agentleFS
Jinchen-YangJinchen-Yang/diansai-skill/.claude/skills/power-design/SKILL.md

power-design

Skill9 starsChanged 4 months agoMITView on GitHub

设计多路隔离供电系统并校验余量。当用户要"设计供电/电源""算电流预算""选稳压/DCDC""分电源轨"时使用。按电机堵转电流(不是标称)算每轨负载,产出 design/power.yaml + power.md,并用 tools/power_budget.py 做确定性校验,需人工批准。

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

power-design —— 供电系统(流水线 ⑤)

lane: 任何模型(正确性交 power_budget.py) · 门: 人工批 + power_budget PASS

电源是 1 号翻车点:电机堵转瞬态把 MCU 拉掉电复位。一切按最坏情况算。

前置

design/solution.md(需求)+ design/bom.csv(选了哪些件/稳压)。

步骤

  1. 分轨(典型 4 轨,按方案裁剪):
    • VM_motor —— 电池直供电机驱动(不稳压,加保险/铺铜)。
    • V5_servo —— 舵机独立 5~6V 高电流轨(勿挂逻辑轨,堵转>1A)。
    • V3V3_logic —— MCU + 模拟传感器,AMS1117 或 buck。
    • V5_k230 —— K230 独立 5V(耗流远大于 MCU)。
  2. 派负载(Read KB 04/05 取电流;电机/舵机标 stall: true 用堵转电流)。稳压器从 bom.csv 取,没有就提示在配件表/jlc_search 选。
  3. 写 design/power.yaml(schema 见 tools/power_budget.py 头注;参考 examples/sending-medicine-2023/power.yaml)。
  4. 跑确定性门:python tools/power_budget.py design/power.yaml。FAIL(某轨欠流)就换更大稳压或加 buck,重跑直到 PASS。
  5. 写 design/power.md(人类可读:分轨图 + 预算表 + 选的稳压 + 注意),更新 STATUS.md。
  6. 人工门:用户确认稳压选型与电池容量。

关键纪律

  • 电机/舵机一律 stall: true;逻辑用标称。默认余量 30%。
  • 电机 VM 与逻辑 GND 分开回流再单点汇合(接线阶段落实)。
  • power_budget PASS 是必要非充分——电池容量/放电倍率、保险、铺铜宽度仍需人工核(接线阶段)。

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.