos descubribles). 10 tools fhiron_*, prompts pre-armados, bilingüe es/en, wizard `init` 1-clic. Compatible con Claude Code, Cursor,
Premium 9:16 Reel OS for Remotion. 5 cinematic style families, 22 production-tested presets, audio-locked motion, IG-safe by default. v1.1+ bakes in leonxlnx/taste-skill design discipline + huashu-design productivity patterns.
Agent-first local Open Graph Creator studio and CLI.
Code intelligence toolkit for AI agents — extract functions, trace call chains, find callers, detect dead code without reading entire files. Works as MCP server, CLI, or agent skill. Supports JS/TS, Python, Go, Rust, Java.
Agent skill that generates beautiful HTML pages for diagrams, diff reviews, plan reviews, slide decks, and data tables
X (Twitter) data platform skill for AI coding agents. 100+ REST API endpoints, 2 MCP tools, 23 extraction types, HMAC webhooks.
Standalone AI agent skill for brainstorming without specs, plans, commits, scaffolding, or implementation.
MCP server for n8n with tools for generating workflows, linting, diagnosing failed executions, and driving live n8n instances. Built for AI agents.
An agent skill that deeply parses resumes, extracts structured data, and provides actionable insights to improve ATS compatibility and readability.
Multi-skill bundle for AI coding agents: surf-search-skill (multi-provider web search via Tavily + Parallel + Brave) + surf-plan-skill (research-driven execution planning). Includes `surf` interactive setup with live key validation, automatic provider fal
观远 BI Card/Page 生成工具 - 通过 JS DSL 创建图表和仪表板
Agents should invoke this skill before modifying unfamiliar codebases, answering where/how something is implemented, tracing dependencies, mapping repo structure, or planning changes. Explores a repository and returns a strict JSON handoff with key files,
TypeScript SDK for the mail.com mobile API.
A premium, highly customizable Vue & Nuxt component library.
TypeScript SDK for Lightning settlement, preimage proof, and execution unlocks for AI agents.
Agent skill for choosing GPT-Image2 visual styles, prompt templates, categories, and scene tags.
Agent skill wrapper for the ingraft repository-context CLI.
OpenCode plugin + MCP server + skill that runs an automated GitHub Copilot PR review loop: request review, wait deterministically via `gh run watch`, triage every comment, push fixes, reply, resolve, gated merge. Solves the silent-fail of github_request_c
AI skill for frontend design: 50+ UI styles, 177 palettes, 90+ UX rules. Works with Claude Code, Cursor, Windsurf, Copilot, Codex.
Agent Skill and npm installer for GPT Image API proxy generation using GPT_IMAGE_BASE_URL and GPT_IMAGE_API_KEY.
Switch and manage multiple Git user.name/user.email identities from the command line
Makes Claude Code reason harder, recall past corrections, and learn from every session so its competence compounds run over run. The Mulahazah engine turns each fix into a reusable instinct, so a lesson learned once is applied automatically next time — no
Agents should invoke this skill for high-stakes or complex research needing multi-source evidence, scientific/technical fact-checking, decision traces, or rigorous verification. Runs deterministic two-phase research with schema/policy validation.
Venture Intelligence pack for Claude Code - idea validation, competitor research, and Bull/Bear/Judge verdict
Tool-agnostic Agent Skill for Guandata BI (观远 BI). Data analysis + ETL governance/write + custom chart development + HTML application-style dashboard generation. Compatible with Claude Code, OpenClaw, Codex, Hermes (gbrain). V1.5.0: progressive-disclosure
Web search and content extraction skill for pi-coding-agent. Search the web and fetch pages via a real headless browser (CDP). Works on Linux, macOS, and Windows.
Claude Code / Cursor / Cline skills for drdeploy. One command sets up SKILL.md files, installs the drdeploy CLI binary, and adds drdeploy routing to your CLAUDE.md.
Three investment research lenses: momentum (what's trending), contrarian (undervalued hidden gems), and balanced (Boglehead-style ETF portfolio). Works with Claude Code, Gemini CLI, OpenAI Codex, Cursor, and any Agent Skills-compatible harness.
Chinese adult-oriented AI text GalGame agent skill with harem-formation pacing, freeform roleplay, desire-map, character differentiation matrix, story memory, and novel export.
Elite adaptive whitebox exploit research skill for Claude Code and OpenCode. Classifies targets, loads domain-specific methodology, and hunts real vulnerabilities.
Opt-in UXCraft skill, CLI, and MCP server for AI coding agents — accessibility, design systems, UX research, and frontend handoff in one workflow.
Generative UI hosting CLI — publish single-file HTML pages from Claude Code, Codex, or Gemini CLI to a hosted URL. Runtime for the clawpage skill / plugin. Manages pages, short links, KV data tables, blob storage (R2), and view stats.
Azure DevOps PowerShell skill for GitHub Copilot, Claude Code, and other AI agents.
Install kane-cli browser automation skill for AI coding agents (Claude Code, Codex CLI, Gemini CLI)
Codex skill for Bundlephobia and npm package size analysis.
LaunchMyStore universal agent skill (SKILL.md open standard) — works in Claude Code, Claude.ai, the Claude API, OpenAI Codex, Cursor, Gemini CLI, Windsurf, Antigravity, Aider, OpenCode, and any other SKILL.md-compatible host. Natural-language router for t
Stack-agnostic code-hygiene skill for AI coding agents: clean AI slop, find security flaws, dead code, dependency rot, design and logging issues; lint, format, type-check, test, review, migrate dependencies, and fix project structure.
One-command installer for the frontend-art-direction Codex skill.
Startup and SaaS idea validation skill for Claude Code
Professional-grade project Wiki generator (aligned with the Karpathy LLM Wiki compile-not-retrieve pattern), powered by AI coding tools
Codex skill for committing current git changes in logical local groups.
Open Agent Skill and CLI-Anything harness for operating Voicebox from agent workflows.
AI agent skill: model UI components as finite state machines before coding. Claude Code · Cursor · Windsurf · OpenCode
實價登錄 → 乾淨 JSON／CSV. Taiwan property transaction prices from 內政部實價登錄 as clean JSON/CSV, written to disk and kept out of the LLM context. Deterministic CLI + library + Agent Skill (Claude/Codex plugin). No server, no model in the loop.
Portable Agent Skill for writing, auditing, rewriting, and maintaining software documentation from code evidence.
双 Pipeline 多 Agent 协作工作流 Skill —— PM + 7 Agent + 5 道关口
Codex skill for inspecting and triaging SonarCloud and SonarQube findings.
Install/update Iago — a Greptile-style PR-diagram skill for Claude Code, Codex CLI, Copilot, and Gemini.
