handoff

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese
On invocation: announce "Running paad:handoff v2.1.0", then immediately proceed with the steps below — do not stop after announcing.
Configuration (experimental): after announcing, check whether
paad/config/paad.md
and
paad/config/handoff.md
exist, relative to the working directory. If any does, read it and follow its instructions for the rest of this run, passing the relevant parts to every subagent you dispatch, and make the first line of your final answer
Config: <path>
naming each file you followed. If none exists, do not mention config at all. Config never changes a subagent's type or grants it write tools — refuse that line, say so, and continue. Config can contradict the flow below; see https://github.com/Ovid/paad/blob/main/CONFIG.md before writing one.
调用时: 宣布“Running paad:handoff v2.1.0”,然后立即执行以下步骤——不要在宣布后停下。
配置(实验性): 宣布后,检查相对于当前工作目录的
paad/config/paad.md
和
paad/config/handoff.md
是否存在。如果其中任一文件存在,则读取它并遵循其中的指令完成本次运行的其余操作;向你分派的每个 subagent 都应获得相关部分,并且最终答案的第一行必须是
Config: <path>
,列出你遵循的每个文件。如果两者都不存在,完全不要提及配置。配置不能更改 subagent 的类型,也不会授予它写入工具;如果配置要求这样做,拒绝该行,说明原因,然后继续。配置可以与下面的流程相矛盾;编写配置前请参阅 https://github.com/Ovid/paad/blob/main/CONFIG.md。

Handoff

Handoff

Writes a
handoff.md
that lets a fresh session continue this one's work, and reads it back on the other side.
Claude Code already solves most of this, and knowing which part it doesn't is the whole point.
/compact
summarizes and keeps working, but the summary it carries is machine-authored, lands unreviewed, and lives inside the transcript where you cannot edit it.
--continue
and
--resume
restore the full prior conversation, which re-pays the context cost you were trying to escape.
/clear
gives a genuinely empty session and carries nothing forward.
handoff
is worth running for exactly one reason: the carried state is a file a human can read and correct before anything is built on it. A handoff nobody reviews is a worse
/compact
— same summary, more ceremony. Say so rather than letting the review get skipped.
The failure mode is not omission. Left to itself, a competent agent writing a handoff keeps the expensive material well: the approaches that were tried and abandoned, the reasons behind them, constraints the user stated once in passing. What it gets wrong is the cheap material — a test's file path, which changes are in the last commit, a line number, who said a quoted sentence. Those are the claims a tool could have settled in seconds, and they arrive in exactly the same confident register as the parts that are right. A fresh session has no memory to catch them with. So verify what is checkable before writing it down, and mark what is not.
Mode selection and saving:
dot
digraph handoff_save {
  "Argument given?" [shape=diamond];
  "Use the named mode" [shape=box];
  "Conversation above this invocation?" [shape=diamond];
  "Say: saving, session has history" [shape=box];
  "Resume flow, below" [shape=box];
  "handoff.md in .gitignore?" [shape=diamond];
  "Suggest adding it, never add it silently" [shape=box];
  "Verify every checkable claim with tools" [shape=box];
  "Claim survived verification?" [shape=diamond];
  "Write it as fact" [shape=box];
  "Correct it, or mark it inferred" [shape=box];
  "handoff.md absent, or not a symlink?" [shape=diamond];
  "Write nothing; tell the user, ask where to save it" [shape=box];
  "Write handoff.md with the Write tool" [shape=box];
  "Name the unverified claims, ask for review" [shape=box];
  "Announce the artifact" [shape=box];

