Prompt-driven capabilities that teach an agent new workflows. Every skill here is evaluated before it is listed.
Ranked by GitHub stars. Search to find fast, or page through the full list.
Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.
Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior.
Example skill demonstrating Anthropic SKILL.md format. Load when learning to create skills or testing the OpenSkills loader.
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.
Control headless Chrome via Cloudflare Browser Rendering CDP WebSocket. Use for screenshots, page navigation, scraping, and video capture when browser automation is needed in a Cloudflare Workers environment. Requires CDP_SECRET env var and cdpUrl configured in browser.profiles.
Add Sentry v8 error tracking and performance monitoring to your project services. Use this skill when adding error handling, creating new controllers, instrumenting cron jobs, or tracking database performance. ALL ERRORS MUST BE CAPTURED TO SENTRY - no exceptions.
Frontend development guidelines for React/TypeScript applications. Modern patterns including Suspense, lazy loading, useSuspenseQuery, file organization with features directory, MUI v7 styling, TanStack Router, performance optimization, and TypeScript best practices. Use when creating components, pages, features, fetching data, styling, routing, or working with frontend code.
把用户提供的素材（网页 URL / PDF / DOCX / Markdown / 纯文本 / 截图 / 粘贴材料）编辑、设计成一篇美丽的、可离线打开和分享的单文件 HTML 网页文章。基于 reacticle 组件协议：不手写裸 HTML/CSS，而用语义组件 + 受主题约束的 Raw 自由层；按 source→规划→双确认→生成→终审→修复的小型 harness 流程推进，默认 100% 信息保留的长文。触发场景：把 URL/PDF/DOCX/文章做成网页文章 / 长文 / briefing / 解释文 / 视觉文章 / 教程 / 审阅复盘 / 方案分析，'render this as a beautiful web article / 把这篇做成网页文章 / 生成一篇可分享的 HTML 长文 / reacticle 文章'。只生成文章，不生成后台、表单、dashboard、产品原型或通用 Web App。
Test authenticated routes in the your project using cookie-based authentication. Use this skill when testing API endpoints, validating route functionality, or debugging authentication issues. Includes patterns for using test-auth-route.js and mock authentication.
Create and manage Claude Code skills following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns, file paths, content patterns), enforcement levels (block, suggest, warn), hook mechanisms (UserPromptSubmit, PreToolUse), session tracking, and the 500-line rule.
把一篇文章或口播稿，做成"看起来像视频"的点击驱动 16:9 网页演示，可选合成口播音频。流程：原始文章 → 一次产出口播稿 + outline 开发计划 → 用户一次对齐 5 件事（稿子 / outline / 主题 / 素材 / 开发模式）→ 网页开发（逐章 / 顺序 / 并行）→ 可选音频合成（provider-agnostic：内置 MiniMax mmx-cli + OpenAI TTS，可换 ElevenLabs / edge-tts / Azure / 自带 TTS）。outline 只规划节奏与信息密度，不规划动画 —— 动画由章节开发时按 PRINCIPLES + ANTI-AI 法则即时设计。每次点击推进口播稿的一个节拍，每一步独占整屏，进度条平时隐藏只在悬浮时出现。适用场景：用网页做视频（动态 PPT 但不像 PPT）、把口播稿 / 文章变成可交互的解说、为 B 站 / YouTube / 视频号录屏教程、做有电影感的产品 / talk demo。本 Skill 沉淀的是设计方法论 + 协作流程 —— 不绑定任何特定样式 / 字体 / 颜色 —— 因此能复用到任意主题与美学。
Comprehensive backend development guide for Node.js/Express/TypeScript microservices. Use when creating routes, controllers, services, repositories, middleware, or working with Express APIs, Prisma database access, Sentry error tracking, Zod validation, unifiedConfig, dependency injection, or async patterns. Covers layered architecture (routes → controllers → services → repositories), BaseController pattern, error handling, performance monitoring, testing strategies, and migration from legacy patterns.
面向本地知识库目录的检索和问答助手。核心流程：(1)分层索引导航 (2)遇到PDF/Excel时必须先读取references学习处理方法 (3)处理文件后再检索。按文件类型组合使用 grep、Read、pdfplumber、pandas 进行渐进式检索，避免整文件加载。用户问题涉及"从知识库目录回答问题/检索信息/查资料"时使用。
面向 GPT Image 2 的图像生成 / 编辑技能。可在 3 种环境下使用：(A) Garden 本地模式，通过 OpenAI 兼容接口直接出图并落盘；(B) Host-Native 模式，把本 Skill 当作提示词工程指引，把渲染好的 prompt 交给宿主 Agent 自带的图像工具出图；(C) Advisor 模式，宿主无任何图像工具时退化为高质量 prompt 顾问。涵盖 18 大类、80+ 个结构化模板，覆盖海报 / UI / 产品 / 信息图 / 学术图 / 技术架构图 / 漫画 / 头像 / 流程板 / 电影分镜 / IP 周边 / 编辑工作流等场景。
GEO-first SEO skill for Claude Code.
