MCPInstall

eda-research

Component research and procurement. Search JLC for components, analyze datasheets, compare options, and document selections with rationale.

Installs
73
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/l3wi/claude-eda --skill eda-research
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads eda-research automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

EDA Research Skill

Source and select components for electronics projects.

Auto-Activation Triggers

This skill activates when:

  • User asks to "find a component", "search for", "source"
  • User asks about component specifications or comparisons
  • User mentions LCSC, datasheets, or part numbers
  • User asks "what MCU/regulator/sensor should I use"
  • Project has design-constraints.json but missing component selections

Context Requirements

Requires:

  • docs/design-constraints.json (or prompt user for requirements)
  • docs/project-spec.md (optional, for context)

Produces:

  • docs/component-selections.md - Human-readable selection log
  • docs/bom-draft.json - Machine-readable BOM
  • datasheets/*.pdf - Downloaded datasheets for selected components

Workflow

1. Load Context

Read existing project constraints:

@docs/design-constraints.json
@docs/project-spec.md
@docs/component-selections.md (if exists)

If constraints missing, ask user for minimum requirements:

  • What does this component need to do?
  • Key specifications (voltage, current, package)?
  • Budget constraints?

2. Understand Requirements

For the target component role, identify:

  • Critical specifications (must-have)
  • Preferred specifications (nice-to-have)
  • Package preferences (SMD size, through-hole)
  • Any specific brands or series to consider/avoid

2.5 Check Architecture Constraints

Before searching, review design-constraints.json for:

  • Power topology: LDO vs buck decision already made in architect phase
  • Thermal budget: Max watts for this role (check thermal.hotComponents)
  • DFM targets: Assembly method affects package choice
  • Board layers: May affect component density

For power components, see reference/REGULATOR-SELECTION.md for selection criteria. For passives, see reference/PASSIVE-SELECTION.md and reference/DECOUPLING-STRATEGY.md.

3. Research Options

Use web search to understand:

  • Common solutions for this application
  • Recommended parts from reference designs
  • Known issues or considerations
  • Alternative approaches

4. Search JLC

Use mcp__jlc__component_search to find candidates:

  • Search with specific parameters
  • Filter by stock availability
  • Note pricing at target quantity
  • Check for "Basic" parts (lower assembly fee at JLCPCB)

5. Analyze Candidates

For top 3-5 options:

  • Download/fetch datasheets
  • Extract key specifications
  • Check application circuits
  • Note layout requirements
  • Identify any gotchas

5.5 Validate Against Constraints

Before presenting options, verify each candidate:

Thermal validation:

P_dissipation = (calculated from datasheet)
Thermal budget = (from design-constraints.json)
✓ P_dissipation < Thermal budget

Assembly compatibility:

  • Hand assembly → 0603/0805 minimum, no fine-pitch
  • Reflow → 0402+ OK
  • Turnkey → Check JLCPCB availability

Architecture compliance:

  • Meets LDO/buck decision from architect phase
  • Noise specs OK for rail type (analog vs digital)
  • Efficiency acceptable for battery applications

Flag any candidates that fail validation with specific concerns.

6. Present Comparison

Create a comparison table:

PartMPNKey SpecsPriceStockProsCons
.....................

Include recommendation with rationale.

7. Confirm Selection

  • Get user confirmation
  • Document selection with rationale
  • Update constraint file
  • Save datasheet

8. Validate Symbol (After library_fetch)

When fetching online components with mcp__jlc__library_fetch, analyze the returned validation_data:

Quick checks:

CheckExpectedAction if Failed
pin_pad_count_matchtrueCheck for exposed pads (EP)
has_power_pinstrue (for ICs)Review pin types
has_ground_pinstrue (for ICs)Review pin names

Common issues:

  • QFN/BGA packages often have exposed thermal pads (EP) not included in symbol
  • Pin electrical types may be incorrect (power pins marked as passive)
  • Pin names may not match datasheet

Fixing with library_fix:

Use mcp__jlc__library_fix to regenerate symbol with corrections:

mcp__jlc__library_fix lcsc_id="C#####" corrections='{
  "pins": [
    { "action": "add", "number": "EP", "name": "GND", "type": "passive" },
    { "action": "modify", "number": "1", "set_type": "power_in" }
  ]
}'

Correction actions:

  • add - Add missing pin (number, name, type required)
  • modify - Rename and/or change electrical type
  • swap - Swap positions of two pins
  • remove - Remove incorrect pin

Output Format

component-selections.md Entry

### [Role]: [Part Name] ([LCSC Number])

**Selected:** [Date]
**MPN:** [Manufacturer Part Number]
**Manufacturer:** [Name]
**Price:** $X.XX @ [quantity]

**Specifications:**
- Key spec 1: value
- Key spec 2: value

**Rationale:**
[Why this part was chosen over alternatives]

**Alternatives Considered:**
- [Part 2] - rejected because [reason]
- [Part 3] - rejected because [reason]

**Design Notes:**
- [Any layout or application notes from datasheet]

**Datasheet:** `datasheets/[filename].pdf`

bom-draft.json Entry

{
  "role": "regulator-3v3",
  "lcsc": "C6186",
  "mpn": "AMS1117-3.3",
  "manufacturer": "AMS",
  "description": "3.3V 1A LDO Regulator",
  "value": "3.3V",
  "footprint": "SOT-223",
  "quantity": 1,
  "unitPrice": 0.04,
  "extendedPrice": 0.04,
  "category": "power",
  "basic": true
}

Component Role Categories

See reference/COMPONENT-CATEGORIES.md for detailed role definitions.

