liuchengxu
liuchengxu/dotfiles
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/liuchengxu/dotfiles --skill handoff命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Use when asked to review code or a design at any granularity — a pull request, an architecture/design proposal, a module, a file, or a whole codebase/repo — "review this PR", "review this repo", "audit this module", "challenge this design", "is this architecture sound", "adversarial review"; especially anything touching trust boundaries, signing/key flows, consensus rules, upgrade/governance logic, protocol APIs, or crate/module boundaries being locked in. DO NOT use for quick working-diff hygiene (use code-review) or prose/document editing passes (use doc-review).
Review a written document (markdown, design doc, runbook, README, etc.) for redundancy, inconsistency, clarity, and density. Apply the general rules first, then the type-specific addendum for the doc's genre. TRIGGER when: user asks to "review", "audit", "clean up", "tighten", "compress", or "check" a markdown / documentation file (including a proposal, pitch, or decision memo); user pastes a doc and asks for an editorial pass; user asks if a specific reviewer comment is "addressed"; about to DRAFT a design doc, proposal, planning doc, or RFC (apply Part C's authoring defaults, then self-review). DO NOT TRIGGER when: user wants substantive technical correctness review of a design, algorithm, or protocol (use adversarial-review), or review of a code diff or implementation (use code-review); writing a GitHub issue or PR body (use writing-issues-and-prs). Design docs and proposals may still trigger for structure, readability, and claim/ask calibration.
Render a markdown doc as a self-contained HTML view, written by hand for that document. TRIGGER when the user asks for an "html view", "make this readable", "render as html/page", "open as a page", or wants a shareable page of a markdown deliverable (review report, plan, ADR, research/design note). DO NOT TRIGGER to author new content (write the markdown first), for the todo board (use /todo), or to build interactive dashboards and tools (author those directly).
基于 SOC 职业分类
正在显示 SKILL.md
| name | handoff |
| description | Compact the current conversation into a handoff document for another agent to pick up. |
| argument-hint | What will the next session be used for? |
Write a handoff document summarising the current conversation so a fresh agent can continue the work. Save it to a path produced by mktemp -t handoff-XXXXXX.md (read the file before you write to it).
A handoff is durable context, not a chat pointer. Include cwd/repo, branch, commit or dirty state when relevant, exact next action, blockers, and the small set of terms/artifacts the next agent needs. References to other artifacts need a one-line label of what they contain; if access is uncertain, summarize the needed fact.
Label the status of every load-bearing fact: confirmed (verified this session), inferred (code-traced, not executed), attempted/failed (tried, with the failure), or not checked. Never flatten a qualified hypothesis into a conclusion — "probably X, not reproduced" stays qualified in the handoff.
Suggest the skills to be used, if any, by the next session.
Do not duplicate content already captured in other artifacts (PRDs, plans, ADRs, issues, commits, diffs). Reference them by path or URL instead.
If the user passed arguments, treat them as a description of what the next session will focus on and tailor the doc accordingly.