  "Argument given?" -> "Use the named mode" [label="save or resume"];
  "Argument given?" -> "Conversation above this invocation?" [label="no"];
  "Conversation above this invocation?" -> "Say: saving, session has history" [label="yes"];
  "Conversation above this invocation?" -> "Resume flow, below" [label="no"];
  "Use the named mode" -> "Say: saving, session has history" [label="save"];
  "Use the named mode" -> "Resume flow, below" [label="resume"];
  "Say: saving, session has history" -> "handoff.md in .gitignore?";
  "handoff.md in .gitignore?" -> "Suggest adding it, never add it silently" [label="no"];
  "handoff.md in .gitignore?" -> "Verify every checkable claim with tools" [label="yes"];
  "Suggest adding it, never add it silently" -> "Verify every checkable claim with tools";
  "Verify every checkable claim with tools" -> "Claim survived verification?";
  "Claim survived verification?" -> "Write it as fact" [label="yes"];
  "Claim survived verification?" -> "Correct it, or mark it inferred" [label="no"];
  "Write it as fact" -> "handoff.md absent, or not a symlink?";
  "Correct it, or mark it inferred" -> "handoff.md absent, or not a symlink?";
  "Write handoff.md with the Write tool" -> "Name the unverified claims, ask for review";
  "Name the unverified claims, ask for review" -> "Announce the artifact";
  "handoff.md absent, or not a symlink?" -> "Write handoff.md with the Write tool" [label="yes"];
  "handoff.md absent, or not a symlink?" -> "Write nothing; tell the user, ask where to save it" [label="no"];
  "Write nothing; tell the user, ask where to save it" -> "Write handoff.md with the Write tool" [label="user names a safe path"];
}
Resuming:
dot
digraph handoff_resume {
  "handoff.md exists?" [shape=diamond];
  "Say so, offer to save one instead" [shape=box];
  "Read it, summarize in a few lines" [shape=box];
  "Recorded commit matches HEAD?" [shape=diamond];
  "Report the drift before asking" [shape=box];
  "Ask: proceed?" [shape=diamond];
  "Stop, leave the file alone" [shape=box];
  "Check the files and state it names" [shape=box];
  "Everything matches?" [shape=diamond];
  "Report every mismatch, ask again" [shape=box];
  "Start the recorded next step" [shape=box];
  "Leave handoff.md in place" [shape=box];

  "handoff.md exists?" -> "Read it, summarize in a few lines" [label="yes"];
  "handoff.md exists?" -> "Say so, offer to save one instead" [label="no"];
  "Read it, summarize in a few lines" -> "Recorded commit matches HEAD?";
  "Recorded commit matches HEAD?" -> "Ask: proceed?" [label="yes"];
  "Recorded commit matches HEAD?" -> "Report the drift before asking" [label="no"];
  "Report the drift before asking" -> "Ask: proceed?";
  "Ask: proceed?" -> "Check the files and state it names" [label="yes"];
  "Ask: proceed?" -> "Stop, leave the file alone" [label="no"];
  "Check the files and state it names" -> "Everything matches?";
  "Everything matches?" -> "Start the recorded next step" [label="yes"];
  "Everything matches?" -> "Report every mismatch, ask again" [label="no"];
  "Report every mismatch, ask again" -> "Start the recorded next step" [label="user confirmed"];
  "Start the recorded next step" -> "Leave handoff.md in place";
}
写入一份
handoff.md
,让全新的会话继续当前会话的工作;在另一端则将其读回。
Claude Code 已经解决了这里的大部分问题,而明确它没有解决的那部分正是关键所在。
/compact
会进行总结并继续工作,但它携带的摘要由机器生成、未经审阅,且保存在你无法编辑的会话记录中。
--continue
和
--resume
会恢复完整的先前对话,从而重新支付你原本想要规避的上下文成本。
/clear
会开启一个真正为空的会话,不携带任何信息。
handoff
值得运行的原因只有一个:承接下去的状态是一个文件,人类可以在任何内容基于它构建之前阅读并修正它。 没人审阅的 handoff 比
/compact
更糟——摘要相同,流程却更多。要直说,不要跳过审阅。
失效点不是遗漏。 如果放任一个称职的 Agent 编写 handoff,它通常会很好地保留高价值材料:尝试过并放弃的方案、背后的原因,以及用户顺口提过一次的约束。它真正容易写错的是廉价材料——测试的文件路径、最后一个 commit 中的变更、行号、某句引文是谁说的。这些断言工具几秒内就能确定,却会与正确部分使用完全相同的笃定语气出现。新会话没有记忆来捕捉它们。因此,写入前验证所有可验证的内容,并标记不可验证的内容。
模式选择与保存:
dot
digraph handoff_save {
  "Argument given?" [shape=diamond];
  "Use the named mode" [shape=box];
  "Conversation above this invocation?" [shape=diamond];
  "Say: saving, session has history" [shape=box];
  "Resume flow, below" [shape=box];
  "handoff.md in .gitignore?" [shape=diamond];
  "Suggest adding it, never add it silently" [shape=box];
  "Verify every checkable claim with tools" [shape=box];
  "Claim survived verification?" [shape=diamond];
  "Write it as fact" [shape=box];
  "Correct it, or mark it inferred" [shape=box];
  "handoff.md absent, or not a symlink?" [shape=diamond];
  "Write nothing; tell the user, ask where to save it" [shape=box];
  "Write handoff.md with the Write tool" [shape=box];
  "Name the unverified claims, ask for review" [shape=box];
  "Announce the artifact" [shape=box];

