--- name: claude-md-master description: Master skill for CLAUDE.md lifecycle - create, update, improve with repo-verified content and multi-module support. Use when creating or updating CLAUDE.md file
Guide creation of AI-friendly project structures with progressive disclosure indexing, modular architecture, and intent-oriented code. Use when starting a ne...
Identifies vestigial code — not just unused imports, but dead feature branches still compiled, zombie configurations nobody reads, orphaned tests that valida...
Run one Better Ralph iteration: pick next incomplete PRD story by priority, implement it, run checks, commit, mark passed, and append progress, using only st...
Autonomous programming mode for openclaw.ai. Use this skill whenever a user requests any code change, feature addition, refactor, bug fix, or project task —...
Get Shit Done - Full project planning and execution workflow. Handles project initialization with deep context gathering, automated research, roadmap creation, phase planning, and execution with verif
Ensures alignment between user and Claude during feature/spec planning through a structured interview process. Use this skill when the user invokes /plan-int...
Multi-agent orchestration plugin for OpenCode. Use when the user wants to install, configure, or operate oh-my-opencode — including agent delegation, ultrawork mode, Prometheus planning, background
Generate a deep, code-first project wiki and VitePress documentation site (DeepWiki-style) for a repository. Use when asked to create a complete wiki/manual...
Analyzes web performance using Chrome DevTools MCP. Measures Core Web Vitals (FCP, LCP, TBT, CLS, Speed Index), identifies render-blocking resources, network dependency chains, layout shifts, caching
Transform raw brain dumps (dictated freestyle) into structured implementation artifacts. Use when user has messy ideas, scattered thoughts, or dictated strea...
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative
Autonomous spec-driven development with OpenSpec CLI and Claude Code. You orchestrate (draft artifacts, make judgment calls, ship PRs) while Claude Code revi...
CRITICAL - Guide for using Ex-Coder Autonomy CLI with OpenRouter/Groq models. Includes agent modes (build/plan), snapshot system, session management, LSP int...
Provides a comprehensive methodology to optimize productivity and tool use across multiple AI coding assistants through assessment, selection, context engine...
PIV workflow orchestrator - Plan, Implement, Validate loop for systematic multi-phase software development. Use when building features phase-by-phase with PRPs, automated validation loops, or multi-ag
Install, authenticate, and use Claude Code CLI as a native coding tool for any OpenClaw agent system.
# Ultrathinker You are an expert software developer and deep reasoner. You combine rigorous analytical thinking with production-quality implementation. You never over-engineer—you build exactly wha
Build autonomous AI agents with Claude Agent SDK. Structured outputs guarantee JSON schema validation, with plugins system and hooks for event-driven workflows. Prevents 14 documented errors. Use whe
Integrate Outlit SDK for customer context for agents. Triggers when users need to add Outlit to any web framework (React, Next.js, Vue, Nuxt, Svelte, Angular...
Delegate coding tasks to Cursor Agent CLI. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large...
The complete operating system for building software with AI. From first prompt to production deployment — prompting frameworks, architecture patterns, testin...
**Give your AI the ability to understand meaning, not just match keywords.**
OpenCode AI - AI-driven code editor/IDE (CLI/TUI version of Cursor/Windsurf). Use when: (1) AI-assisted coding tasks, (2) Code refactoring with AI, (3) GitHu...