👀 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...

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

Use when a buyer just paid Spec72 (Lint/Catalog/Audit/Sprint) or needs the post-pay intake fields for https://spec72.dev/thanks/. Collect pack, repo URL, what breaks, handoff owner, email, tx/receipt — then point humans to Gumroad SKUs. Free pointer skill; Spec72 does the paid work.

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

Help any repository-capable AI agent spend less time rediscovering files and loading unnecessary context. Create concise project maps for code, content and operations, linked from existing agent instructions. For Codex, Claude Code, OpenClaw and other agents; documentation-only, no application changes.

Audit public software releases before installation using static artifacts, license checks, endpoint scans, and live distribution verification.

Use when GitHub access fails: fallback mirrors for git.

Use when the user wants an E-E-A-T, credibility, authorship, or trust-signal review using TrustGrowth evidence when connected or observable public/repository evidence otherwise.

Every call the team records is collected into the cadence layer each morning, scribed into a log entry, and — once a claim repeats — promoted into the context knowledge layer, as one reviewable pull request against your GTM repo. Triggers: "our call recordings never make it into the knowledge base", "turn our call transcripts into context", "keep our context updated from sales calls", "we relearn the same objection every quarter", "scribe yesterday's calls into the repo every morning", "replace the GitHub Action that summarizes our meetings". Cargo CDK, defineAgent, harnessSlug claudeCode, repository env, GitHub, Avoma, Gong, Fireflies, cadence, context. Skip when: you want one call summarized right now, which is a read against the recorder's own API and needs nothing deployed.

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...

元开（yotta-dev-mcp）—— 一个 stdio MCP server 提供 18 个确定性开发工具：repo_map（代码库地图）、system_model（系统模型与 .yotta/architecture.json 契约分层）、architecture_review（契约评审）、impact_analysis（变更影响锥）、verify_change（L0-L5 验证账本）、self_test（完整性检查与 seeded defect / mutation 反证）、run_adapter（显式运行 import-linter / dependency-cruiser / Repomix）、find_code（符号定位）、compress_output（长输出压缩）、review_code / review_diff（规则化评审）、scan_secrets（密钥脱敏扫描）、scan_dependencies（依赖与 typosquat 启发式）、check_publish_readiness（发布前守门）、run_checks（白名单检查，默认关闭执行）、scaffold_skill（技能脚手架，默认 dry-run）、workflow_state（.workflow 状态读取与安全追加）。Python 3.8+ 标准库、默认离线、默认只读、输出带文件行号与规则证据；缺工具或配置一律 UNKNOWN，不自动安装、不联网。

Create or edit a Europass CV in the Candidate XML format that the official europass.europa.eu editor imports (2020 format, HR-XML 3 based). Use when asked to produce, convert, fix or check a Europass CV/XML/PDF for import into Europass, or when an import 'shows only personal data' or is rejected as an old format.

Audit Git repositories and worktrees, preserve findings, and monitor scheduled audit health without deleting work.

Review demos for standards and delivery completeness

Use when your calendar is eating your week and you want to know exactly where the time goes, when planning recurring meetings for a team, before proposing a new recurring meeting, when someone says 'we should sync weekly' and you want data, or when auditing which meetings to kill — imports ICS calendar files, measures meeting hours per week/person/meeting-series (including double-bookings and fragmentation), computes focus-time destruction from meeting placement, scores the true cost of each series (hours × attendees × frequency), flags specific meetings to kill/shorten/make-async using explicit rules, and simulates the recovered hours before anyone has to argue about it.