Convert any local photo into a LEGO-style brick mosaic preview. MCP server + Node API powered by the BMBrick color quantization engine. Renamed from @bmbrick/agent-mosaic-skill.
Plain code doctrine package published by kamilchm
Marketing Intelligence pack for Claude Code - website audits, deal strategy, retainer finder, meeting prep, cold outreach, and ad creative analysis for agencies
Spec-driven, BDD-shaped project management for AI agents — OpenSpec proposals synced to GitHub, Azure DevOps, Jira, Linear, or GitLab.
CLI for skills-hub.ai — discover, install, and publish AI coding skills
Codex skill for inspecting and triaging GitHub security alerts.
Agents should invoke this skill for Tauri + Django + React desktop apps, especially backend lifecycle, CORS/auth, frontend integration, build packaging, dual desktop/web deployment, Rust commands, and platform-specific gotchas.
Agent Skill for fortpanel-publish. Installs SKILL.md (Anthropic Agent Skills format) and depends on the fortpanel-publish CLI as a runtime tool.
Agents should invoke this skill for broad multi-claim research projects needing planning, parallel investigation, source merging, gap closure, citation audit, and final synthesis when narrower research skills are insufficient.
TrueNorth CLI — crypto market intelligence in your terminal (technical analysis, derivatives, options, DeFi). Equity, commodity, macro, meme, KOL and Polymarket capabilities are available at app.true-north.xyz.
为非多模态大模型（deepseek、GLM、mimo 等）提供图片识别能力的 Agent Skill。支持多图识别、多模型回退、19+ 平台。
Instalador da skill /os para agentes, copiando a skill para .agents/skills/os no projeto atual.
Npx-installable AI skill for generating exam-ready LaTeX study notes from course materials (PDF, DOCX, PPTX). Includes diagram extraction, OCR, worked numericals, and complete compilation-ready .tex output.
MCP server for the Markdown Review Sidecar Format (MRSF)
Official PayWay Cambodia API SDK for Node.js
Official CLI for the PiAPI platform — call 97 multimodal AI models (image, video, audio, 3D, LLM) from your terminal or AI agent
中文长篇小说创作系统 — 自动检测环境、一键安装到 Claude Code / Codex / nanoPencil。
TapDB 游戏数据分析 AI Agent Skill - 查询和分析 TapDB 中的游戏运营数据（活跃/留存/付费/来源/LTV 等）
Pre-commit secret scanner. Blocks API keys, tokens, .env files, and private keys from leaking into git. Ships as a skill for Claude Code, OpenAI Codex CLI, Google Antigravity, and Moonshot Kimi CLI, plus a standalone CLI / git hook.
Agents should invoke this skill for academic or technical papers, arXiv/PubMed/IEEE/ACM links, PDFs, methodology review, limitations, practical implications, or extracting findings for engineering decisions.
Agent Skill for the dim container-image build daemon. Installs SKILL.md (Anthropic Agent Skills format) and depends on the dimctl CLI as a runtime tool.
Agents should invoke this skill for Docker Compose deployments, container updates, stack health checks, rollbacks, compose-file changes, image upgrades, failed deploys, or service restart planning. Provides safe deployment and rollback workflows.
Agents should invoke this skill for slow code, high CPU/memory, latency, large data processing, algorithmic complexity, profiling plans, benchmarks, or optimization requests. Profiles first and weighs trade-offs before changing code.
Agents should invoke this skill when planning tests from specs, architecture docs, PRs, risky changes, new features, bug fixes, or release work. Generates prioritized unit, integration, E2E, regression, and edge-case coverage.
Agents should invoke this skill when checking CVEs or known vulnerabilities in installed packages, dependencies, Docker images, OS packages, exposed services, or software versions. Produces severity-rated scan reports.
Agents should invoke this skill when a spec, plan, README, issue, or requirement must be verified against implementation. Traces requirements to code, checks interface contracts, and reports gaps or mismatches.
DOM-aware JS evaluator. Pipe code via stdin to run against any HTML page (URL, local file, or inline). Lightweight happy-dom alternative to Playwright for non-layout, non-interactive tasks.
Local CLI for generating SpeakCut short videos from narration text.
Agents should invoke this skill for code reviews, linting/formatting setup, maintainability checks, complexity concerns, warning cleanup, coding standards, or quality gates in Rust, TypeScript, Python, shell, and mixed repos.
Self-contained Pi package for skill lifecycle management: memory, skill-bank audit, evaluation, creation, and refinement tools.
Protects code from accidental AI overwrite or deletion in Cursor IDE — mandatory pre-write snapshots, review-before-apply, local Git safety net, and deterministic recovery. | 保护代码免受 Cursor AI 代理意外覆写或删除——强制写前快照、预览再执行、本地 Git 安全网、确定性恢复。
Your agent writes bad Rails. This catches it. A static-analysis CLI for Ruby on Rails that scores your codebase 0-100 and installs as an agent skill for Claude Code, Codex, Cursor, and Copilot.
Run rails-doctor, design-doctor, react-doctor, and qa-doctor with one command. Auto-detects which apply, aggregates the scores into a single report, and installs all four agent skills at once.
Data-driven form component based on ElementPlus implementation
Agents should invoke this skill for code security reviews, leaked secret checks, dependency risk, unsafe shell/Python/TypeScript/Rust patterns, auth/input-validation flaws, SAST-style audits, or supply-chain concerns in repositories.
Agents should invoke this skill when choosing or evaluating libraries, frameworks, tools, platforms, models, databases, APIs, or architectures for a use case. Produces criteria scoring, ecosystem assessment, and recommendations.
Pull .env updates from .env.example automatically. Keep your environment files in sync.
Agent skill for Pinduoduo and Taobao thermal transfer ribbon e-commerce image planning and production.
Agents should invoke this skill for connectivity, DNS, Pi-hole, port reachability, routing, firewall reachability, TLS/network timeouts, or service access failures. Provides structured network troubleshooting commands and interpretation.
Agents should invoke this skill for backup health checks, restore testing, NAS/Gitea backup integrity, 3-2-1 strategy review, backup script audits, or verifying repositories and archives can be restored safely.
Load agent skills temporarily without permanent installation. Temp mode auto-cleans on restart. Frozen mode persists across sessions.
Agent skill that guides AI coding assistants through building i2 Analyze connectors
All-in-one Claude Code skill: build, fix, review, deploy with one /aura command. 46 modes, 23 agents, 6-layer security, ~55% token savings.
Agents should invoke this skill when comparing competing products, services, libraries, tools, vendors, or approaches for market/product positioning, feature matrices, strategic trade-offs, pricing, adoption, or differentiation.
