Monitors your working session and detects when you've drifted from your stated task into unrelated changes. The coding equivalent of a GPS "recalculating" —...
Delegate various coding tasks to Claude Code. Use this skill when you need assistance with code generation, bug fixing, feature implementation, code review,...
Metacognitive pre-execution analysis — teaches the agent to see what ISN'T there before acting on what IS. Zero-cost reasoning skill that reduces wasted turn...
Token-efficient Claude Code workflow. Other skills burn tokens polling tmux every 30s — this one uses completion callbacks and only checks when notified. Obs...
Use the local Codex CLI through mcporter and codex-mcp-server for real coding work in the current project. Use when the user asks to build features, fix bugs...
Control OpenCode directly via the Agent Client Protocol (ACP). Start sessions, send prompts, resume conversations, and manage OpenCode updates. Includes auto...
Install, authenticate, and use Claude Code CLI as a native coding tool for any OpenClaw agent system.
Use Cursor Agent for coding tasks via two paths: (1) Local CLI — run Cursor Agent directly from terminal for fast, general-purpose coding in any project; (2)...
Git archaeology engine that reconstructs the WHY behind code — not what changed, but what pressures, failures, and pivots shaped the codebase into its curren...
Coordinate and manage complex AI-driven software development workflows using a multi-agent architecture. Analyze, design, debug, and improve code projects with intelligent agents leveraging a unified
A comprehensive skill for using the Cursor CLI agent for various software engineering tasks (updated for 2026 features, includes tmux automation guide).
You are an expert in PR quality, enforcing manageable PR sizes. ## PR Size Limits | Metric | Warning | Block | |--------|---------|-------| | Files Changed | > 15 | > 30 | | Lines Changed | > 400 |
规范的 Git 开发流程：分支管理 → 开发 → PR → Review → 合并。 支持新 feature 开发和 bug 修复，强制禁止直接推送到 main。 触发于 "开发", "实现", "新功
Unified TDD skill with three input modes — from spec, from task, or from description. Enforces test-first development using repository patterns, with proptes...
Framework pengembangan perangkat lunak lengkap untuk tim ClawGator. Brainstorming, planning, eksekusi sistematis, TDD, debugging, code review, dan git worktrees. Trigger otomatis sebelum memulai proye
Four-phase debugging framework that ensures root cause investigation before attempting fixes. Never jump to solutions.
Asistente de programación especializado. Analiza código, encuentra bugs, sugiere optimizaciones, refactoriza y genera documentación automáticamente.
CodeFlicker CLI 编程助手 - 快手员工专用的 AI 代码开发工具，支持更多模型和免费用量
Backup and restore OpenClaw workspace SOUL files with versioning, validation, and sanitized openclaw.json handling.
Manages the full deploy cycle — build validation, GitHub push, Vercel deployment, and health checks
Interface with the SanctifAI Human-in-the-Loop API to create tasks and wait for human responses. Use when the user needs to delegate a decision, data entry, or verification task to a human via the San
Systematically improve code through disciplined analysis, targeted mutations, verification, scoring, and logging to iteratively enhance quality and design.
代码审查、重构建议、安全漏洞检查、命名规范、复杂度分析、注释文档生成. Use when you need code reviewer pro capabilities. Triggers on: code reviewer pro.
# SYSTEM PROMPT: Code Recon # Author: Scott M. # Goal: Comprehensive structural, logical, and maturity analysis of source code. --- ## 🛠 DOCUMENTATION & META-DATA * **Version:** 2.7 * **Primary AI