vibesec-skill
A skill that helps Claude write secure web applications and runs security scans or audits, applying bug bounty experience to catch vulnerabilities before code reaches production.
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 →.
A skill that helps Claude write secure web applications and runs security scans or audits, applying bug bounty experience to catch vulnerabilities before code reaches production.
通用 Web API 采集与前端签名问题的方法论。只要任务涉及抓接口或写 Node/Python 协议程序、sign/token/动态 Cookie/自定义头、 本地生成的值服务端不认、HTTP 200 却是业务错误或空数据、浏览器能过本地不过、SDK…
Kimi K2 CLI + tmux multi-agent parallel dev platform with sengoku military hierarchy
Check work for adherance with architecture and run checks
Deploys and operates a self-hosted OpenTag setup for Slack, pairing a local runner with a GitHub-connected Control Plane so an engineering channel gets an AI teammate that stays reachable even when its computer is offline.
Use when packaging AAAI code, data, multimedia appendices, technical appendices, reproducibility evidence, and post-acceptance…
Update people profiles in 05-knowledge/people/ with new information from brief data, meetings, or Slack
卡住时手动激活 NoPUA 清醒模式——识别失败模式,以道法自然引导自己停→观→转→行→悟,而非靠恐惧硬撑。
An AI agent skill that runs pre-submission checks on your iOS/macOS project to catch common mistakes that lead to App Store rejection.
Interactive quiz tutor for Obsidian StudyVault learning. Use when the user wants to: (1) Take a diagnostic assessment of their…
Interactively build EasyPaper metadata from a research-materials folder using Claude Code's file-investigation tools. Output is…
A skill for building, testing, validating, packaging, and publishing plugins for the OpenPets desktop pet companion using its plugin SDK, manifest, and permissions.
This skill MUST be used whenever the task involves adding, installing, or upgrading an npm package/library/dependency in this…
A highly advanced AI agent that functions as a master orchestrator for complex, multi-agent tasks. It analyzes project…
Ask a question about the current project's codebase via the repobrain knowledge hub. / 通过 repobrain 知识库询问当前项目代码。
Develops and visually tests UI components in isolation outside of the full application.
Security auditor for AI agent configurations Scans Claude Code setups for hardcoded secrets, permission misconfigs, hook injection, MCP server risks, and agent prompt injection vectors. Available as CLI, GitHub Action, and GitHub App integration.
Expert specialist in Animated Component Libraries implementation, patterns, and best practices.
You are the Analysis Agent for NanoResearch. Your job is to analyze experiment results and produce structured findings.
A personal collection of portable Codex agent skills. It includes a guardrail skill for safer Codex coding work and a pre-launch audit skill for vibe coding projects before shipping or committing.
把 Excel 工作表导出为 CSV,默认 utf-8-sig 编码解决中文乱码,支持多工作表批量导出。当用户提到 Excel 转 CSV、表格转文本、CSV 乱码时使用。
Lane escalate (opus, high effort). Only when evidence warrants it: the lane below failed repeatedly, checks keep failing,…
Turns your coding assistant into a security scanner that checks your codebase for vulnerabilities such as business logic flaws, insecure file uploads, GraphQL injection and hardcoded secrets, without any third-party tools. Works with Claude Code, Codex, Cursor and other agent-skill assistants.
Recommend curated prompts from a 10,000+ real-world image generation prompt library. Works with ANY AI image model — Nano Banana…
A command-line tool for interacting with the X (formerly Twitter) API, supporting both OAuth 1.0a and OAuth 2.0 authentication.
Turn a known bug into a tight, red-capable reproducer, then prove the reproducer locks that bug with a reversal negative control…
Use this agent when the user mentions accessibility checking, App Store submission, code review, or WCAG compliance.
Mine the current session for knowledge worth sharing — identify learnings, present them for approval, and propose each approved…
Creates and edits Word, PDF and Excel documents, turns photos into animated GIF stickers with captions, and generates speech, music, video and images, so you can produce these files without building them by hand.
INVOKE THIS SKILL when building ANY Deep Agents application. Covers create_deep_agent(), harness architecture, SKILL.md format,…
Orchestration patterns learned from experience. Review at startup and before heartbeat responses.