Browser QA your agent will actually run. Discovers every feature in a running app, exercises each one with Playwright, and reports pass/fail with screenshots so the agent can iterate to green. Installs as a skill for Claude Code, Codex, Cursor, and Copilo
Telegram agent-skill for Claude Code, Codex CLI, Cursor, Gemini CLI, Cline, Windsurf, and any AI coding agent that supports the universal SKILL.md format. Lazy-loaded — ~0 context tokens until your prompt mentions Telegram. Standalone CLI (`telegram-agent
Agent Skill and npm installer for GPT Image API proxy generation using GPT_IMAGE_BASE_URL and GPT_IMAGE_API_KEY.
WIP AI chat UI agent skill for building WIP-owned chat interfaces.
Agents should invoke this skill for refactors, code smells, migrations, duplication removal, module splitting, API cleanup, or restructuring plans. Emphasizes small safe steps, behavior preservation, and verification after each change.
UI/UX 设计智能系统 — 自动检测环境、一键安装到 Claude Code / Codex / nanoPencil。
Agents should invoke this skill for Linux server security reviews, SSH hardening, firewall/open-port audits, user/permission checks, exposed services, or host hardening requests. Produces severity-rated findings and practical remediation steps.
HTTP-only Super API skill installer for Claude Code, Codex, and OpenClaw
naming-suite — Brand & naming intelligence skills for Claude Code. Domain generation, brand auditing, competitor mapping, naming guides.
Agents should invoke this skill when identifying, categorizing, prioritizing, or planning technical debt work, debt sprints, cleanup backlogs, TODO consolidation, or long-term maintainability risks. Tracks debt with severity/effort.
Browser-based question boards with rich blocks (markdown, charts, mermaid, tables, code, sandboxed HTML) and element-level annotations for AI coding agents (Claude Code, Codex, …): ask users structured questions, present interactive visuals, collect inlin
Elite, read-only MCP/Grafana observability audit skill plus CLI — org/app/incident audits, alert and dashboard scoring (0–5 rubric), SLO and burn-rate recommendations, 2026-grade evidence ledger, two-layer client reports, OTel-stable semantic conventions,
Agents should invoke this skill as the final gate before release, handoff, or claiming completion for substantial changes. Runs acceptance/readiness checks, determines pass/fail, and gives a go/no-go recommendation.
Agents should invoke this skill for architecture reviews, module boundaries, dependency direction, coupling/cohesion, SOLID concerns, system design trade-offs, layering, service boundaries, or design decisions before implementation.
Agents should invoke this skill when choosing patterns, designing traits/interfaces/components, deciding abstraction boundaries, evaluating dependency injection/callbacks, or comparing implementation approaches in Rust, TypeScript/React, or Django/Python.
Guandata BI Skills 聚合安装包 - 一次性安装和更新 guancli、guands、guanetl、guanwf、guanvis
Install the HumanJS coding-agent skill — teaches Claude Code, Cursor, and Codex to write humanized Playwright automation. Run: npx @humanjs/skill
vegastack — a deterministic, offline knowledge harness for coding agents (Claude Code, Codex, Cursor, Gemini) with project-selected local registry entries for infrastructure, cloudops, CI/CD, and Terraform.
Teochew People (潮汕人) writing and review skill for AI agents.
Skill evaluation CLI — waza-schema-compatible runner with empirical-prompt-tuning iteration loop, structured self-report grader, and LLM-as-Judge.
Agents should invoke this skill when defects, regressions, failed tests, unexpected behavior, or spec mismatches are found. Produces structured reproducible bug reports with severity, evidence, environment, and actionable next steps.
Website audit and pitch proposal generator for marketing agencies. Claude Code skill.
Agent Skill for compiling vague intent into useful artifacts.
Install the expose.team Agent Skill for Claude Code, ChatGPT, Cursor, Copilot, and 30+ AI agents
AI Agent Skill for generating beautiful single-file HTML presentations with reveal.js — 6 themes, 17 layouts, 8 chart presets
Pi extension package for Product Hunt research and digest workflows.
观远工作流数据流编辑工具 - 创建、编辑、导出、预览、保存数据流
观远 ETL 本地开发工具 - 拉取、编辑、导出、预览、保存 ETL
Cloudflare Wrangler multi-account manager — save, switch, and run wrangler against multiple Cloudflare Workers accounts with AWS-style --profile and per-invocation shadow HOME isolation.
CLI for playing board games on TableCraft — join rooms, make moves, challenge bots. Includes the `tablecraft-player` skill for AI agents (Claude Code, Codex CLI, etc.).
Core library for SEO keyword intelligence skills — DataForSEO API client, scoring engine, workspace manager
Seamlessly integrate ZenTao with OpenClaw. A powerful MCP server and CLI tool providing intelligent ChatOps capabilities for ZenTao project management.
观远 BI 数据源/数据集管理工具 - 连接账号、数据集创建/配置/刷新、增量设置、定时更新
Agent skill that runs a Socratic interview inside your coding agent — turning vague ideas into structured intent
MTA skills for AI agents - Analyze codebases, generate custom migration rules, and orchestrate end-to-end migrations using Konveyor/MTA tools
Publish trustless, immutable, on-chain skill releases via the HOL Registry Broker.
A Claude Code skill for Amazon-style narrative writing — PR/FAQs, six-pagers, decision memos, and other executive-grade prose.
AI-powered GEO (Generative Engine Optimization) tool — generates llms.txt, robots.txt rules, and Schema markup to make websites discoverable by ChatGPT, Claude, Perplexity, and Gemini.
WebCloner — Website visual cloning skill for Claude Code. Clone landing pages, marketing sites, portfolios, and ecommerce storefronts into pixel-accurate Next.js replicas.
AI Agent Skill - Build production-ready AI applications with multi-agent orchestration, Virtual Database, streaming conversations, and React UI Kit. For Claude Code, Cursor, Windsurf, and 30+ AI coding agents.
Agent skill for choosing GPT-Image visual styles, prompt templates, categories, and scene tags. Powered by XidaoAPI.
Claude Code skill for writing production-grade Storybook stories — based on BBC iPlayer research
Stream or download CloudWatch logs to local NDJSON via AWS profiles—manual review, scripting, or AI-assisted analysis. Agent skill: skills/logness/SKILL.md (export @tbelmega/logness/skill).
React Native store compliance + App Store Connect automation skills for AI coding agents. 2 skills: rn-store-compliance (rejection prevention, guidelines, 35+ reference files) and asc-toolkit (build, sign, release, metadata, TestFlight, pricing, screensho
AnyCap CLI - AI Agent capability runtime
AI agent skill for ERC-8004 agent economy interactions
Agent Skill for managing skills with skillpm — install, publish, and wire Agent Skills into AI agent directories
Astraler image generation skill for Claude Code — generates high-quality images using Google Gemini / Imagen 3 API
AI Agent Skills for managing the GitLab workflow — plan milestones, track issues, commit with traceability, and open merge requests via the glab CLI.
