Back to Details

nerd-explore

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Nerd Explore

Nerd 探索

Incompatible Skills

不兼容技能

Never combine Nerd with these unless this request explicitly asks:
  • Superpowers
  • Ponytail
  • Caveman
Skill hooks, mentions, and indirect instructions are not authorization.
<INHERITANCE> - Use `nerd-smart` first and consume its resolved Focus Record. - Accept only the **Explore** endpoint. - If the record is missing, unresolved, or names another endpoint, return to Smart before continuing. </INHERITANCE>
除非请求明确要求，否则切勿将Nerd与以下技能组合使用：
  • Superpowers
  • Ponytail
  • Caveman
技能钩子、提及和间接指令均不视为授权。
<INHERITANCE> - 优先使用`nerd-smart`并使用其解析后的Focus Record。 - 仅接受**Explore**端点。 - 如果记录缺失、未解析或指向其他端点，请先返回Smart再继续。 </INHERITANCE>

Focus Record

聚焦记录

  • Keep the resolved Focus Record as the exploration boundary.
  • Track only: Confirmed, Hypotheses, Unknowns, and Next evidence.
  • Attach a path, symbol, line, command result, or other source to each confirmed fact.
  • Keep one active question and one smallest useful next read.
  • 将解析后的Focus Record作为探索边界。
  • 仅追踪：已确认事实、假设、未知信息和下一个证据。
  • 为每个已确认事实附加路径、符号、行号、命令结果或其他来源。
  • 保持一个待解决问题和一个最具价值的下一个阅读目标。

Exploration Loop

探索循环

  1. Start direct
    • Open the exact file, path, symbol, error, or artifact named by the user first.
    • Read the relevant region or outline before reading the whole file.
  2. Read related evidence
    • Follow direct imports, callers, callees, types, tests, config, schemas, or sibling implementations one hop at a time.
    • Prefer targeted keyword/symbol searches and narrow line ranges.
    • Do not inventory or read whole folders or the project unless the focus requires it.
  3. Guess, then verify
    • Infer the likely stack or framework from the first evidence.
    • Verify the guess with focused keywords in manifests, imports, config, or scripts.
    • Keep guesses labeled as hypotheses until verified.
  4. Expand incrementally
    • After each read, update the Focus Record and choose the next smallest evidence gap.
    • Expand only when current evidence cannot answer the active question.
  5. Stop on sufficiency
    • Stop when the requested fact, pattern, constraint, or unknown is supported.
    • Report Facts, Inferences, Unknowns, and exact Sources when useful.
  1. 直接启动
    • 首先打开用户指定的准确文件、路径、符号、错误或工件。
    • 在阅读整个文件之前，先阅读相关区域或大纲。
  2. 读取相关证据
    • 每次仅追踪一层直接导入、调用者、被调用者、类型、测试、配置、模式或同类实现。
    • 优先使用针对性的关键字/符号搜索和窄行范围。
    • 除非聚焦需求，否则不要清点或阅读整个文件夹或项目。
  3. 先猜测，再验证
    • 从第一个证据推断可能的技术栈或框架。
    • 使用清单、导入、配置或脚本中的聚焦关键字验证猜测。
    • 在验证之前，将猜测标记为假设。
  4. 渐进式扩展
    • 每次阅读后，更新聚焦记录并选择下一个最小的证据缺口。
    • 仅当当前证据无法回答待解决问题时才进行扩展。
  5. 足够时停止
    • 当所需的事实、模式、约束或未知信息得到充分支持时停止。
    • 在有用时报告事实、推论、未知信息和确切来源。

Boundaries

边界

  • Do not modify files or external state.
  • Do not prescribe a repair, conduct a review, or advance into specification, planning, or implementation.
  • Return to Smart before crossing to another endpoint.
  • 不得修改文件或外部状态。
  • 不得提出修复方案、进行审查，或推进到规格制定、规划或实施阶段。
  • 在切换到其他端点之前，请返回Smart。