Build polished visual web artifacts with HTML/CSS/JavaScript/React: pages, dashboards, prototypes, slide decks, animations, UI mockups, and data visualizations. Use when the user wants a browser-rendered, interactive, or presentational front-end deliverable. Not for back-end, CLI, or non-visual coding tasks.
GEO-first SEO skill for Claude Code.
Full website GEO+SEO audit with parallel subagent delegation. Orchestrates a comprehensive Generative Engine Optimization audit across AI citability, platform analysis, technical infrastructure, content quality, and schema markup. Produces a composite GEO Score (0-100) with prioritized action plan.
Edit videos with coding agents
GEO-first SEO skill for Claude Code.
Generate a professional, client-facing GEO report combining all audit results into a single deliverable with scores, findings, and prioritized actions
Generate production-quality SVG+PNG technical diagrams from natural language.
AI citability scoring and optimization. Analyzes web page content to determine how likely AI systems (ChatGPT, Claude, Perplexity, Gemini) are to cite or quote passages from the page. Provides a citability score (0-100) with specific rewrite suggestions.
Content quality and E-E-A-T assessment for AI citability — evaluate experience, expertise, authoritativeness, trustworthiness, and content structure
A Claude skill that writes the accurate prompts for any AI tool. Zero tokens or credits wasted. Full context and memory retention
Generate a professional PDF report from a GEO audit using pandoc + Chrome headless. Converts GEO-AUDIT-REPORT.md into a styled, client-ready PDF with a cover page, color-coded score tables, severity-tagged findings, and a 90-day roadmap.
Pull the latest GEO-SEO skill updates from the upstream repository. Compares installed files against the latest release, shows what changed, and updates all skills, agents, scripts, and schema templates in place.
Project management skill system for Agents that uses GitHub Issues and Git worktrees for parallel agent execution.
AI crawler access analysis. Checks robots.txt, meta tags, and HTTP headers to determine which AI crawlers can access the site. Provides a complete access map and recommendations for maximizing AI visibility while maintaining appropriate control.
GEO-first SEO skill for Claude Code.
Create, analyze, proofread, and modify Office documents (.docx, .xlsx, .pptx) using the officecli CLI tool. Use when the user wants to create, inspect, check formatting, find issues, add charts, or modify Office documents.
Platform-specific AI search optimization — audit and optimize for Google AI Overviews, ChatGPT, Perplexity, Gemini, and Bing Copilot individually
Schema.org structured data audit and generation optimized for AI discoverability — detect, validate, and generate JSON-LD markup
Use when code changes are complete and ready for quality review, before committing or creating PRs. Triggers after implementing features, fixing bugs, or refactoring code. Also use when user asks to check code quality, analyze technical debt, review code smell, or mentions "fuck-u-code", "code quality", "shit mountain", "code review", "static analysis". Covers all 14 supported languages (Go, JS, TS, Python, Java, C, C++, Rust, C#, Lua, PHP, Ruby, Swift, Shell).
Brand mention and authority scanner for AI visibility. Analyzes brand presence across platforms that AI models rely on for entity recognition and citation decisions. Produces a Brand Authority Score (0-100) with platform-specific recommendations.
Technical SEO audit with GEO-specific checks — crawlability, indexability, security, performance, SSR, and AI crawler access
Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.
Analyzes and generates llms.txt files -- the emerging standard for helping AI systems understand website structure and content. Can validate existing llms.txt files or generate new ones from scratch by crawling the site.
The Open Standard for Generative UI
Write changelogs for Bifrost releases. Reads git history, bumps module versions following the core→framework→plugins→transport hierarchy, writes transports/changelog.md (enterprise-style) and per-module changelog.md files, and updates version files. Invoked with /changelog-writer or /changelog-writer <transport-version>.
Scan Bifrost HTTP controllers/handlers/integrations and validate OpenAPI API coverage, route methods/paths, parameters, request/response docs, and auth/security information. Use when asked to audit missing or incorrect APIs, compare controllers against docs/openapi, validate auth information, or fix API documentation drift. Invoked with /api-validator [scope] [--fix].
Pre-release safety audit for the Bifrost repo. Scans database migrations changed in a release for high-scale deadlock / lock-contention risks and for work that blocks application boot time, then produces a pass/warn/fail report with a concrete remediation plan. Invoked with /release-checklist [git-ref-range]. Built to grow - new checks are appended to the Checks Registry.
Investigate a GitHub issue by fetching details, analyzing the codebase, researching documentation, and presenting an actionable implementation plan with test guidance. Use when asked to investigate, analyze, triage, or plan work for a GitHub issue. Invoked with /investigate-issue <ISSUE_ID> or /investigate-issue (prompts for ID).
Write, update, and review Mintlify MDX documentation for Bifrost features. Explores the full codebase (UI, Go backend, config schema), validates config.json examples, places screenshot placeholders, and presents outlines for approval before writing. Invoked with /docs-writer <feature-name>, /docs-writer update <doc-path>, or /docs-writer review <doc-path>.
Reviews a PR or diff with multi-angle finders and adversarial verification, then reports a findings table, a merge/no-merge recommendation, required followups, and offers to create a follow-up PR. Use when the user types /review-pr [PR# | branch | path].