Agent skills directory

Techniques for creating deterministic terminal demo screencasts with VHS

VHS terminal recording best practices from Charmbracelet (formerly charmbracelet-vhs). This skill should be used when wr...

Generate professional terminal recordings from VHS tape files.

VIA Labs (ViaLabs) MPN encoding patterns, series identification, and handler guidance. Use when working with USB hub/PD...

Validate code readiness.

Vibe — reads your session and picks the perfect genre

Vibe Code Orchestrator (VCO) is a governed runtime entry that freezes requirements, plans XL-first execution, and enforc...

Vibe mode — a persistent, test-first build loop for local web apps and CLIs. The user describes a change; the loop tests...

Talos-class comprehensive code validation. Use for "validate code", "run vibe", "check quality", "security review", "arc...

Generate and deploy production-grade websites from a natural language description. Use when asked to "vibe a site", "vib...

Use when making a small, quick change — a bug fix, typo, minor feature, tweak, or anything the user calls "vibe coding"...

Build one feature end to end under the vibe contract — one intake round, locked acceptance tests as the only checkpoint,...

Delegate a coding task to Mistral Vibe and supervise the result via git diff. Trigger: /vibe <instruction>. Claude orche...

Scientific research engine with agentic tree search. Infinite loops until discovery, rigorous tracking, adversarial revi...

Vibe Code Orchestrator (VCO) is a governed runtime entry that freezes requirements, bounds execution, and enforces verif...

Browser automation for AI agents. Navigate pages, fill forms, click elements, take screenshots, and manage tabs — all th...

Natural language test automation methodology where tests are written as plain English instructions, leveraging AI agents...

Validates completed work against defined acceptance criteria. Use after completing a task that has specific success crit...

Full spec-driven workflow for adding a feature to an existing codebase with an AI coding agent. Triggers on "feature:" p...

Generates edge case, failure mode, and spec-driven test cases. Covers boundary values, nil inputs, concurrency, resource...

Standalone agentic architecture skill. Designs complete multi-agent AI systems from scratch — no other vibe-* skills req...

Generate AGENTS.md and AI configuration files for your project. Use when the user wants to create agent instructions, se...

Catches shortcuts and reward hacking — weakening or deleting tests to make them pass, hard-coding expected outputs, sile...

Architecture planning workflow for establishing code structure, patterns, and principles before any code is written. Run...

Brutal Vibe Audit for engineering quality. Auto-activates on: "code review", "technical audit", "engineering quality", "...

Build, run, troubleshoot, or extend the VibeWidget macOS SwiftUI app and widget. Use when Codex needs to work on a VibeW...

Comprehensive brainstorming workflow for turning any app idea into a clear, validated, buildable brief. Two paths: perso...

Build your MVP following the AGENTS.md plan. Use when the user wants to start building, implement features, or says "bui...

Translate consciousness navigation into user's native language. Use when need to match user's frequency (technical/poeti...

Scope change workflow for modifying, adding, or removing requirements at any point during a build. Triggers on "change:"...

Generates and maintains two changelog files from git tags, TASKS.md, DECISIONS.md, and feature folders. CHANGELOG.md at...

Run a comprehensive code quality check looking for common patterns that AI coding agents introduce.

Validate PRD quality and coherence before innovation phase using vibe-check MCP tool. Checks for requirement clarity, us...

Analyze which tools Claude uses most frequently. Use when user says "what tools do I use most", "tool usage stats", "ana...

Troubleshoot and diagnose vibe-check setup. Use when user says "check my vibe-check setup", "troubleshoot vibe-check", "...

Show recent Claude Code sessions and work history. Use when user says "what have I been working on", "recent work", "wha...

Search through Claude Code conversation history. Use when user says "search my conversations", "find when I talked about...

Get the current Claude Code session ID and log file path. Use when user says "get session id", "what is my session id",...

Create a public share link for the current Claude Code session. Use when user says "share session", "share this session"...

