select-parts

select-parts is a skill for Claude Code from Jinchen-Yang/diansai-skill. It costs 119 tokens per session (933 once invoked), scanned A, original, MIT.

A component-selection workflow for choosing electronic parts from an organiser’s parts list and producing a bill of materials, or BOM—a structured list of parts needed to build a device.

In plain words
What is it for?
Use it to read parts-list PDFs or text, select parts for each subsystem, record specifications and sources in a BOM, and prepare the list for human approval.
Why use it?
It helps match available components to voltage, current, interface, quantity, and other design requirements before purchasing. Missing parts can be identified and marked for separate sourcing.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to read parts-list PDFs or text, select parts for each subsystem, record specifications and sources in a BOM, and prepare the list for human approval.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jinchen-yang/diansai-skill/select-parts
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Jinchen-Yang/diansai-skill --skill select-parts
Clone the repo
git clone --depth 1 https://github.com/Jinchen-Yang/diansai-skill

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for select-parts

README.md
[![agentmods](https://agentmods.dev/badge/skills/jinchen-yang/diansai-skill/select-parts/github.svg)](https://agentmods.dev/skills/jinchen-yang/diansai-skill/select-parts)
Your own site
<a href="https://agentmods.dev/skills/jinchen-yang/diansai-skill/select-parts"><img src="https://agentmods.dev/badge/skills/jinchen-yang/diansai-skill/select-parts/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for select-parts

Your own site · 80×15
<a href="https://agentmods.dev/skills/jinchen-yang/diansai-skill/select-parts"><img src="https://agentmods.dev/badge/skills/jinchen-yang/diansai-skill/select-parts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 119 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 933 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00119 $0.00933
Opus 5.5 $0.00048 $0.00373
Sonnet 5.5 $0.00024 $0.00187
Haiku 4.5 $0.00012 $0.00093

Measured 2mo ago against content hash ba1d2fd235c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

select-parts scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/select-parts/SKILL.md · 40 lines

What it actually says

select-parts —— 选材(流水线 ④)

lane: lead · needs: multimodal(解析配件表 PDF → 只 lead/Claude lane 跑) · 门: 人工批 BOM

候选器件来自主办方当年配件表(不是凭空选、也不是固定库存)。从中按需求挑,金奖经验加持。

前置

  • design/solution.md(需求表)。没有先跑 /plan-solution。
  • inputs/partslist/ 里有配件表(PDF/文本)。没有就提醒投喂,停。

步骤

  1. 解析配件表:Read inputs/partslist/ 文件(PDF 多模态直接读),列出候选器件表:类别 / 型号 / 关键参数 / 数量(主办方给的可用项)。
  2. 逐子系统选型:对 solution.md 子系统清单每一项,从候选表里挑满足需求的件。判据按序:
    • 满足需求表的硬指标(电压/电流/接口/电平/数量);
    • 查 KB 03/04/05 的引脚说明 + 选型理由 + 金奖经验(Read),优先 KB 里点名好用、队伍熟悉的;
    • 满足供电(电机驱动撑得住堵转、稳压撑得住负载——交 power-design 复核)。
  3. 缺口回填:配件表里没有满足需求的,用 python tools/jlc_search.py "<规格>" 现查在库件作候选,标注"需额外采购",并记 LCSC/价格/库存。
  4. 写 design/bom.csv(列见下)。每件标来源(配件表/需采购)与对应子系统、对应 lib/modules 模块块(供 interconnect 用)。
  5. 人工门:把 BOM 摊给用户批准(尤其"需额外采购"项与关键件额定)。批准后更新 STATUS.md,提示可并行 /power-design 与 /interconnect。

design/bom.csv 列

subsystem,part,model,lcsc,qty,key_spec,source,module_block,note
电机驱动,TB6612FNG,TB6612FNG,C141517,1,VM≤13.5V/1.2A,配件表,tb6612fng,
主控,MSPM0G3507,MSPM0G3507,,1,M0+80MHz,配件表,mspm0g3507-min,
稳压(逻辑),AMS1117-3.3,AMS1117-3.3,C347222,1,3.3V/1A,需采购,,jlc查得
...

(module_block 对应 lib/modules/<name>.yaml,没有对应块就留空,interconnect 时按需补。)

注意

  • 绝不相信凭记忆的型号/参数:关键件额定(Vmax/Imax/封装/引脚)以配件表/数据手册为准;拿不准的标"待核手册"(读手册=多模态=lead)。
  • 电源轨能不能撑由 power-design 用 power_budget.py 复核,这里先保证选到候选。
  • 候选器件优先复用 lib/modules/ 已有的 known-good 接法块。
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2mo ago First seen · 40 lines · 119 tokens per session scan A ba1d2fd235c7

Subscribe to this mod's changes

select-parts is a skill published in the GitHub repository Jinchen-Yang/diansai-skill (12 stars, last pushed 3mo ago), licensed MIT. It adds 119 tokens to every session and 933 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

select-parts compared with skills from other repositories

select-parts next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
select-partsJinchen-Yang/diansai-skillSkill123mo agoMITA119Claude Code
mspm0-ccsmc3545dada/mspm0-skillSkill3783mo agoMITA101Claude Code, Codex
mspm0-skillIbook000/mspm0-skillSkill131mo agoMITA76Claude Code, Codex
volt-otatonone-ai/tononeSkill7723d agoMITA70Claude Code
volt-firmwaretonone-ai/tononeSkill7723d agoMITA76Claude Code
agentic-hilagentic-hil/agentic-hilSkill24yesterdayApache-2.0A104Claude Code
iot-expertpersonamanagmentlayer/pclSkill4411d agoApache-2.0A59Claude Code