  "Argument given?" -> "Use the named mode" [label="save or resume"];
  "Argument given?" -> "Conversation above this invocation?" [label="no"];
  "Conversation above this invocation?" -> "Say: saving, session has history" [label="yes"];
  "Conversation above this invocation?" -> "Resume flow, below" [label="no"];
  "Use the named mode" -> "Say: saving, session has history" [label="save"];
  "Use the named mode" -> "Resume flow, below" [label="resume"];
  "Say: saving, session has history" -> "handoff.md in .gitignore?";
  "handoff.md in .gitignore?" -> "Suggest adding it, never add it silently" [label="no"];
  "handoff.md in .gitignore?" -> "Verify every checkable claim with tools" [label="yes"];
  "Suggest adding it, never add it silently" -> "Verify every checkable claim with tools";
  "Verify every checkable claim with tools" -> "Claim survived verification?";
  "Claim survived verification?" -> "Write it as fact" [label="yes"];
  "Claim survived verification?" -> "Correct it, or mark it inferred" [label="no"];
  "Write it as fact" -> "handoff.md absent, or not a symlink?";
  "Correct it, or mark it inferred" -> "handoff.md absent, or not a symlink?";
  "handoff.md absent, or not a symlink?" -> "Write nothing; tell the user, ask where to save it" [label="no"];
  "Write nothing; tell the user, ask where to save it" -> "Write handoff.md with the Write tool" [label="user names a safe path"];
}
恢复:
dot
digraph handoff_resume {
  "handoff.md exists?" [shape=diamond];
  "Say so, offer to save one instead" [shape=box];
  "Read it, summarize in a few lines" [shape=box];
  "Recorded commit matches HEAD?" [shape=diamond];
  "Report the drift before asking" [shape=box];
  "Ask: proceed?" [shape=diamond];
  "Stop, leave the file alone" [shape=box];
  "Check the files and state it names" [shape=box];
  "Everything matches?" [shape=diamond];
  "Report every mismatch, ask again" [shape=box];
  "Start the recorded next step" [shape=box];
  "Leave handoff.md in place" [shape=box];

  "handoff.md exists?" -> "Read it, summarize in a few lines" [label="yes"];
  "handoff.md exists?" -> "Say so, offer to save one instead" [label="no"];
  "Read it, summarize in a few lines" -> "Recorded commit matches HEAD?";
  "Recorded commit matches HEAD?" -> "Ask: proceed?" [label="yes"];
  "Recorded commit matches HEAD?" -> "Report the drift before asking" [label="no"];
  "Report the drift before asking" -> "Ask: proceed?";
  "Ask: proceed?" -> "Check the files and state it names" [label="yes"];
  "Ask: proceed?" -> "Stop, leave the file alone" [label="no"];
  "Check the files and state it names" -> "Everything matches?";
  "Everything matches?" -> "Start the recorded next step" [label="yes"];
  "Everything matches?" -> "Report every mismatch, ask again" [label="no"];
  "Report every mismatch, ask again" -> "Start the recorded next step" [label="user confirmed"];
  "Start the recorded next step" -> "Leave handoff.md in place";
}

Arguments

参数

  • /handoff
    — infer the mode. Conversation above this invocation means you are saving; an empty session means you are resuming. Say which way it went, in one line, before acting.
  • /handoff save
    — write a handoff regardless
  • /handoff resume
    — read the existing handoff regardless
The inference is a convenience, not a guess worth defending. If it picks wrong, the user says
save
or
resume
and you obey without arguing.
  • /handoff
    ——推断模式。如果本次调用上方存在对话,说明你正在保存;如果会话为空,说明你正在恢复。行动前用一行说明采用了哪种方式。
  • /handoff save
    ——无论当前状态如何,都写入 handoff
  • /handoff resume
    ——无论当前状态如何,都读取现有 handoff
这种推断只是一种便利机制,不值得为之争辩。如果推断错误,用户会指定
save
或
resume
,你应直接服从,不要争论。