Implement tasks from an OpenSpec change (Experimental)
A skill for X/Twitter operations covering topic selection, tweets and long posts, account diagnosis, growth and conversion. It is built on named creators' methods and corrected against the author's own account data.
Convert files and URLs to Markdown. Supports PDF, DOCX, PPTX, XLSX, HTML, EPUB, CSV, JSON, GitHub URLs, images, audio, ZIP, and…
Expert in Akka.NET architecture, actor systems, and distributed computing patterns. Specializes in analyzing actor lifecycle…
A Claude Code skill for building, testing, and driving iOS apps in the Simulator. It runs Xcode builds, launches apps, and taps, types, and swipes through the UI using accessibility labels, with token-efficient scripts.
Use when a Hermes agent needs to evaluate agent behavior, run Autocontext scenarios, inspect Hermes curator state, export…
Run the slides-grab design gate before export.
This repository is a Virtual Monolithic Repository (VMR) which includes all the source code and infrastructure needed to build the .NET SDK.
Explain machine learning, deep learning, generative AI, LLMs, AI agents, and speech modeling in a Hung-Yi Lee-inspired teaching…
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Build a macOS/iOS Shortcut end-to-end via the shortcut-builder agent. Pass a natural-language brief — e.g.…
Sends one question to several AI search sites at once and returns their answers together, so you stop querying each site by hand. Useful for tracking trends, public opinion and hot topics, and for pulling content from links you specify.
Edit, resize, animate and study image ads with GooseWorks in this chat. New static or image ads go to the make-static-ads skill…
<!-- Based on Anthropic's code-simplifier subagent:…
Reaches Jira and Confluence for issues, pages and project metadata.
Fetches, filters and analyzes real-time news and papers from many tech, finance and AI sources such as Hacker News, GitHub, arXiv and Hugging Face Papers. Built for Claude Code users who want a current digest of technology and AI news.
Trigger when: (1) User wants to create an educational/explainer video, (2) User has a vague concept they want visualized, (3)…
Reviews code, tests, and docs that an AI agent has just written or changed, checking for common AI mistakes before you commit or merge. Covers general code quality, tests, documentation, WordPress, and WooCommerce.
Audit a repo's agent context — CLAUDE.md files, codebase docs, skills, and tool/MCP designs — against Anthropic's Claude 5…
Review code changes for quality, security, and best practices. Proactively use this after code modifications.
Analyzes your project's dependencies and checks architecture health.
Syncs and audits AI coding setups for Claude Code, Cursor, and Codex, with skills for adding CLI commands, writing Vitest tests, adding LLM providers, and saving persistent learnings.
毛泽东思维框架:以《毛泽东选集》五卷为核心,提炼毛泽东分析问题、制定战略、组织行动的认知操作系统。 核心来源:《矛盾论》《实践论》《论持久战》《中国社会各阶级的分析》《星星之火可以燎原》《论联合政府》《关于正确处理人民内部矛盾的问题》等。…
A skill that searches flights, hotels, attractions, concerts and travel deals from natural language requests. It connects to the Fliggy service for real-time search and booking of hotels, flights, cruises, visas and car rentals.
Comprehensive guide for developing WebGPU-enabled Three.js applications using TSL (Three.js Shading Language). Covers WebGPU…
You are a **code auditor** for experienced developers. Your job is not to explain — it's to surface what matters architecturally.…
Hit the Cloudflare REST API for bulk, fleet, and operations wrangler can't do
Hands a task to another agent and gates the result behind peer review. Fires when you ask to hand off work, sync Codex and Cursor, or open the dashboard.
Analyze Swift Package Manager dependencies, package plugins, module variants, and CI-oriented build overhead that slow Xcode…
Use this subagent to diagnose a CORAL run that's misbehaving — agents restarting, every eval failing, the score plateaued, or "is…
Runtime testing skills for Claude Code that let an agent verify web and desktop apps as they actually run. They cover test-driven development against the live app, sweeping for dead buttons, diagnosing broken UI, and driving Electron or Tauri apps.
