👀 PR Review AI Skills

Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.

Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.

Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.

Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks

Code refactoring patterns and techniques for improving code quality without changing behavior. Use for cleaning up legacy code, reducing complexity, or impro...

Delegate coding tasks to external agents (Claude Code, Codex) via ACP. Triggers on phrases like "改代码", "修bug", "重构", "review", "实现功能", "写测试", "优化", "fix", "r...

Deep-dive analysis of GitHub projects. Use when the user mentions a GitHub repo/project name and wants to understand it — triggered by phrases like "帮我看看这个项目...

Git-based version control for OpenClaw system configuration changes. Provides two core capabilities: (1) SAVE - Create a checkpoint before sensitive operatio...

Build and query AST summaries + call graphs for codebases. Use when exploring a project's structure, finding function definitions, tracing call chains, under...

Zero-regression bug fix workflow: triage → reproduce → root cause → impact analysis → fix → verify → knowledge deposit → self-reflect. Use when: - Feature br...

交付规格覆盖审计器。当一次 Coding Agent 开发任务完成(或即将宣布完成)时, 从会话记录(CC JSONL / OpenClaw trajectory)确定性抽取「做了什么、改了哪些文件、 验证了几次」的原始证据,再对照规格清单逐条判定覆盖情况——主目标之外的 接口兼容、状态一致、错误处理、回归风险等互依规格最容易被"逐条打勾式交付"漏掉。 先追问规格、再抽证据、后做语义判定,输出覆盖矩阵与反例场景。 触发词: 交付审计, 规格覆盖, 交付前检查, 这次改动覆盖了哪些需求, 完成了吗, 交付质量, spec coverage, delivery audit, coverage check, task complete audit, 交付核对, 需求覆盖, 上线前核对, 改动核对。 激活条件: 需要有明确的"一次开发任务/一轮改动"语境(用户给出任务描述、 会话记录路径或仓库路径);纯代码问答、与交付无关的闲聊不触发。 NOT for: 静态代码质量评分(用 code-review-ProMax)、Skill 质量评审 (用 skill-review-pro)、上下文预算分析(用 context-budget-analyzer)、 全仓库架构文档生成(用 project-doc-analyst)。

Trigger Claude Code development tasks in observable tmux sessions with stable startup, progress visibility, and completion callback to OpenClaw. Use when use...

Reference tool for devtools — covers intro, quickstart, patterns and more. Quick lookup for Db Explorer concepts, best practices, and implementation patterns.

Verify Rust with Verus, check proof repairs, and run cached Z3 queries with Sail. Use when cargo verus verify is slow, when developing Verus proofs, or when giving coding agents SMT-LIB solver access through the CLI or MCP.

Refactor an existing OpenClaw docs page with source-audited preservation, restructuring, and verification.

GitHub CLI for issues, PRs, CI/check logs, comments, reviews, releases, repos, and gh api queries.

Hand coding and research jobs to Claude Code or Codex on the owner's own plans through the local Huntaway Pipe, watch them, and review an exact commit with models from two companies.

Review systemic defects, unused code and ineffective gates

Build playable browser games (2D canvas or 3D Three.js) from natural language, with an automated screenshot verification loop the agent runs before claiming the game works — no unverifiable "should look fine" claims. Persists games in a stable workspace (games/<slug>/, not /tmp), iterates via targeted edits, publishes to https://jerithai.com/games/<slug>/ via the existing nginx + Cloudflare tunnel. Reuses the full 3D pattern library from the original build-game skill and adds 2D canvas, genre-appropriate engine choice, and verify-before-deliver as a hard gate.

Deterministic code-verification guard for AI coding agents. Runs syntax, type, lint and test checks before and after code changes, and decides PASS / FAIL / REGRESSION / UNVERIFIED purely by script exit codes. The agent may only quote the verdict, never overrule it. Use when the user asks to modify code, implement features, fix bugs, or verify change reliability (trigger phrases - verify this, run the tests, regression check, confirm it works, 验证一下, 跑测试, 回归检查, 确认没问题). Not for general code review or security audits.

项目发布前检查工具。代码质量检查、API测试、部署检查清单、版本管理、上线前审查、回归测试。Pre-publish quality checker for code, API, deployment, versioning, launch review, regression testing. 发布检查、上线审查...

Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.

Verify score facts, arrange both-hand piano fingerings, and export reviewable results

龙虾好友协议技能：基于P2P加密通讯的社交好友管理系统，提供好友发现、关系管理、安全通信和社交图谱功能。