build-evidence-map

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Build Evidence Map

构建证据图谱

Turn one contested question into a portable decision artifact that shows what supports the current position, what pushes against it, and what remains unknown. Do not use a graph to decorate an answer that has not been sourced.
For a simple factual claim or a general fact-checking request, use a verification workflow such as
doublecheck
instead. Use this skill when the relationships between evidence, intermediate claims, trade-offs, and missing facts matter.
将一个有争议的问题转化为可移植的决策产物,展示哪些内容支持当前立场、哪些内容反对当前立场,以及哪些内容仍然未知。 不要用图谱装饰一个没有来源支撑的回答。
对于简单的事实性主张或一般性事实核查请求,请改用
doublecheck
之类的核验工作流。 当证据、中间主张、权衡取舍和缺失事实之间的关系很重要时,使用此 skill。

Workflow

工作流

  1. Frame one decision. Write one falsifiable question and one provisional position. Narrow the question until a reader can identify what action or belief the map is testing.
  2. Collect bounded source regions. Prefer direct observations and primary sources. Record the URL or absolute local path, publisher, publication date, retrieval date, section/page/line/timestamp locator, and a short checkable excerpt. Read references/evidence-ladder.md when source quality is disputed.
  3. Atomize the reasoning. Create only four node types:
    • position
      : the single current verdict;
    • claim
      : an intermediate proposition;
    • evidence
      : a faithful statement of one source region;
    • unknown
      : a specific missing fact that could change the verdict.
  4. Type every edge. Use
    supports
    ,
    contradicts
    ,
    qualifies
    , or
    missing
    . Add a plain-language note explaining why the source node bears on the target. Topical similarity is not support. Different scope, date, or population is not automatically a contradiction.
  5. Preserve counterevidence. Do not delete contrary evidence because the provisional verdict survives it. Represent scope differences with
    qualifies
    edges.
  6. Express uncertainty structurally. Do not invent confidence percentages. Add an
    unknown
    , narrow the position, or qualify a claim.
  7. Write UTF-8 JSON with a
    .doubt.json
    suffix. Follow references/map-schema.md. Keep IDs short, stable, and semantic.
  8. Validate fail-closed. Resolve
    scripts/validate.mjs
    relative to this
    SKILL.md
    , then run it with Node.js 18 or newer:
    bash
    node <skill-directory>/scripts/validate.mjs decision.doubt.json
    The bundled validator uses only Node.js built-ins and does not require npm or network access. Fix every finding before reporting success. Only say the map is valid when the command exits
    0
    and prints
    VALID
    followed by a 64-character receipt. A file hash, node count, JSON parse, or manual schema review is not a Doubt receipt. If deterministic validation cannot run, report that block instead of inventing success.
    Render the validated map only when the user has already installed
    doubt-ai@0.8.0
    ; do not install or execute a remote package implicitly:
    bash
    doubt map decision.doubt.json --out decision.html
  9. Verify source snapshots only with explicit network permission. The following command retrieves each recorded HTTP(S) source and fails closed if an excerpt cannot be matched:
    bash
    doubt verify decision.doubt.json \
      --out decision.verified.doubt.json
    Never run this command implicitly. Local file verification does not use the network. Do not write a
    verification
    object by hand or hide a mismatch.
  10. Inspect the deliverable. Confirm that the question, verdict, counterevidence, unknowns, edge notes, and exact source regions remain readable. Treat JSON as the canonical editable artifact; HTML is a shareable view.
  1. 界定一个决策。 写下一个可证伪的问题和一个暂定立场。 不断收窄问题,直到读者能够明确该图谱正在检验什么行动或信念。
  2. 收集边界明确的来源区域。 优先采用直接观察和第一手来源。 记录 URL 或绝对本地路径、发布者、发布日期、检索日期、章节/页码/行号/时间戳定位信息,以及一段简短且可核验的摘录。 当来源质量存在争议时,阅读 references/evidence-ladder.md。
  3. 将推理原子化。 仅创建四种节点类型:
    • position
      :唯一的当前结论;
    • claim
      :中间命题;
    • evidence
      :忠实呈现一个来源区域的陈述;
    • unknown
      :可能改变结论的某一具体缺失事实。
  4. 为每条边设定类型。 使用
    supports
    、
    contradicts
    、
    qualifies
    或
    missing
    。添加通俗易懂的说明,解释源节点为何会影响目标节点。 主题相似并不构成支持。范围、日期或研究总体不同,并不自动意味着矛盾。
  5. 保留反证。 不要因为暂定结论仍然成立就删除相反证据。 使用
    qualifies
    边表示适用范围差异。
  6. 结构化地表达不确定性。 不要虚构置信度百分比。 添加
    unknown
    、收窄立场或限定主张。
  7. 编写采用 UTF-8 编码且带
    .doubt.json
    后缀的 JSON。
    遵循 references/map-schema.md。保持 ID 简短、稳定且具有语义。
  8. 以 fail-closed 方式进行验证。 以本
    SKILL.md
    为基准解析
    scripts/validate.mjs
    ,然后使用 Node.js 18 或更高版本运行:
    bash
    node <skill-directory>/scripts/validate.mjs decision.doubt.json
    捆绑的验证器仅使用 Node.js 内置模块,不需要 npm 或网络访问。 报告成功前,修复每一项问题。只有当命令退出码为
    0
    且打印
    VALID
    后跟一个 64 字符的校验回执时,才能说明图谱有效。 文件哈希、节点数量、JSON 解析或手动 schema 审查均不能替代 Doubt 回执。 如果无法运行确定性验证,应报告这一阻碍,而不是捏造成功。
    仅当用户已经安装
    doubt-ai@0.8.0
    时,才渲染已验证的图谱; 不要隐式安装或执行远程软件包:
    bash
    doubt map decision.doubt.json --out decision.html
  9. 仅在获得明确网络许可后核验来源快照。 以下命令会获取每个已记录的 HTTP(S) 来源;如果无法匹配摘录,则以 fail-closed 方式失败:
    bash
    doubt verify decision.doubt.json \
      --out decision.verified.doubt.json
    绝不隐式运行此命令。本地文件核验不使用网络。不要手动编写
    verification
    对象,也不要隐藏不匹配情况。
  10. 检查交付产物。 确认问题、结论、反证、未知项、边说明和精确来源区域仍然清晰可读。 将 JSON 视为规范的可编辑产物;HTML 则是可共享视图。