Query Claude Code usage statistics from the vibe-check database. Use when user says "claude stats", "usage stats", "my c...

Open the Vibe Check stats page in browser. Use when user says "vibe stats", "view my stats", "open stats", or "stats pag...

Safely integrates commits from parallel agent branches using sequential cherry-pick. Use after parallel work completes i...

Audit rapidly generated or AI-produced code for structural flaws, fragility, and production risks. Use when evaluating p...

Safe production cleanup and hardening for vibe-coded fullstack apps (Next.js, React, Node.js, etc.). Removes dead import...

Describe your idea, get a deployed product. All Craft Coder skills + brainstorm, validation, marketing. Use when: user w...

This skill should be used when users want professional SDLC practices with automated git workflows, intelligent code rev...

Help users build software using AI coding tools. Use when someone is using AI to generate code, building prototypes with...

LLM-readable code standards. Functions ≤50 lines, files ≤200 lines, nesting ≤3 levels. SRP, DRY, KISS, Early Return.

Comprehensive guide for AI-assisted vibe coding. Use when the user wants to build applications through natural language...

Methodology for effective AI-assisted software development. Use when helping users build software with AI coding assista...

Turn an idea into a functional, demo-ready prototype using AI-assisted “vibe coding” (timeboxed build loop, prompt pack,...

Transform an AI agent into a tasteful, disciplined development partner. Not just a code generator, but a collaborator wi...

Use this when an approved Spec that passes the installed authoritative spec-intake validator must be turned into stable...

Inject UX principle context into AI coding sessions before generating components and UI flows.

Vibe Coding 架构选型与项目启动方法论。在写任何一行代码之前，先用结构化思维锁定架构，再把架构翻译成 Prompt，最后才进入编码阶段。 TRIGGER when: 开始新项目、AI编程、Vibe Coding、选架构、项目规划、...

教非技术背景的人看懂技术架构、做好技术选型——把"只会照搬话术的小白"练成"能看穿方案好坏的人"。 当用户问"该用什么技术/框架"、"帮我选技术栈"、"AI 给的方案我看不懂"、"这几个方案怎么选"， 或者需要把 demo 做成更正经的东西...

Skill abrangente sobre Vibe Coding, GitHub Copilot Agent Mode e metodologia de colaboração com IA. Use para entender os...

质检 Agent：检查 vibe-coding-kit 其他 Skill 的产出物是否符合治理规范。 当用户说"检查一下产出"、"帮我看看合不合规"、"质检"、"验证 PRD"、"检查项目说明书"， 或在任何 Skill 完成产出后，使用此...

**VIBE CODING ORCHESTRATOR v5.0** - 16개 AI 스킬 자동 조율 시스템. 비개발자도 프로급 코딩. 바이브 코딩에서 프로덕션까지. 4단계 성숙도 모델. 2025 현대 도구 통합.

一个"访谈式"的需求 Agent：通过一问一答 + 在岔路口给建议，把一个说不清需求的人，带到一份 AI 能直接照着开工的 PRD。 当用户说"我想做个 XX 但不知道怎么跟 AI 说"、"帮我理需求"、"帮我写个 PRD"、"我有个想法，...

把需求、原始 PRD、竞品分析、零散笔记或模糊产品想法提炼成可直接发给 Claude Code、Codex 或其他编码 Agent 的精简中文 Markdown PRD。触发：用户说“帮我写一个用来vibe coding的PRD”、要求整理...

把验证过的 Vibe Coding demo，做成能长期运行、给别人用的正式系统。 当用户说"想上线"、"怎么部署"、"这个 demo 想做成正式的"、"要注意安全吗"、"怎么测试我的项目"， 或者准备把代码开源/公开发布时，使用此 Ski...