Agent skill for P2P file transfer — send files between agents and humans with zero configuration
Claude Code skill to generate complete animated presentations for the Animot app from a text prompt or structured markdown
Record conscious markers and typed beats during work sessions, then write chronicle markdown to your vault Progress folder.
SEO and GEO (Generative Engine Optimization) linter for Markdown/MDX content — the first open-source linter that checks your content for AI search visibility
Template for building Pi packages with extensions, Agent Skills, prompts, and themes.
Impact-aware code review skill kit with hard-gate enforcement, compare reporting, and multi-agent installer support.
Installer for the cinematic-scroll Agent Skill — copies the skill into ~/.claude/skills/ (Claude Code, Cursor, etc.). The skill builds cinematic, scroll-driven websites: pinned chapters, parallax, 3D tilt, environment-morphing backgrounds, and full releas
Skill for your agent — reference guide for integrating WhatsApp Business messaging into any application through a third-party BSP (Coexistence-style API). Provider-, database-, and framework-agnostic.
Agent Skill for YouTube transcripts, search, and channel browsing via the SubDownload MCP server. Works with Claude Code, Cursor, Codex, Windsurf, Gemini CLI, OpenCode, and more.
Production-ready AI agent skill for the Zama Protocol (FHEVM). Drop into Claude Code, Cursor, Windsurf, or OpenClaw and your agent gains full knowledge of confidential smart contract development: encrypted types, FHE operations, ACL, input proofs, user/pu
Claude Code, Codex, and Cursor skills for adding Deepdub text-to-speech to JavaScript, Python, and CLI projects.
Anti-AI-slop refactor tool. Detects the structural bloat patterns LLMs love to generate — padding comments, useless try/catch, dead imports, explicit any, commented-out code, unnecessary async, and 12 more.
Installer and source files for the nestjs-openapi-docs agent skill.
App Shot Editor layout DSL + device-frame geometry — framework-free building blocks for composing editable App Store screenshot layouts. Intended for use via a bundler (Vite, esbuild, etc.).
Cookie Chain developer skill for Claude Code and Cursor — onboard builders to the SVM-compatible Cookie Chain with one command.
A Claude Code agent skill that adds native SwiftUI animations — micro-interactions, view transitions, loading states, gesture-driven motion, hero animations, SF Symbol effects, and haptics — to iOS, macOS, watchOS, and visionOS views.
Re:ZERO-style implementation loop for pi coding agent: Subaru implements, seven witches review, Return by Death retries.
Xueqiu (雪球) stock data CLI for AI agents — quotes, klines, financials, KOL sentiment, live news, and more
A Claude Code skill that routes inference to a locally running Ollama model or Ollama Cloud model.
Generate polished product demo videos with one command. Just give a URL and a prompt.
Programming-first context engine for Claude Code — TypeScript-powered codebase indexing, dependency graphing, symbol-level search, and zero-token context injection via hooks.
A systemic UI design skill for Claude Code, Gemini CLI, and Google Antigravity
Install the rag-engineering skill for Codex and Claude Code — methodology, diagnosis, and discipline for building, refactoring, evaluating and testing any RAG system.
LeadGenius Pro API Skill — B2B lead and client management with Cognito JWT auth (cookies + Bearer + API key). Includes E2E test suite.
Slack Admin CLI for humans and AI agents — manage Enterprise Grid via admin.* APIs
Chat with any YouTube video from your terminal using AI
Two surfaces for AI agents to operate Dokploy infrastructure: a `dokploy` CLI + Claude Agent Skill (recommended), plus an MCP server. Tracks Dokploy v0.29.5, 526 endpoints across 48 grouped tools.
Search AI podcast quotes by topic — recent episode excerpts from Lex Fridman, Dwarkesh Patel, No Priors, Latent Space, and dozens more. Universal agentskills.io skill compatible with Claude Code, OpenAI Codex, Hermes Agent, OpenClaw, and any other agent t
Agent Skill + MCP server for Supabase Realtime/CDC. Bounded subscription pattern fits Edge Function isolate budgets.
Postals — the agent skill that turns any AI into a direct mail machine. One MCP tool call mails a physical handwritten postcard (real pen-and-ink, USPS 3-5 day delivery, $4.99 per card). Works with Claude Desktop, Cursor, Claude Code, OpenClaw, n8n, LangC
AI-native video editor — talk to Claude to make video. Trim, zoom, caption, and assemble clips via the clip CLI and a Claude Code skill.
Build learning pathways for individuals, teams, and ecosystems
SkillOS skill pack for AI coding agents — guidance on integrating @skillos/sdk into skill games (puzzle, word, match, retro arcade, speedrun, rhythm, trivia) for permissionless tournaments, on-chain leaderboards, and sponsor-funded prize pools.
Agent skills for Prisma Next — eight workflow-scoped SKILL.md files an agent loads on demand to operate Prisma Next end-to-end.
Grilling session that challenges plans against the existing domain model, sharpens terminology, and updates CONTEXT.md/ADRs inline as decisions crystallise.
FHEVM Skill for Claude Code, Codex CLI, Cursor, and other AGENTS.md tools (Aider, Cline, Continue, Zed, Jules). One-shot installer for confidential smart contract workflows on Zama FHEVM v0.11.
Programming-first context engine for Claude Code — TypeScript-powered codebase indexing, dependency graphing, symbol-level search, and zero-token context injection via hooks.
An Agent Skill that generates structured developer journals (modification summary, future-reader guide, collaborator-facing API notes, and a self-review) to <project>/.journal after a coding session. Cross-platform: installs into Claude Code, Cursor, Gemi
🤖 Quick-start skill for AI agents to earn XLM on the Stellar testnet via XLMx402earn
Turn agent answers into self-contained HTML artifacts and presentation decks — operator briefs, review packets, incident timelines, decision briefs, and talks. Zero dependencies, zero build, one file.
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.
The ultimate AI design CLI for Agents and Developers. Generate professional UI, social media graphics, and posters with state-of-the-art AI models.
Agent skill for the LingXia cross-platform app framework. Installs a markdown skill bundle into your project so AI coding tools — Claude Code, Claude Agent SDK, OpenAI Codex, Cursor, or any agent that reads project markdown — can build lxapps, host apps,
AI Agent Skill for generating beautiful, animated SVG technical diagrams with 11 themes and 14 diagram types
Agents should invoke this skill to create, update, or implement standardized PATCH.md documents that describe reproducible source code patches.