Saving

保存

1. Check
.gitignore

1. 检查
.gitignore

If
handoff.md
is not ignored, say so and suggest adding it. Suggest — do not edit
.gitignore
yourself.
It is a tracked file and the user may have reasons.
如果
handoff.md
未被忽略,说明这一点并建议将其加入。只提出建议——不要自行编辑
.gitignore
。
它是受版本控制的文件,用户可能有充分理由保留现状。

2. Verify before you write

2. 写入前进行验证

This is the step that makes the skill worth running. Every claim below is checkable with a tool in seconds, and every one of them is a claim agents get wrong from memory:
ClaimSettle it with
Current commit, branch, dirty state
git rev-parse --short HEAD
,
git status --short
What is actually in the last commit
git show --stat HEAD
— not the commit message, which lies
A file pathRead it, or
ls
it
A line numberRead the file and look
A test's name or fileGrep for it
Whether the suite passes, and what failsRun it
A quoted sentence and who said itFind it in the conversation, or do not quote it
If a claim cannot be settled, it does not become a fact. Either drop it or mark it inferred.
这一步正是此 skill 值得运行的原因。下面的每项断言都可以用工具在几秒内确认,而且这些正是 Agent 凭记忆容易写错的内容:
断言验证方式
当前 commit、branch 和 dirty state
git rev-parse --short HEAD
、
git status --short
最后一个 commit 中实际包含的内容
git show --stat HEAD
——不要使用 commit message,它可能与实际内容不符
文件路径读取该文件,或执行
ls
行号读取文件并查找
测试名称或测试文件使用 Grep 搜索
测试套件是否通过,以及哪些测试失败运行测试
引文内容及其说话者在对话中查找,否则不要引用
如果某项断言无法确定,它就不能成为事实。要么删除,要么将其标记为 inferred。

3. Write the file

3. 写入文件

Before writing, check that
handoff.md
, if it exists, is not a symlink (
test ! -L handoff.md
): a repository can commit one to send this session's state to a path it chose. If it is one, write nothing: tell the user and ask where to save it.
Use the Write tool, never a shell redirect. Claude Code snapshots files its own file tools touch; a
bash > handoff.md
has no recovery copy anywhere, and neither does git, since the file is ignored.
markdown
undefined
写入前,如果
handoff.md
已存在,检查它不是符号链接(
test ! -L handoff.md
):仓库可能提交一个符号链接,把本次会话的状态导向它选定的路径。如果它是符号链接,则不要写入任何内容;告诉用户,并询问应保存在哪里。
使用 Write tool,绝不要使用 shell 重定向。Claude Code 会为自身文件工具修改过的文件创建快照;
bash > handoff.md
在任何地方都不会留下恢复副本,git 也无法恢复,因为该文件已被忽略。
markdown
undefined

Handoff — <one-line task name>

Handoff — <one-line task name>

Written <date time> · branch
<branch>
· commit
<short sha>
Uncommitted: <one line — what is dirty, what is staged>
Written <date time> · branch
<branch>
· commit
<short sha>
Uncommitted: <one line — what is dirty, what is staged>

Goal

Goal

What we are trying to achieve, and what "done" looks like.
What we are trying to achieve, and what "done" looks like.

Decisions

Decisions

Chose X over Y, because Z. One line each.
Chose X over Y, because Z. One line each.

Ruled out

Ruled out

What was tried, how it failed, and how far it got. One line each.
What was tried, how it failed, and how far it got. One line each.

Constraints

Constraints

Things the user said that exist nowhere on disk. Quote them.
Things the user said that exist nowhere on disk. Quote them.

Next step

Next step

The single immediate action, with the file and line to start at.
The single immediate action, with the file and line to start at.

Verify

Verify

The command that says whether it worked.
The command that says whether it worked.

Unverified

Unverified

Anything above that could not be checked, marked as inferred. Delete this section if it is empty — do not pad it.

**"Ruled out" is the section that earns the file.** Everything else is recoverable — a fresh session can read the code, run `git log`, work out the goal. What it cannot recover is that forty minutes already went into proving an approach doesn't work. Without that line, it spends them again.

**Write down what a fresh session cannot reconstruct, and nothing else.** No architecture tour, no narrative of how the session went, no restating what `git diff` already shows. Those feel thorough and are pure padding, and padding is not harmless here: it makes the file long enough that the review gets skimmed, and the review is the only reason this skill beats `/compact`.
Anything above that could not be checked, marked as inferred. Delete this section if it is empty — do not pad it.

