跳到正文
cccskills
免费在 GitHub 公开

handoff

Compact the current conversation into a portable handoff document, with an optional live clarification path for compatible Codex tasks.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(2)

  • SKILL.md2.0 KB
  • agents/openai.yaml141 B

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Write a handoff document summarising the current conversation so a fresh agent can continue the work. Save to the temporary directory of the user's OS ($TMPDIR, else /tmp; %TEMP% on Windows) - not the current workspace.

Include a "suggested skills" section in the document, naming which skills the next agent should call the Skill tool for.

When the facts are available, include a compact Continuation section with:

  • the exact source task ID (omit it rather than guessing),
  • the current execution owner (source, receiver, or unassigned),
  • the repository, branch, fixed point, and worktree state when relevant.

If the source and receiving sessions are existing Codex App tasks working in the same directory, suggest /codex-task-messenger. The receiver may use it to ask the source task one concrete question when the answer is not settled by the handoff or its referenced artifacts. A Messenger reply supplements the handoff; it does not replace the handoff or expand the user's authorization.

Before editing a shared directory, the receiver should confirm execution ownership once if the handoff leaves it unclear. Read-only clarification does not require an ownership transfer. If the source task is unavailable or Messenger is incompatible with the destination, continue from the handoff and referenced artifacts, surfacing only a real blocker.

Do not duplicate content already captured in other artifacts (specs, plans, ADRs, issues, commits, diffs). Reference them by path or URL instead.

Redact any sensitive information, such as API keys, passwords, or personally identifiable information.

If the user passed arguments, treat them as a description of what the next session will focus on and tailor the doc accordingly.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

ask-matt

免费

Ask which skill or flow fits your situation. A router over the skills in this repo.

中文简介正在准备中。当前显示原文说明。

tt-a1i/matt-skills-with-to-goal1852026年10月10日 更新

Hand the current conversation off to a fresh background agent that picks up the work immediately.

中文简介正在准备中。当前显示原文说明。

tt-a1i/matt-skills-with-to-goal1852026年10月10日 更新

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

中文简介正在准备中。当前显示原文说明。

tt-a1i/matt-skills-with-to-goal1852026年10月10日 更新

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

中文简介正在准备中。当前显示原文说明。

tt-a1i/matt-skills-with-to-goal1852026年10月10日 更新

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

中文简介正在准备中。当前显示原文说明。

tt-a1i/matt-skills-with-to-goal1852026年10月10日 更新

Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.

中文简介正在准备中。当前显示原文说明。

tt-a1i/matt-skills-with-to-goal1852026年10月10日 更新

查看 tt-a1i 的全部技能

报告此技能的问题