AI Agent Skills

Two Claude Code skills: 10-80-10 token discipline for Fable 5, plus GPT-5.5 (Codex) as an independent reviewer. Agent-driven, reversible installer.

A universal orchestration workbench for macOS. Seamlessly mix AI models (Codex, Claude) with traditional CLI tools (git, npm) via static DAG pipelines or dynamic self-he…

Use when checking skill metadata, references or repository boundaries, or preparing an explicitly requested skills release.

Audit the choices an implementing agent made, not its diff — a pure decision audit that traces the session's history into a choices ledger, changes no code, and never bl…

Eval and improve a skill against golden cases — run the target skill blind in a fresh, context-free subagent on each example input, grade the artifact against the expect…

Conduct a retrospective on a coding session.

Free open-source Multilogin/Incogniton/Kameleo alternative for fingerprint spoofing (Canvas/WebGL/User-Agent). Perfect for Selenium/Playwright/Puppeteer automation, web…

Personal Claude Code configuration versioned inside ~/.claude — agents, skills, hooks, settings, and statusline (reference, not a starter template)

node-based WebGL design tool

Use when the user wants to create/generate/scaffold a new Spring Boot project (Maven or Gradle, REST API / Web App / Spring Boot + Angular full stack). Derives progen CL…

Vue hooks for TanStack AI. ALWAYS use when writing code importing \"@tanstack/ai-vue\". Consult for debugging, best practices, or modifying @tanstack/ai-vue, tanstack/ai…

Self-review checklist for the coding agent to run before dispatching a reviewer. Checks CONVENTIONS.md compliance, Boy Scout Rule, test coverage, types, and SOLID. Produ…

Build → verify artifact → deploy → wait → smoke deployment pipeline. Platform-agnostic (MCP or CLI), with configurable timeout, retry with exponential backoff, and integ…

Test-driven development with red-green-refactor loop using vertical slices. Use for features (epic tasks) or bugs (specs/bugs/BUG-*.md).

当用户要写出高质量 Goal Prompt 和交付后继续进化用的 Loop Prompt，把模糊、战略性、多步骤、证据不足、持续/自动化或容易跑偏的请求整理成可执行、可验证、可暂停且带时间参数的目标契约时使用。适用于写 goal、优化任务提示词、明确 done/success criteria、deep research 后定战略、大改…

Open source AI platform for rapid development of advanced AI and AGI pipelines.