Common roles:

  • mcu - Main microcontroller
  • regulator-Xv - Voltage regulators
  • crystal - Oscillators/crystals
  • connector-* - Various connectors
  • esd-* - ESD protection
  • decoupling-* - Bypass/bulk capacitors
  • led-* - Indicator LEDs
  • sensor-* - Various sensors

Guidelines

  • Prefer JLCPCB "Basic" parts when suitable (lower assembly cost)
  • Check stock levels - avoid parts with < 100 in stock
  • Consider package size vs hand soldering capability
  • Note lead times for non-stock items
  • Always document why a part was chosen
  • Download datasheets for all selected components
  • Identify 1-2 alternatives for critical components (see reference/COMPONENT-ALTERNATIVES.md)
  • Validate thermal before confirming power components
  • Check architecture decisions from design-constraints.json before selecting

Reference Documents

DocumentUse For
REGULATOR-SELECTION.mdLDO vs Buck selection criteria
DECOUPLING-STRATEGY.mdCapacitor values for ICs
PASSIVE-SELECTION.mdResistor/capacitor fundamentals
COMPONENT-ALTERNATIVES.mdFinding equivalent parts
DATASHEET-ANALYSIS.mdExtracting key specs
COMPONENT-CATEGORIES.mdRole naming conventions
JLC-SEARCH-TIPS.mdSearch strategies

Next Steps

After component selection is complete:

  1. Run /eda-source for remaining components
  2. When all components selected, run /eda-schematic
  3. Update design-constraints.json stage to "schematic"

FAQ

What does the eda-research skill do?

Component research and procurement. Search JLC for components, analyze datasheets, compare options, and document selections with rationale.

How do I install eda-research?

Run npx skills add https://github.com/l3wi/claude-eda --skill eda-research in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/eda-research/ (personal) or .claude/skills/eda-research/ (project).

Which AI agents can use eda-research?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is eda-research safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains eda-research?

It is published by l3wi in l3wi/claude-eda. It has 73 recorded installs.

More from l3wi/claude-eda

View all →

eda-schematics

l3wi/claude-eda

Schematic capture and wiring. Create schematic sheets, place symbols, add wires and net labels, organize hierarchical designs.

491 installs

eda-pcb

l3wi/claude-eda

PCB layout and routing. Component placement, trace routing, copper pours, design rule configuration, and layout optimization for manufacturability.

Frontend & Design467 installs

eda-drc

l3wi/claude-eda

Design validation and review. Run DRC/ERC checks, verify against constraints, check component availability, and prepare comprehensive validation reports.

Frontend & Design160 installs

eda-architect

l3wi/claude-eda

Electronics project architecture and constraint definition. Guides users through defining project requirements, power systems, interfaces, and physical constraints.

Popular productivity & automation skills

View category →

agent-browser

vercel-labs/agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

OfficialProductivity & Automation1.3M installs

lark-doc

open.feishu.cn

飞书云文档(Docx / Wiki)内容操作:读取、创建、编辑文档,插入或下载图片附件,以及操作思维笔记。用户提供文档 URL/token(包括 doubao.com 的 /docx/、/wiki/)时使用;按 URL 路径/token 而非域名路由;/page/ 是妙搭应用,非飞书云文档。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive;随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。

lark-base

open.feishu.cn

飞书多维表格(Base)操作:建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式(BaseApp/AppMode 页面与组件)、Workspace 目录、workflow、角色权限、模板中心(多维表格模板分类/列表/搜索);遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps;文件导入/导出转 lark-drive,认证/授权转 lark-shared。

lark-drive

open.feishu.cn

飞书云空间(云盘/云存储):管理 Drive 文件和文件夹,包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、查询权限设置、评论/权限/订阅、标题、版本、飞书文档密级标签(secure labels)和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题,或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用;doubao.com 云空间 URL/token 也按资源路径和 token 路由,不回退 WebFetch。不负责:文档内容编辑(走 lark-doc)、表格/Base 表内数据操作(走 lark-sheets/lark-base)、知识空间节点/成员管理(走 lark-wiki)、原生 Markdown 文件读写/patch/diff(走 lark-markdown)。

lark-shared

open.feishu.cn

Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling notice JSON.

lark-im

open.feishu.cn

飞书即时通讯:收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片(Interactive Card)、监听卡片按钮回调(card.action.trigger)。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶(添加/移除/查询置顶会话)、管理标签数据、处理卡片回调时使用。