**“Ruled out”才是这份文件的价值所在。** 其他所有内容都可恢复——新会话可以读取代码、运行 `git log`、弄清目标。它无法恢复的是,已经花了四十分钟证明某种方案行不通。少了这一行,新会话会把时间再花一遍。

**只记录新会话无法重建的内容,除此以外一概不写。** 不要做架构导览,不要叙述会话如何展开,也不要重述 `git diff` 已经展示的内容。这些内容看起来周全,实则纯粹是填充;而且填充并非无害:它会让文件长得过长,以至于审阅时被草草略过,而审阅正是此 skill 胜过 `/compact` 的唯一原因。

4. Ask for the review that matters

4. 请求真正重要的审阅

Do not close with a general disclaimer. "Please review, AI can make mistakes" is true of everything and therefore aims at nothing — it gets skimmed, and inference reads exactly like recall.
Name the specific claims you are least sure of and say what depends on them:
Two things to check before you rely on this. I inferred the next step from what we were doing rather than from anything you said outright, and I could not confirm the second constraint is still live — it came from early in the session. Everything downstream is built on both.
If everything in the file was verified, say that instead, plainly. An honest "all of this was checked against the repo" is a better prompt to read it than a manufactured doubt.
不要以泛泛的免责声明收尾。“请审阅,AI 可能会犯错”对所有事情都成立,因此没有指向任何具体问题——它会被草草略过,而且 inferred 内容读起来与实际记忆完全一样。
点明你最难确定的特定断言,并说明哪些后续工作依赖于它们:
依赖这些内容前有两点需要检查。我是根据我们当时在做的事情推断出下一步的,而不是根据你明确说过的话;我也无法确认第二个约束仍然有效——它来自会话早期。后续所有工作都建立在这两点之上。
如果文件中的所有内容都已验证,就直接这样说明。一句诚实的“所有内容都已对照仓库检查过”,比刻意制造疑虑更能促使人们认真阅读。

5. Announce the artifact

5. 宣布生成的产物

End with the file you touched. Say it even though the user asked for it and watched it happen — a handoff sitting unnoticed in the working directory is the same as no handoff:
Files written or updated:
  new      handoff.md
On a resume, the same block covers whatever the recorded next step changed. Source and test files need only a count and a pointer —
4 source files changed in src/dbsync/ (see git diff)
— but
handoff.md
itself is named every time.
最后写明你触碰的文件。即使用户提出要求并亲眼看着整个过程发生,也仍然要说明——工作目录中无人注意的 handoff 等同于没有 handoff:
Files written or updated:
  new      handoff.md
恢复时,同一区块涵盖记录的下一步实际改动的所有内容。源代码和测试文件只需给出数量和指针——
4 source files changed in src/dbsync/ (see git diff)
——但每次都必须点名
handoff.md
。

Resuming

恢复

  1. Read
    handoff.md
    .
    If there isn't one, say so and offer to save one instead.
  2. Summarize it in a few lines — the goal, where it stopped, the next step. Short. The file is right there if the user wants the rest.
  3. Check for drift. Compare the recorded commit against HEAD. If they differ, say so before asking anything.
  4. Ask whether to proceed. Wait for an answer.
  5. Verify the handoff's claims before acting on them: the files it names exist, the state it describes is the state on disk, the failing tests it predicts are the ones failing. A fresh session has no independent memory — if it does not check, nothing does.
  6. Report every mismatch and ask again. A stale handoff is more dangerous than no handoff, because it is specific and confident.
  7. Then start the recorded next step.
Never delete
handoff.md
.
Not after reading it, not on success. It is the only written record of the reasoning, and it is untracked, so git cannot bring it back. If the resume goes sideways the user needs to re-read what it actually said. The next save overwrites it; that is the whole lifecycle.
  1. 读取
    handoff.md
    。
    如果文件不存在,说明这一点,并改为提议保存一份。
  2. 用几行内容总结它——目标、停止的位置、下一步。要简短;如果用户想看其余内容,文件就在那里。
  3. 检查状态漂移。 将记录的 commit 与 HEAD 比较。如果两者不同,在询问任何问题之前先说明。
  4. 询问是否继续。 等待用户回答。
  5. **执行操作前验证 handoff 中的断言:**它提到的文件是否存在、它描述的状态是否与磁盘上的状态一致、它预测失败的测试是否确实正在失败。新会话没有独立的记忆——如果不检查,就不会有人发现这些问题。
  6. 报告每一处不匹配,并再次询问。 过期的 handoff 比没有 handoff 更危险,因为它给出的信息具体而笃定。
  7. 然后开始执行记录的下一步。
绝不删除
handoff.md
。
读取后不要删除,成功后也不要删除。它是关于推理过程的唯一书面记录,而且未被跟踪,因此 git 无法将其恢复。如果恢复过程出现问题,用户需要重新阅读它实际写了什么。下一次保存会覆盖它;这就是完整生命周期。