Agent Skills for CloudTools — AWS, GCP, Azure, and MCP
Claude Code skill that helps builders make architecture and ideation decisions on Arkiv. Covers mental model, brainstorming walkthroughs, ETHLisbon sponsor mix patterns, business model patterns, and 30+ idea seeds. Pairs with arkiv-ethlisbon-skill for ful
FHEVM Agent Engineer — Production skill pack for building confidential smart contracts with AI agents
AI skill suite for financial advisors and wealth managers — portfolio narratives, market commentary, financial plan summaries, and compliance communication review.
Agent Skill for storing and retrieving author information
CLI tool for AI agents to manage tasks on BotBoard
Autonomous research & experiment loops for coding agents. Run experiments overnight, wake up to results.
Modular agent skill for code review and refactoring, grounded in the s4.codes code-correctness lesson series.
CLI tool for installing and managing AI agent skills for Claude Code, Cursor, Windsurf and more
Install the Taste skill into Claude Code with one command.
Agent skill for cachelyze — teaches AI agents how to use cachelyze effectively
Agent skill for 1:1 Figma-to-code implementation with self-correcting validation loops. Works with Claude Code, Codex CLI, and any Agent Skills-compatible tool.
LLM Wiki 知识库管理技能 — 向导式初始化，逐步采访，自动搭建 Wiki，Obsidian 集成
Agent skill for hearback — instructions + tools (OpenAI/Anthropic/Claude Code formats) for AI agents to file bugs and feature requests
A routed skill-design catalog for AI agents, installed with one /skill-master entry point.
Claude Code skill for defuddle - extract clean article content from web pages
Client shim for the Reassign MCP — a circular 24-hour calendar and time-tracking copilot.
Node coordinator that discovers AI agent skills from installed npm packages and registers them in AGENTS.md. Sibling of netresearch/composer-agent-skill-plugin.
AI-powered CLI to explain programming errors with fixes and ELI5 output.
DIP 开发方法论 — 自动检测环境、一键安装到 Claude Code / Codex / nanoPencil。
Claude Code / Codex agent skill for email / calendar / Teams / meetings / Drive / OneDrive / SharePoint / contacts / GitHub via apl + gh.
An Agent Skill for evidence-backed release preparation, changelog drafting, SemVer recommendations, and approval-gated publishing plans.
Claude Code skill that makes you Arkiv-fluent for ETHLisbon. Pairs with the official arkiv-best-practices skill, adds gap-fill gotchas, ETHLisbon starter templates, and Claude Code prompting patterns. One npx command installs both.
Use when evaluating, implementing, reviewing, or debugging Shoo auth (shoo.dev) Google sign-in in browser apps, including @shoojs/react, @shoojs/auth, hosted shoo.js, Convex custom JWT integration, PKCE callbacks, session checks, and server-side id_token
Installable Realtime Register REST API v2 agent skill and CLI. Ships SKILL.md, 109 operation references, and the rtr validation/doc CLI. Install with `npx @cave-man/realtime-register-skills install`.
X/Twitter topic intelligence skill for Claude Code
KnowFun AI multimodal content generator - Create AI PPT/presentations, posters, interactive games, and educational films. Lightning-fast REST API for educators, content creators, and learners. Integrate with Claude Code, Cursor, Cline, OpenClaw AI assista
Type-safe, performant and extensible clone implementation
Claude Code skill for real-time cryptocurrency prices from multiple exchanges via Luzia API
Cursor/Agent 技能：老年人回忆录成书流水线（访谈→story-extractor 碎片→骨架 JSON→逐章散文→单文件 HTML，系统字体无 Google Fonts）
Control a Xiaomi Robot Vacuum X20+ via the xiao CLI — agent-ready skill for Claude Code, Codex CLI, Cursor, Gemini CLI, Copilot (agentskills.io format).
Professional ecommerce SEO audit skill for Claude Code with 7 specialized audit types. Developed by Affilino NZ - Auckland Shopify SEO Agency.
Claude Code skill: transform rough prompts/ideas into production-ready LLM prompts with CoT, Constitutional AI, RAG optimization, and multi-model support
AIUSD trading and account management skill via MCP protocol.
Team intelligence for AI coding agents. Extract conventions, anti-patterns, and domain knowledge from your codebase and PR history.
CLI for code context with semantic search, AI analysis and summary
An interactive, hands-on tutorial system that teaches users to become Claude Code power users through progressive exercises on a real practice project. v1.1.5 fixes model configuration and improves user experience.
Agent skill for documenting codebases with the C4 model
Task management CLI for AI coding agents. Push tasks from Copilot, Claude, or any agent.
Treasury yield agent skill — rebalances stablecoin yield across Aave / Morpho / Kamino within a protocol allowlist.
Create stunning AI-powered presentations from your terminal
Customized QA/AzureDevops skill for GitHub Copilot, Claude Code, and other AI agents.
CLI + agent skill for Lenny's Newsletter & Podcast archive via MCP
AI-driven structured interview skill for coding agents. The agent asks questions one by one, follows up naturally, and produces a clean markdown transcript.
一个 Agent Skill，让 AI 助手成为 Vue 2 → Vue 3 迁移专家。包含专家知识库、SOP 工作流和可执行 Codemod。
Comprehensive Zero CRM API skill for managing contacts, deals, tasks and user profiles via REST API. Simple, fast, and powerful CRM automation with bulk operations and comprehensive documentation.
联系人搜索 Skill — 本地扫描简历/表格/通讯录 + 在线搜索 BOSS直聘/脉脉/LinkedIn 等平台候选人 + LinkedIn 深度资料抓取与候选人评估
AI skill installer and integration verifier for Trustless Work (Escrow-as-a-Service on Stellar)
Incremental React architecture guidelines as an agent skill
Portable Microsoft 365 plus Cloudflare mail orchestration framework with skill bundle packaging for agent harnesses like Codex.
Craft-themed React UI primitives — paper, rope, crayon palette
AIUSD Pro — AI-powered trading agent with built-in reasoning.
AI agent skill: 交互式代码架构图生成 - 分析代码仓库自动生成可交互的分层架构 HTML，支持点击下钻查看 Mermaid 子流程图
Installer for the openDAG agent skill.
Consultative goal-setting and KPI design assistant for Claude Code using discovery-first approach. Asks qualifying questions before recommending frameworks (OKR, SMART, BSC, V2MOM, 4DX, EOS Rocks). Includes KPI libraries, dashboard blueprints, review cade
AIUSD Natural Language Skill for OpenClaw
Stealth browser for AI agents. iPhone 15 Pro fingerprint. Drop-in Playwright replacement.
TSX -- AI framework for building TopStepX trading bots. Extends GSD (Get Shit Done) with trading domain workflows, agents, and templates.
Agent skills for Pictify — generate images from HTML/CSS with AI agents. OG images, social cards, banners, screenshots, certificates, and more.