Vibe Coding（用 AI 写代码）项目的第一步：把模糊的想法，变成 AI 能精准落地、不会跑偏的需求。 当用户说"我想做一个 XX"、"帮我用 AI 做个 demo"、"我有个想法想验证"、"帮我跟 AI 对齐需求"， 或者描述了一...

Use when an AI-built, Vibe Coding, or inherited software project cannot start, build, test, validate, run locally, pass...

Detect whether a vibe-coded or AI-generated software project is maintainable engineering or unmaintainable shit. Use for...

Vibe Coding（用 AI 写代码）开发过程中的避坑与自救——真正翻车大多发生在"开工后"。 当用户说"AI 越改越乱"、"demo 改坏了退不回去"、"AI 老忘记之前说的"、"功能越加越多很乱"、 "AI 说做好了但其实没用"，或...

AI skill that teaches while coding through MCQs, TDD enforcement, and systematic debugging. Activate on any code request...

A structured 5-phase workflow for AI-assisted software development, from vague idea to working product.

AI outputs YAML descriptors instead of code, CLI executes deterministically for 100% auditable behavior with zero slop....

Audits tests for concurrency safety — race conditions, shared mock state, cleanup ordering. Use when writing tests that...

Tracks and reports token usage and dollar cost across every level of a vibe-* project — per task, per session, per featu...

Enforces tiered test coverage standards with three dimensions — line coverage by tier, spec-to-test traceability, and sp...

Judges whether a user's input suits the Vibe Creating style of video-prompt writing, and when it does, distills single-s...

Extracts and records architectural decisions from diffs, conversation context, and explicit choices. Supports automatic...

Delegate a coding task to the Mistral Vibe CLI (`vibe`) as a background implementer, then review its diff and land it yo...

Prepares a vibe-* project for deployment to 7 platforms: Railway, Render, Fly.io, Heroku, Vercel, Netlify, GitHub Pages....

Frontend design workflow that produces non-generic, editorial-quality UI. Immediately invokes the frontend-design skill...

Generates a DESIGN.md file for any website URL or fetches a pre-built one from the awesome-design-md collection (55+ sit...

Create stunning, modern web designs with aurora effects, glassmorphism, neon glows, and sophisticated aesthetics. Perfec...

Challenges a recommendation, design, or large change across 5 dimensions (consistency, completeness, actionability, alig...

Performs a fast 6-point quality check for technical documents (specs, design docs, READMEs). Use after editing any speci...

Environment health check and auto-remediation for vibe-* projects. Checks node_modules vs package.json drift, nested .gi...

Generates complete documentation for vibe-* projects — inline code docs, README.md, CHANGELOG.md, API reference, and com...

Generates and runs full end-to-end UI tests using Playwright against a live URL. Auto-installs Playwright and Chromium i...

Vibe creates reality, not describes it. Use when need to engineer specific emergence conditions through language frequen...

Full spec-driven workflow for diagnosing and fixing a bug with an AI coding agent. Triggers on "bug:" prefix, "I have a...

Refuses "flaky" as a diagnosis. Turns an intermittent failure into a reproduction by isolating it from the environment,...

独立开发者 Web/SaaS 项目专属 Vibe Coding 全流程。Invoke when starting a new web product project to run a complete 14-skill pipeline f...

Generates fuzz test scaffolding for parsers handling external input (YAML, JSON, config files, user input). Seeds corpus...

Assesses production readiness or audits a codebase against its specs. Supports quick static mode, deep 17-dimension audi...

Closes a large backlog of findings (a gap analysis, an audit, or 10+ bugs) in prioritized waves. Loops through triage, d...

Implements snapshot/golden file tests with temporal normalization so tests don't break daily. Use when implementing test...

Independent document review for the vibe-* framework, on the elephant-goldfish model. The agent that wrote a document (t...

Dual-layer dependency graph for vibe-* projects. No external packages. DEPENDENCY_GRAPH.json maps file-level relationshi...

Generates complete handoff packages for every transition scenario in a vibe-* project. Five modes: client (project compl...