Gives text-only coding agents the ability to see: image question answering, OCR on long screenshots, restoring frontend UI from images, and GUI automation. It ships as local vision CLIs plus a skill, with optional integration for several coding agents.
Generate Guizang-style material illustrations, labeled explanatory visuals, material-styled chart illustrations, and data-first…
A research agent that searches X/Twitter for real-time perspectives, developer discussions, product feedback, and expert opinions. It can also filter and monitor posts from the terminal.
Build presentation plans for PPT / slides / decks through a conversation-first workflow, then propose multiple visual directions…
Design and build expressive 3D scenes, explainers and interactive models with grounded subject knowledge. Use for 3D creation or…
Independently written prompt templates for building AI coding agents, inspired by patterns observed in Claude Code codebase. System prompts, tool prompts, agent prompts, memory management, and multi-agent coordination.
Design and build a high-converting questionnaire-style onboarding flow for your app, modelled on proven conversion patterns from…
Teaches Claude Code to benchmark Clojure code and measure execution time using the criterium library, covering its bench macro and plans, JIT warmup and GC isolation for statistically sound results.
把一条视频重建成「只有画面和声音」的干净文件——**源片的元数据一概不搬**: GPS、设备型号、账号 ID、创建时间、章节、GoPro 的遥测轨,全部留在原地。 走的是白名单而不是黑名单:不列要删什么,只说带什么过去(画面一条流、声音一条流),…
Gearboy is an accurate, cross-platform Game Boy / Game Boy Color / Super Game Boy emulator written in C++ that runs on Windows, macOS, Linux, BSD and RetroArch, with an embedded MCP server for AI debugging and development.
Three modes for CS-conference papers (CVPR/ICCV/ECCV vision, ACL/EMNLP/NAACL NLP, ICLR/NeurIPS/ICML/AAAI ML). DIRECT-EDIT mode…
Runs multi-source research for Claude Code and produces structured reports with citation tracking and source credibility scoring. Searches across several providers and checks sources before writing the report.
A unified terminal tool that indexes and searches your local coding agent history from Claude Code, Codex, Gemini, Cursor, Aider and others, so past sessions can be found quickly.
Use when captions, subtitles, or the spoken text of a YouTube video is needed — even if not explicitly requested: pasted video…
Provides skills for project discovery, idea intake, session control, and event-driven notifications through the local drclaw CLI, plus research help such as literature reviews and paper analysis. Aimed at researchers working with Claude Code.
Polish and improve English writing for academic/research papers, especially in CS and ML fields. Use this skill whenever the user…
Edits CapCut and JianYing video projects from the terminal or an LLM agent, covering subtitles, timing, speed, volume, templates, animations, and cutting long videos into shorts. The result opens in CapCut with every track still editable.
分析台股 / 台股ETF / 台指期選擇權 / 美股 / 加密貨幣 / 外匯的交易紀錄 (CSV / JSON / Excel),用統計學判斷使用者的獲利是「可重複的優勢」還是 「運氣 + 倖存者偏差(賭博)」,不適合長期投資會明確勸退。內建反詐工具:…
A collection of reusable AI agent skills for Unity workflows. Compatible with Claude Code, GitHub Copilot, Cursor, Cline, and 50+ other agents.
AWS API Gateway for REST and HTTP API management. Use when creating APIs, configuring integrations, setting up authorization,…
A Traditional Chinese rewriting skill that removes AI-sounding writing traces from text, corrects mainland-style wording and half-width punctuation, and makes copy read like it was written by a person.
Inspect LLM torch profiler traces at forward-pass, layer, and kernel level. Use when you need layer timings, anchor-kernel…
Gives AI agents natural language access to crypto markets, letting them search tokens, execute trades, track wallets, monitor trading signals and interact with DeFi protocols across chains.
Bug → spec protocol. When a bug is found or a test fails, trace the cause, decide whether a new §V invariant would catch…
Shared skills that the pstack plugin does not cover: test audits (test-audit, adapted from openclaw's), screenshot walkthroughs and video transcripts, and pstack setup, sync and skill-drift audits (sync-pstack).