The flight recorder for AI coding — keeps your docs in sync with your code
Payroll co-signer skill — reviews and co-signs a monthly payroll batch with anomaly signals + CAS-claim broadcast.
Skill for setting up and managing Woodpecker campaigns correctly using API V2 and V1. Includes correctly linked prospect enrollment and signature automation.
Immigration law skills for Claude Code — case summaries, client letters, RFE responses, and visa briefs for immigration attorneys.
Claude Code skill for safe GitHub releases using staged pre-release/beta workflows
utoo toolchain skills from ai
Claude Code skill that triages Workflowy nodes by proposing locations based on rules
Expert AI Visibility and Local SEO guidance from Local Falcon - the pioneer of geo-grid rank tracking
Production image asset generation skill for Codex, Claude Code, and compatible agent runtimes using Nano Banana 2 and Nano Banana Pro.
CLI for managing secrets in OS-native credential storage. Includes Agent Skill for AI coding assistants.
SuperApp 数据可视化辅助工具 - 在 guandata-studio-startup 中接入 @wubaoqi/guan-chart-kit
Global liquidity quantitative analysis skill for Claude Code - generates trading signals for Gold, Nasdaq, BTC based on Fed liquidity indicators
Agent Skill for automating Microsoft Excel via MCP Server — 225 operations including Power Query, DAX, PivotTables, Charts, and more
OpenCode agent skill: address code review comments on a pull request — single or bulk mode
CLI + agent skill for Lenz verified claims fact-checking API
x402 skill — agents pay paywalled web APIs per-call via x402 micropayments with cents-per-call + cents-per-day caps so runaway loops stop themselves.
AP agent skill for ChatGPT Apps + Xero — drafts vendor payments from Xero invoices within a policy envelope, queues them for principal approval.
Shareable agent skill and export CLI for .agents/dispatches session records
Puppeteer-based bulk screenshot automation for web pages. CLI & programmatic API.
OpenCode agent skill for refining GitHub issues
Design system orchestrator for AI coding agents — 31 style specs, Flow system, blocking task lists, and automated QA
AP agent skill for Claude Desktop + QuickBooks Online — drafts vendor payments from QBO invoices within a policy envelope, queues them for principal approval.
OpenCode agent skill: fully autonomous end-to-end development flow
The Frontend Craft Specification. 324 rules across 20 categories with measurable thresholds. Utilities for color contrast, timing validation, spring physics, typography scales, spacing systems, and touch target compliance.
Universal refactoring skill for AI coding tools — supports 14 tools including Claude Code, Cursor, Windsurf, Copilot, and more
MCP server for staged access to the Agent Skill creation process document
Comprehensive sales operations setup assistant for Claude Code - implements lead management, forecasting, sales enablement, data analysis, process optimization, and team building
OpenCode agent skill: generate an effective AGENTS.md for a new project by exploring the codebase and migrating any existing instruction files
Cross-agent SaaS launch-readiness auditor skill
Agent Skill for Warden Docker development environments
OpenCode agent skill: diagnose and resolve application errors with root cause analysis and a fix plan
OpenCode agent skill: comprehensive planning workflow for GitHub issues
AIUSD Core — trading tools and account management for AI agents via MCP protocol.
Trip-budget skill for ChatGPT — issues a scoped virtual card for a weekend with MCC filters + auto-revoke.
OpenCode agent skill: full-repository audit for security, code quality, performance, and error handling
MeOS installer wrapper for local-first skill setup across Codex, Claude Code, OpenClaw, and OpenCode.
Claude Code skill — Direct-to-Runtime Zero-Hop Stack architecture guide
Claude Code skill for Spotify playback control + 5947 music genre database
Portable Microsoft 365 plus Cloudflare mail orchestration framework with skill bundle packaging for agent harnesses like Codex.
OpenCode agent skill: plan a GitHub milestone with phased issues and explicit dependencies
Agent skill for verifying app behavior — capture evidence, generate interactive reports for human review
Claude Code agent skill for secure coding across 15 stacks: 10 web frameworks (Spring, Django, Flask, FastAPI, Rails, React, Vue, Angular, Go, ASP.NET), 4 languages (C, C++, TypeScript, C#), and Terraform. Install via npx.
BYOCB ArbInjectionSkill - Smart contract vulnerability scanner for arbitrary call injection. Educational tool for security research.
Generic agent skill for operating the WorldFork branching simulation backend.
TypeScript toolkit and CLI for the viral SBTI parody personality test.
Native Pi extension for YouTube Data API search, video details, and transcripts without an MCP daemon.
AI agent skill providing Crip Walk (C-Walk) dance knowledge — history, techniques, cultural context. SKILL.md format for Claude Code, Codex, and AI agents. Data from https://cripwalk.homes
Astraler image generation skill for Claude Code — generates high-quality images using Google Gemini / Imagen 3 API. Installs automatically to ~/.claude/skills/
AI agent skill for operating the LeadGenius Pro Automation API and lgp CLI. Covers ICP management, FSD pipeline automation, lead generation/enrichment/scoring, user provisioning, territory analysis, webhook management, and email platform integration.
A skill that creates new Claude skills and automatically shares them on Slack using Rube for seamless team collaboration and skill discovery.
Claude Code skill for Google Docs, Sheets, Drive, and Apps Script operations
Install the Trustless Work escrow skill for your AI coding agent (Claude Code, Cursor, Copilot, and more)
Agent skill for research — teaches AI agents how to use research effectively
CLI + stdio MCP server + agent skill for uploading files to swap cloud storage (Tencent COS first).
Pre-execution static analysis skill for AI-generated code changes
Agent Skill for automating Microsoft Excel via CLI — Power Query, DAX, PivotTables, Charts, VBA, and more from scripts and coding agents
MCP server for the Markdown Review Sidecar Format (MRSF)
Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization
Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simpl
Claude Agent Skill for creating AI talking head videos with VEED Fabric
Salesforce ↔ LeadGenius Skill — Export leads from LeadGenius and import them into Salesforce with custom AI fields, FLS deployment, and automated scripts.
Create a complete new page in the application with routing, layout, data fetching, and all necessary components following project patterns.
GetSkill CLI
Implement a comprehensive search system with full-text search, filtering, faceted navigation, and result highlighting across multiple entity types.
Use when invalid data causes failures deep in execution, requiring validation at multiple system layers - validates at every layer data passes through to make bugs structurally impossible
Add a many-to-many relationship between two existing entities using a junction table, including migration, types, and service methods.
Identifies high-quality leads for your product or service by analyzing your business, searching for target companies, and providing actionable contact strategies. Perfect for sales, business development, and marketing professionals.
A release-aware Agent Skill for terse commit messages using scope-first subjects and optional Conventional Commit metadata.
JD or job link -> ATS-optimized tailored resume. One-command installer for the resume-forge Claude Code / agent skill (default | classic | latex templates).
