Runs a budget-aware Agent Health audit for Codex, Claude Code, agent instructions, hooks/MCP, verifier surfaces, and AI maintainability. Use when users ask 检查claude/检查codex/配置检查/健康度 or report agents ignoring instructions, missing validation, or code becoming hard to maintain. Not for debugging code or reviewing PRs.
1 skill · 3 agents
Reviews code diffs, PRs, issue queues, release readiness, commits, pushes, publishing, and project audits. Use when users ask review/看看代码/合并前/看看issue/PR/release/push or to implement an approved plan, with safety gates for dirty and untracked worktrees. Not for exploring ideas, debugging root causes, or prose review.
1 skill · 2 agents
Produces distinctive, production-grade UI for pages, components, visual interfaces, typography, and screenshot-driven polish. Use when users ask 设计/做页面/做组件/UI/前端/截图 or say a screen is ugly, unclear, inconsistent, or visually wrong. Not for backend logic or data pipelines.
1 skill
Finds root cause before applying fixes for errors, crashes, regressions, failing tests, broken behavior, and screenshot-reported defects. Use when users ask 排查/报错/崩溃/不工作/回归/判断为什么报错, or say something used to work and now fails. Not for code review or new features.
1 skill
Runs a six-phase research workflow that turns unfamiliar domains, source bundles, or collected material into publish-ready output. Use when users ask 学习一下/深入研究/研究一下/整理成文章/deep dive/compile sources or need one coherent reference from many inputs. Not for quick lookups or single-file reads.
1 skill
Fetches URLs and PDFs as clean Markdown for reading, quoting, citation, and downstream work, including paywalls, JS-heavy pages, X/Twitter, and Chinese platforms. Use when users ask 看这个链接/读一下/抓取网页/read this/check this URL/fetch this page. Not for local text files already in the repo.
1 skill