Quality gates

质量门槛

A finished map must satisfy all of these:
  • exactly one
    position
    has incoming reasoning;
  • every evidence node names one source and participates in an edge;
  • every source is used and has dates, a bounded locator, and a substantive excerpt;
  • every non-position node has a directed path to the position;
  • the reasoning graph has no duplicate edges or directed cycles;
  • contrary or qualifying evidence is present when the source set contains it;
  • each decision-changing gap is an explicit
    unknown
    node;
  • every edge note explains support, contradiction, qualification, or absence;
  • the verdict is no broader than the evidence.
完成的图谱必须满足以下所有条件:
  • 恰好一个
    position
    节点拥有传入的推理关系;
  • 每个
    evidence
    节点都指定一个来源并参与至少一条边;
  • 每个来源均被使用,且具有日期、边界明确的定位信息和实质性摘录;
  • 每个非
    position
    节点都有一条通向
    position
    的有向路径;
  • 推理图谱中不存在重复边或有向环;
  • 来源集合中包含相反或限定性证据时,图谱中必须呈现这些证据;
  • 每个可能改变决策的缺口都对应一个明确的
    unknown
    节点;
  • 每条边的说明都解释支持、矛盾、限定或缺失关系;
  • 结论的宽泛程度不得超过证据所能支持的范围。

Deliver the result

交付结果

Report:
  • the current position in one sentence;
  • the strongest counterevidence or qualification;
  • the most important unresolved unknown;
  • paths to the canonical JSON and any rendered HTML;
  • whether deterministic validation and explicit source verification ran.
Never describe a structurally valid map as proven true. Validation establishes traceability and graph integrity; source quality and inference quality still require human review.
报告:
  • 用一句话说明当前立场;
  • 最有力的反证或限定条件;
  • 最重要的未解决未知项;
  • 规范 JSON 及任何已渲染 HTML 的路径;
  • 是否运行了确定性验证和明确的来源核验。
绝不能把结构上有效的图谱描述为已被证明正确。 验证只能确立可追溯性和图谱完整性;来源质量和推理质量仍需人工审查。