OpenClaw-first 的 KOL Skill 工厂：采集 Twitter/X 用户，沉淀为可安装的通用 Agent Skill
Create production-grade iOS paywalls with StoreKit 2 integration - A Claude Code skill for generating native Swift paywall implementations
A skill that creates new Claude skills and automatically shares them on Slack using Rube for seamless team collaboration and skill discovery.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' w
Picks random winners from lists, spreadsheets, or Google Sheets for giveaways, raffles, and contests. Ensures fair, unbiased selection with transparency.
Use when executing implementation plans with independent tasks in the current session - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates
Implement a comprehensive search system with full-text search, filtering, faceted navigation, and result highlighting across multiple entity types.
Scaffold a new React component with TypeScript, following the project's conventions for component structure, props, styling, and service integration.
Agent skill for building production-quality data dashboards in HTML or React. KPI cards, 5 chart types, filter systems, sortable paginated tables, CSV export — with three style presets.
Add filtering capability to an existing entity's list view, extending service layer filters and adding UI controls for faceted navigation.
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
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
AI Agent skill for controlling smart home devices through Home Assistant. Supports Huawei, Orvibo, Xiaomi, Aqara, Tuya and more.
Implement a comprehensive search system with full-text search, filtering, faceted navigation, and result highlighting across multiple entity types.
Toolkit for creating animated GIFs optimized for Slack, with validators for size constraints and composable animation primitives. This skill applies when users request animated GIFs or emoji animations for Slack from descriptions like "make me a GIF for S
Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automa
Generate production ready dockerfiles using best practices
Analyzes your recent Claude Code chat history to identify coding patterns, development gaps, and areas for improvement, curates relevant learning resources from HackerNews, and automatically sends a personalized growth report to your Slack DMs.
Claude Code skill that uses Workflowy as a live task board for Claude
Implement a complete, production-ready feature from database to UI, orchestrating multiple skills to deliver an end-to-end user-facing capability.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Token-efficient caveman mode for Elasticsearch AI agents. 64% fewer tokens, 100% technical accuracy.
Create Supabase database migrations with proper table structure, indexes, Row Level Security (RLS) policies, and triggers following project conventions.
Agent skill for Loop — the autonomous improvement engine. Teaches AI agents how to use Loop's REST API.
Extracts and analyzes competitors' ads from ad libraries (Facebook, LinkedIn, etc.) to understand what messaging, problems, and creative approaches are working. Helps inspire and improve your own ad campaigns.
Generates creative domain name ideas for your project and checks availability across multiple TLDs (.com, .io, .dev, .ai, etc.). Saves hours of brainstorming and manual checking.
Extend TypeScript database types to include new tables, columns, or relation types, maintaining type safety across the application.
Implement a complete, production-ready feature from database to UI, orchestrating multiple skills to deliver an end-to-end user-facing capability.
Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effor
Add a new Radix UI component to the project's UI library with proper styling, accessibility, and variant support.
One-command installer for the oh-my-dev Agent Skill.
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P upd
Implement a complete social feature (like, star, bookmark, follow) across all layers: database migration, types, service methods, and UI components.
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-t
Build production-grade LLM prompts using the RTCF Framework (Role, Task, Context, Format). Walks through each component, grills for gaps, and assembles optimized prompts.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Downloads videos from YouTube and other platforms for offline viewing, editing, or archival. Handles various formats and quality options.
Automatically organizes invoices and receipts for tax preparation by reading messy files, extracting key information, renaming them consistently, and sorting them into logical folders. Turns hours of manual bookkeeping into minutes of automated organizati
Implement a complete, production-ready feature from database to UI, orchestrating multiple skills to deliver an end-to-end user-facing capability.
Create complete CRUD (Create, Read, Update, Delete) functionality for a new entity type, including database, types, service layer, and UI components.
Create a complete new page in the application with routing, layout, data fetching, and all necessary components following project patterns.
Replace with description of the skill and when Claude should use it.
Implement a complete, production-ready feature from database to UI, orchestrating multiple skills to deliver an end-to-end user-facing capability.
Analyzes meeting transcripts and recordings to uncover behavioral patterns, communication insights, and actionable feedback. Identifies when you avoid conflict, use filler words, dominate conversations, or miss opportunities to listen. Perfect for profess
Implement a complete, production-ready feature from database to UI, orchestrating multiple skills to deliver an end-to-end user-facing capability.
Implement a comprehensive search system with full-text search, filtering, faceted navigation, and result highlighting across multiple entity types.
Shareable agent skill and export CLI for .agents/dispatches session records
Claude Code skill for generating conventional git commits. Use when committing code, writing commit messages, or following conventional commits format.
Add a new method to an existing service layer file following the project's patterns for data access, type safety, and mock fallback support.
Improves the quality of images, especially screenshots, by enhancing resolution, sharpness, and clarity. Perfect for preparing images for presentations, documentation, or social media posts.
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
Zama Skill for Claude Code, Codex CLI, Cursor, and other AGENTS.md tools (Aider, Cline, Continue, Zed, Jules). One-shot installer for confidential smart contract workflows on Zama FHEVM v0.11.
AI-first workflow manager for heavy MCP tools with lazy Agent Skills and patchable runs.
Reverse-engineer any SaaS into a build blueprint — moat analysis, churn vectors, tech stack, and build prompt for Claude Code
Agent skill and CLI toolkit for structured video understanding workflows.
Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".
Apply Divio's four-quadrant documentation system to write, audit, classify, restructure, and review technical documentation. Use when creating or improving tutorials, how-to guides, reference docs, explanations, docs...
Reusable Agent Skill for creating modern green HTML/CSS/JS presentations for chemical production QC laboratory audiences.
Use Worktrunk for git worktree workflows whenever working in a git repository. Prefer `wt` over manual branch/worktree lifecycle commands when creating task branches, switching contexts, spawning parallel agents, merg...
Build a throwaway prototype to flesh out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations togglea...
Install the llm-wikify maintained-local-wiki skill + commands into Claude Code, Codex, and OpenCode — safely, from one source, never touching your CLAUDE.md / AGENTS.md.
AI 视觉改稿建议助手 / AI Visual Improvement Assistant — an Agent Skill that tells you where to look, why it matters, and what to change first. Works with Claude Code, Codex, Cursor and other SKILL.md-compatible agents.
对标 Trellis 的全平台嵌入式 AI 开发框架：RIPER-5 + 四文件记忆 + 分层架构门禁 + Scout/Builder/Verifier + 22 个工具调用技能（build/flash/debug/serial/can/modbus/visa/static/memory/rtos/peripheral-driver）+ 55+ 篇离线知识库 + 12 个专项流程（含比赛 6-Agent 模式），装进工程、项目级 hook 自动注入 spec、学习回流，一次写全平台交付（Claude/Cu
产品需求文档（PRD）生成器 — 自动检测环境、一键安装到 Claude Code / Codex / nanoPencil。
LLM Wiki 知识库管理技能 — 向导式初始化，逐步采访，自动搭建 Wiki，Obsidian 集成
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says som...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra...
