evidence-docs

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Evidence-backed documentation

基于证据的文档

A claim is documentation only when it carries the means to check it. This skill is the standard and the map: ten canons, and where each is defined, enforced and seeded.
It is a navigator, not a second copy. Every law below has exactly one home — that is canon 3, and a navigator that restated the doctrine would break the rule it is indexing. The full statement of each canon, its rationale and its enforcement live in
documentation.md
The canons.
只有当内容附带可验证的依据时,才能称之为文档。 本技能是标准与指引:包含十条准则,以及每条准则的定义、执行方式和来源。
它是一个导航工具,而非重复副本。以下每条准则都有唯一的来源——这正是准则3的要求,若导航工具重述规范,便会违背其索引的规则。每条准则的完整说明、原理及执行细节请查看
documentation.md
准则部分

The ten canons

十条准则

  1. A claim carries its address
    file:line
    , a command with its output, a test name; a lesson names its commit.
  2. Numbers are computed, never restated.
  3. Every fact has exactly one home — others link, never restate.
  4. A reference resolves from where the document is read — not from where it lives.
  5. Green nobody watched turn red is not evidence.
  6. A check proves its scope and nothing beyond it.
  7. Silence is not a pass — ask what a mechanism prints when it did not look.
  8. An estimate is never announced as a measurement — a rule states its evidence condition.
  9. What was not checked is printed beside what was.
  10. The document ships in the change that made it true — and a correction is appended, never written over.
They are epistemic: what makes a claim documentation. The operational layer — what to do at a given trigger, with a check and an exit criterion — is
learned.md
. When the two seem to say the same thing, the canon is the why and the rule is the how.
  1. 内容附带定位信息 ——
    file:line
    、带输出的命令、测试名称;经验教训需标注对应的提交记录。
  2. 数据需计算得出,不得重复转述。
  3. 每个事实仅有唯一来源 —— 其他内容仅可链接,不得重复转述。
  4. 引用需从文档阅读位置解析 —— 而非文档存储位置。
  5. 无人关注的成功结果不算证据。
  6. 验证仅能证明其覆盖范围,不涉及其他内容。
  7. 无反馈不等于通过 —— 需明确机制未检查时的输出内容。
  8. 估算不得当作实测结果发布 —— 规则需明确其证据条件。
  9. 未检查内容需与已检查内容一并列出。
  10. 文档随使其生效的变更一同发布 —— 修正内容需追加,不得覆盖原文。
这些是认知层面的要求:界定了何为有依据的文档。操作层面——即特定触发场景下的行动、验证方式及退出标准——请查看
learned.md
。当两者内容看似重叠时,准则是原因,规则是执行方法

Where next

下一步指引

You are about to…ReadBecause
set a project's documentation up from nothing
documentation.md
The inventory
four questions answered before the first line of work
record a decision so it survives its authorRegisters and ids +
templates/decisions.md
append-only ids, edge markers, one decision home
change something and not orphan the docsThe Doc Loop + The propagation matrixwhich documents a change owes, starting with the meta-row
decide where a fact belongsSingle source of truthtwo homes disagree the day one of them is updated
build a check that cannot lie
gates.md
three axes, the enforcement ladder, progressive arming, probing
trust a mechanism that reports success
gates.md
False success
the failure that removes the reason to look
wire a check into the agent's own tooling
hooks.md
the hook contract, and why a crashed guard allows the action
audit documentation a project already has
setup.md
seven passes, cheapest first, output is a fix plan
carry a lesson to the next run
retrospective.md
stamp first (the cold trigger reads it), then prune to a cap of ten; every lesson names its commit
seed a gate into a host project
templates/docgate.sh
it seeds green: dormant where there is no input yet
claim that an agent behaves
tdd.md
When the thing under test is an agent — named rather than linked, because this navigator's out-of-directory links break wherever a packager ships this skill alone
the address is a trace id and the assertion that ran (canon 1); a judge nobody watched disagree is a green nobody watched turn red (canon 5)
take a whole change through to acceptance
task-pipeline
this skill is the standard; that one is how a change reaches the repository
你即将要…阅读内容原因
从零开始搭建项目文档体系
documentation.md
清单部分
开始工作前需明确四个核心问题
记录决策以确保其不受作者离职影响登记册与ID +
templates/decisions.md
仅追加式ID、边界标记、决策唯一来源
变更内容且不导致文档脱节文档循环 + 传播矩阵变更需同步的文档范围,从元数据行开始
确定事实的归属位置单一事实来源若存在两个来源,其中一个更新时必然出现分歧
构建可靠的验证机制
gates.md
三个维度、执行层级、渐进式启用、探查机制
信任报告成功的机制
gates.md
虚假成功
此类失败会消除进一步检查的必要性
将验证机制接入Agent工具链
hooks.md
钩子合约,以及为何崩溃的防护会允许操作执行
审计项目现有文档
setup.md
七个检查步骤,从成本最低的开始,输出修复方案
将经验教训带入下一轮工作
retrospective.md
先标记(冷触发时读取),再精简至最多十条;每条经验教训需标注对应的提交记录
在宿主项目中植入文档准入机制
templates/docgate.sh
初始状态为绿色:无输入时处于休眠状态
声称Agent行为合规
tdd.md
当测试对象为Agent时 —— 此处仅命名而非链接,因为本导航工具的跨目录链接在打包工具单独分发此技能时会失效
定位信息为追踪ID及执行的断言(准则1);无人关注的判定分歧属于“无人关注的成功结果变失败”(准则5)
完成完整变更的验收流程
task-pipeline
本技能是标准,而该技能是变更进入代码库的流程指引

When this applies

适用场景

The boundary is "it will be read as true." A decision record, a README, an acceptance report, a runbook, a changelog for users, an audit finding, a claim that something was verified.
Not through this skill: a draft, thinking out loud, an answer in chat, a commit message, a code comment. Demanding a
file:line
for "let me check that" is the fastest way to teach an agent to route around the rule where it actually protects something.
Refusal phrase — "без доков" / "on my word". It works on a task that would otherwise pass through here: do it directly and say out loud that the claim is unbacked, rather than presenting an estimate as a measurement (canon 8).
边界是“内容会被当作事实”。包括决策记录、README、验收报告、运行手册、面向用户的变更日志、审计结果、声称已验证的内容。
不适用场景:草稿、即兴想法、聊天回复、提交信息、代码注释。若对“我确认一下”这类内容要求
file:line
定位,会导致Agent在规则实际需要保护的场景下绕开规则。
拒绝用语 —— "без доков" / "on my word"。此用语可用于原本会进入本流程的任务:直接执行操作,并明确说明内容无依据,而非将估算当作实测结果发布(准则8)。

The one test

唯一测试标准

Before a document ships, read it for the sentence that would embarrass you if someone asked "how do you know?" — and either give that sentence its address, or delete it. Everything above is that question, made mechanical.
文档发布前,通读并找出若有人问*“你怎么知道的?”*会让你尴尬的句子——要么为该句子添加定位依据,要么删除它。以上所有规则都是将这个问题转化为可执行的机械流程。