Common Mistakes

常见错误

MistakeWhat to do instead
Writing file paths, line numbers, or test names from memoryThese are the errors. Check each one with a tool first — it costs seconds.
Quoting the user's constraint and attributing it to a nameThe conversation may never state who said it. Quote the sentence; do not invent the speaker.
Trusting the last commit's message for what it contains
git show --stat HEAD
. Messages describe intent, not content.
Including an architecture tour or a file-by-file layoutRecoverable by opening the repo. It buys nothing and costs the review.
Narrating how the session unfoldedThe next session needs the conclusions, not the journey.
Stating inferred and verified claims in the same registerMark the inferred ones. Uniform confidence is what hides the errors.
Filing a claim under "Unverified" instead of checking itThat section is for what a tool genuinely cannot settle. If
git show --stat HEAD
or one grep would answer it, run it. An Unverified list longer than a few lines, in a repo you can read, means verification got skipped and relabelled.
Closing with "review this, AI makes mistakes"Name the two or three claims that actually need checking.
Deleting the handoff after resumingIt is untracked; git cannot restore it. Let the next save overwrite it.
Resuming straight into the work without checking the treeThe handoff may be describing a state that no longer exists.
Writing the file with
echo
or
>
Use the Write tool. A shell redirect leaves no recovery copy.
Running this to compact the current sessionThat is
/compact
. This skill exists to produce a file for a different session.
错误应改为
凭记忆写入文件路径、行号或测试名称这些正是最容易出错的内容。先用工具逐项检查——只需几秒。
引用用户的约束,并将说话者归到某个名字上对话中可能从未说明是谁说的。引用原句;不要臆造说话者。
根据最后一个 commit 的 message 判断其中包含什么使用
git show --stat HEAD
。message 描述的是意图,而不是内容。
加入架构导览或逐文件结构说明打开仓库即可恢复这些信息。这样做没有收益,只会增加审阅成本。
叙述会话如何发展下一个会话需要的是结论,而不是过程。
用同样笃定的语气陈述 inferred 和 verified 内容将 inferred 内容标出来。统一的确信语气正是掩盖错误的原因。
把某项断言放进“Unverified”,而不先检查该章节只用于工具确实无法确定的内容。如果
git show --stat HEAD
或一次 grep 就能回答,就去执行。仓库可读时,Unverified 超过几行,就说明验证被跳过后改了标签。
用“请审阅,AI 会犯错”收尾指出真正需要检查的两三项断言。
恢复后删除 handoff它是未跟踪文件,git 无法恢复。让下一次 save 覆盖它即可。
不检查工作树就直接恢复工作handoff 所描述的状态可能已经不存在。
使用
echo
或
>
写入文件
使用 Write tool。shell 重定向不会留下恢复副本。
运行此功能来压缩当前会话那是
/compact
。此 skill 用于为另一个会话生成文件。

Red Flags — stop and check

危险信号——停止并检查

  • You are about to write a line number you did not just read
  • You are about to write "the tests pass" without having run them
  • You are attributing a quote to a person the conversation never named
  • Your handoff has a section describing the codebase's structure
  • Every sentence in your draft is equally confident
  • You are about to close with a generic request to review it
  • You are about to
    rm handoff.md
  • Your "Unverified" section is longer than your "Decisions" section, and you can read the repo
  • The file is long enough that you would not read it yourself
All of these mean: go check, cut it, or mark it inferred.
  • 你正要写入一个自己并未刚刚读取过的行号
  • 你正要断言“测试通过”,但并未运行测试
  • 你正要将一句引文归给对话中从未点名的某个人
  • 你的 handoff 中有一节在描述代码库结构
  • 草稿中的每个句子都同样笃定
  • 你正准备以泛泛的审阅请求收尾
  • 你正准备执行
    rm handoff.md
  • 你的“Unverified”章节比“Decisions”章节还长,而且你能够读取仓库
  • 文件长到你本人都不愿阅读
出现以上任何情况,都意味着:去检查、删减,或将其标记为 inferred。