科研 Skill

硬件项目实验记录管理

lab-notebook

Maintains a hardware project’s knowledge base: task cycle, facts with evidence, experiment verdicts, and per-stage reports. Use at the start and end of every project stage.

发布者 Codar安全审核通过v0.1.0更新于 2026-11-18

SKILL.md

Lab notebook

Hardware projects regress when nobody records what was tried. A fix undoes an earlier fix. A measurement gets repeated. A failed idea comes back a week later. An agent's findings are lost when the conversation ends. This skill makes every stage leave the project better documented than it found it.

Talk to the user in their language. Write the notebook in English, unless the user chose another language for project files.

Inputs and outputs

  • Inputs: hw/state.json, hw/knowledge/, hw/decisions.md.
  • Outputs: the files below. This skill owns them.
hw/knowledge/FACTS.md        F-001…  measured or verified facts
hw/knowledge/EXPERIMENTS.md  E-001…  what was tried, with a verdict
hw/knowledge/LESSONS.md      L-001…  rules learned, including user corrections
hw/retros/YYYY-MM-DD-<stage>.md       one report per stage or large task
hw/agents/YYYY-MM-DD-<task>.md        the report of each subagent, saved on arrival

Copy the headers from templates/ the first time.

1. Start of a stage

  1. Read hw/state.json, then hw/knowledge/LESSONS.md. Each lesson that applies to this stage is a rule.
  2. Search FACTS.md and EXPERIMENTS.md for the subject (grep -n -i <word> hw/knowledge/*.md).
    • A fact with evidence is not measured again unless the design changed. Cite its ID.
    • An experiment with the verdict did not work is not repeated without a new hypothesis. Write the hypothesis down first.
  3. If other agents work in the same project, find their files first (git status, file modification times). Do not edit, move or commit their files.

2. During the stage

  • Record facts at the moment you find them. One entry has:

    • an ID;
    • the date;
    • the statement with its value and unit;
    • an evidence tag (CONVENTIONS.md §6);
    • the command or source that reproduces it.

    A number lives only in its fact. Other files cite the ID.

  • Record each experiment with a verdict: worked, did not work or inconclusive. Add the reason and what would change the verdict. Record failures too, because they keep the next session from repeating them.

  • Take a new ID when you write the entry, not from memory. Run scripts/notebook_check.py --next F to get the next free ID. With parallel agents, give each agent its own range (F-2xx, F-3xx) and name the range in its brief.

  • Write each user correction as a lesson when it happens. Record the user's words, what was wrong and the rule that prevents it. Examples of real corrections:

    • "the shape makes no sense, it has to be straight" → L: pouch cells have straight edges;
    • "something is poking through" → L: validate before any render.
  • Regression rule. If a change brings back a failure that an earlier change fixed:

    1. stop;
    2. write an experiment entry for both changes;
    3. find the shared cause, usually the order of operations or two owners of one value;
    4. change the order or the ownership.

    Do not try a third variant of the same fix.

  • Parallel agents.

    • Before you split the work, freeze a common base and run its checks.
    • Agree the file formats.
    • Give each agent its own files.
    • Save each agent's report to hw/agents/ the moment it arrives.
    • Merge one file at a time.

3. End of a stage (checklist)

  1. Verify. Run the checks of the stage's skill, for example bom_check.py, the assembly validator or DRC. Write what was not verified.
  2. Knowledge. Add new F-, E- and L- entries. When a fact changes, write a new entry, and mark the old one SUPERSEDED on <date> by F-xxx: <what changed>. Do not delete it.
  3. Decisions. Add decisions to hw/decisions.md.
  4. State. Update hw/state.json: stage status, gate evidence, open questions.
  5. Report. Write hw/retros/YYYY-MM-DD-<stage>.md from templates/retro.md:
    • the request;
    • what was done and verified;
    • what was not verified;
    • the user's interventions;
    • mistakes and their causes;
    • the lessons added;
    • what is next.
  6. Check. Run scripts/notebook_check.py hw/. It must report no duplicate IDs, no fact without evidence, and no experiment without a verdict.
  7. Commit, only if the user wants commits. Never add attribution lines that the user did not ask for.

Writing rules for project files

These rules apply to every file in hw/. They are adapted from the concise skill (MIT) and from ASD-STE100 controlled language. The full list is in references/writing-rules.md.

  • Use only these normative words: must, must not, should (a deviation needs a written reason), can. Do not use "shall", "may", "ideally" or "try to".
  • Write each fact once, in its owner file. Elsewhere, refer to it by ID (F-012, REQ-004, D-007).
  • Replace vague words with values: "small" → "≤ 30 × 30 × 9 mm", "low power" → "≤ 1.5 mA average", "about 2 weeks" → "10–15 working days [estimate]".
  • Use digits and units with a space: 3.3 V, 68 mAh, 0.35 mm. Repeat the unit in ranges: 2 mA to 4 mA.
  • Keep sentences short: 20 words or fewer for instructions, 25 or fewer for descriptions. Use active voice.
  • Use one term for one thing. Put part numbers, file names, nets and commands in code format.
  • Do not announce, summarize or restate. Each sentence adds a fact, an instruction or a decision.

Gate

The stage closes when notebook_check.py passes, the retro exists and hw/state.json is updated.

Taste and pitfalls

  • An agent report that stays only in the conversation is lost. Save it to a file on arrival.
  • Two agents that take "the next ID" at the start of their tasks collide. Take the ID when you write. This includes open-question IDs in hw/state.json: give each parallel agent its own prefix or range (Q-RF-, Q-PW-). In one real run, two research agents both created Q-07 to Q-09.
  • A number copied into three documents goes stale in two of them. Keep it in one fact and cite the ID.
  • A failed experiment that is not written down gets tried again. Record failures with the same care as successes.
  • A lesson written only in the chat is forgotten in the next session. Write it in LESSONS.md at the moment of the correction.

示例提示词

帮我把这个阶段的实验结论和经验教训整理进项目笔记里。

所属插件

电子电气与信息工程面向电气与电子工程研究:电力系统仿真(PSS/E、PSLF、PowerWorld、pandapower、PyPSA、OpenDSS、ANDES)与越限/稳定/短路处置,FPGA 时序收敛与跨时钟域检查,电路与 PCB 设计评审,硬件产品开发流程。

安装该插件会一并获得同领域的 63 个 Skill / MCP。

同插件的其他科研 Skill

常见问题

硬件项目实验记录管理能做什么?

Maintains a hardware project’s knowledge base: task cycle, facts with evidence, experiment verdicts, and per-stage reports. Use at the start and end of every project stage。

如何安装硬件项目实验记录管理?

在科搭 Codar 左侧点击「插件」,在「组件」页签搜索「硬件项目实验记录管理」并安装;在 Claude Code 或 Codex 中可以发送本页的安装提示词,或下载 Skill 包后解压到 ~/.claude/skills 或 ~/.codex/skills。

硬件项目实验记录管理需要哪些权限?

该科研 Skill没有声明额外权限;执行具体操作时仍由 Agent 按自身规则请求确认。

硬件项目实验记录管理经过官方审核吗?

是。SpeedSkills 收录的每个版本都会记录内容摘要与权限声明,当前版本已通过安全审核。