Install the CyyMall Agent skill for Codex and other coding agents.
Drive your dev site in Playwright, map it, capture console + network + DOM + screenshots + video, write one structured report. Built for AI coding agents and humans.
Repo-local project memory for humans and AI agents.
Codebase knowledge teacher for interaction designers — explains code architecture with analogies, diagrams, and progressive depth. Auto-installs to Claude Code / Codex / nanoPencil.
Pi extension for LocalGPT — unified MCP bridge. 50 curated tools for memory + Gen 3D world building.
Install the CoverView cover-image agent skill into any repo so your coding agent can generate blog/social cover images.
Analyze a user's Plannotator plan archive to extract denial patterns, feedback taxonomy, evolution over time, and actionable prompt improvements — then produce a polished HTML dashboard report. Falls back to Claude Co...
Clipboard-first Pi extension that turns the current conversation into a next-session handoff prompt.
Agent skill for researcher.now: article & video analysis (formatted content + structured claims/facts/quotes) and deep multi-source research returning cited Research Reports. Includes SKILL.md for Hermes/Claude-style skill loaders.
AI Skill: בוחן מיוני רפואה — שאלון אישי-ביוגרפי (מו"ר / מרק"ם / מר"ב). Evidence-based examiner skill for Israeli medical school biographical questionnaires.
Self-contained agent skills for Rong runtime scripting and module authoring.
Interactive SVG writer plugin for initx
Turn an idea or objective into a goal package for /goal. Interviews the user, builds a reviewed fact sheet via Plannotator, then explores the codebase to produce an execution plan.
Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate ti...
Pi extension for on-demand Verse / UEFN docs lookup via verse-mcp.
Hinto AI CLI — manage videos, articles, and publishing via the Hinto API
Pi skill for reviewing npm-registry dependency safety across npm, pnpm, yarn, and bun before project initialization, feature work, package additions, or package updates.
Official Longbridge Securities agent skill — real-time quotes, fundamentals, portfolio, technical analysis for HK/US/A-share/SG markets
Pi extension that lets power users choose provider and model at startup before the session begins.
Visualize peer-review comments for a rebuttal: a self-contained, offline HTML page of the original reviews highlighted in place, colour-coded by action, grouped into priority-ordered rebuttal points each with an editable draft. Ships as a Claude Code skil
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or espe...
Generate self-contained HTML visualizations with Plannotator theming. Use for implementation plans, PR explainers, architecture diagrams, data tables, slide decks, and any visual explanation of technical concepts. Pla...
Switch Pi's AI provider and model based on time of day via YAML time-slot configuration.
A model-aware Agent Skill that silently refines your prompt for the model currently answering.
Vibe Coding workflow pipeline for designer-developers — 8-stage architecture-locked scaffold with cross-module contracts, optimistic updates, and red-line auditing.
Codex skill for analyzing release changes and recommending a semantic version bump.
A post-session programming tutor that runs as an in-session Codex/Claude Code skill. After an AI-assisted coding session it picks the one load-bearing decision you most likely don't truly understand, makes you predict why before it reveals, then teaches t
Flynet agent skill for Claude Code and rules for Cursor. Run `npx @flynetdev/skills` in your project to install both.
Disciplined thinking skill for people who build with AI. Four playbooks — teach, debate, firefight, root-cause — in your LLM.
MCP server — safe place for AI agents to vet ERC-20 tokens on GoPlus 60+ chains and native Pharos (mainnet 1672, Atlantic testnet 688689)
Agent skill for Cursor, Claude Code, and Codex — SEO, GEO, and AI visibility for Next.js and Vite/React apps. Covers metadata, Open Graph, Schema.org JSON-LD, sitemap, robots.txt, keyword clustering, llms.txt, and CSR/prerender guidance.
Install AI-agent Skills & MCP servers with a verified, independent SaferSkills trust score — across Claude Code, Cursor, Windsurf, Copilot, Codex, Gemini, Cline & OpenClaw.
Turn a PRD into a multi-phase implementation plan using tracer-bullet vertical slices, saved as a local Markdown file in ./plans/. Use when user wants to break down a PRD, create an implementation plan, plan phases fr...
Create a PRD through user interview, codebase exploration, and module design. Use when user wants to write a PRD, create a product requirements document, or plan a new feature.
Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.
Compact the current conversation into a handoff document for another agent to pick up.
A monorepo of portable Agent Skills for AI-assisted engineering workflows.
Annotate AI docs & copy/share feedback for Claude, ChatGPT & co. Zero-backend Chrome extension (Manifest V3) + `npx noteback wrap` feedback canvas + agent skill.
Dependency-free CLI for validating file proposal manifests and rendering interactive HTML review viewers.
Lightweight Spotify Now Playing widget for Pi Coding Agent.
The agent skill that makes any AI coding assistant an expert at building agentic tooling. Run npx @nex8n/foundry to install it into your project.
Preview local HTML reports and static mini apps, then publish them to shareable URLs.
抓取微博热榜，根据用户偏好定制化推送热点话题，视情进行信息补全。用户偏好交互式访谈，推送质量即时反馈，特征规则自优化。
Use automatically when evaluating or applying Dolt, the Git-like version-controlled SQL database, for database branching, merging, diffs, audit history, rollback, or versioned MySQL replica workflows.
Dual-model synthesis for Pi — run the same prompt on two models, get one synthesized answer
Agent Skill that turns any repository into a repository-as-spec workspace. Distributed for npx skills add and released via semantic-release.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be use...
Install an AI agent skill for writing clear, testable technical product requirements across Codex, Claude Code, Cursor, Gemini CLI, OpenCode, OpenClaw, Hermes Agent, CodeBuddy, GitHub Copilot, and Trae.
SHELEG Design — an agent skill for building cinematic, scroll-driven, particle-backed landing pages. Installs a SKILL.md + reference doc into your project so Cursor/Claude agents can build sites with a single-clock motion system, a scene-formation particl
提取B站视频/图文内容并生成摘要 — 下载音频+ASR转写/图片OCR、LLM摘要、飞书推送
Claude Code / Agent skill that converts e-commerce screenshots or HTML prototypes into faithful, working web apps — exact colors, typography, text, and components. Animations opt-in. TRD-driven output.
Want to publish your own skill?
See the Creating Skills guide for the full packaging spec, or run skillpm init to scaffold a new skill package in seconds. Skills follow the open Agent Skills spec.