Agent skill
electronics-sourcing
Guide for AI agents to source electronic components using parts-mcp — tool sequencing, decision patterns, and multi-step workflows
Install this agent skill to your Project
npx add-skill https://github.com/andrewyng/context-hub/tree/main/content/sourceparts/skills/electronics-sourcing
Metadata
Additional technical details for this skill
- tags
- electronics,sourcing,bom,components,pcb,manufacturing,workflow
- source
- maintainer
- revision
- 1
- updated on
- 2026-03-15
SKILL.md
Electronics Sourcing Skill
This skill teaches you how to source electronic components effectively using parts-mcp tools. It covers tool sequencing, decision patterns, and how to handle common scenarios.
When to Use Which Search Tool
search_parts — Use when you have a part number, description, or general keywords. This is your default starting point.
"Find me a 100nF capacitor" → search_parts(query="100nF capacitor")
"Look up STM32F411" → search_parts(query="STM32F411")
search_by_parameters — Use when you need to match specific electrical parameters within a category. More precise than keyword search.
"I need a 50V 100nF X7R 0402 cap" → search_by_parameters(
parameters={"capacitance": "100nF", "voltage": "50V", "dielectric": "X7R", "package": "0402"},
category="capacitor"
)
Decision rule: If the user gives you 3+ specific parameters, use search_by_parameters. For part numbers or general queries, use search_parts.
The Search → Price → Availability → Alternative Pattern
This is the core sourcing workflow. Follow this sequence:
1. SEARCH → Find the part
2. DETAILS → Get full specifications (if needed for validation)
3. PRICE → Compare across suppliers
4. AVAILABILITY → Check stock levels
5. ALTERNATIVE → Find replacements (only if price is too high or stock is insufficient)
Do not skip steps 3 and 4. A part that exists in the database may be out of stock or prohibitively expensive.
When the user asks to "source" or "find" a part, they expect pricing and availability — not just search results. Always follow through to at least step 4.
BOM Processing Pattern
BOM processing is asynchronous. Always follow this exact sequence:
1. upload_bom(file_path=path) → Get job_id
2. check_bom_status(job_id=job_id) → Poll until status is "complete"
3. Review matched_parts and unknown_parts
4. For unmatched: search_parts() to resolve manually
5. calculate_bom_cost() with all resolved parts
Polling: Call check_bom_status and check the status field. If "in_progress", wait and poll again. Do not assume instant completion.
Handling unmatched parts: When unknown_parts is not empty, try search_parts with the value and footprint fields as the query. If still unmatched, report them to the user — do not silently skip them.
Datasheet Reading Strategy
Datasheets can be hundreds of pages. Always use this two-step approach:
1. list_datasheet_sections(sku="PART-NUMBER")
→ See the table of contents
→ Identify which sections contain what you need
2. read_datasheet(sku="PART-NUMBER", query="relevant keywords")
→ Read only matching chunks
→ Saves significant context window
Never call read_datasheet without a query parameter unless the datasheet is short (< 20 pages). An unfiltered read of a 200-page datasheet will consume excessive context.
Keyword tips: Use specific technical terms. "maximum input voltage absolute ratings" is better than "voltage". Multiple keywords narrow the results.
Manufacturing Pipeline
Manufacturing operations (DFM, fab quoting, assembly) are all asynchronous:
submit_dfm() → check_dfm_status() # DFM analysis
quote_fabrication() → check_manufacturing_status() # Fab quote
quote_assembly() → polls internally # Combined fab + assembly
DFM first: Always run DFM analysis before requesting a fabrication quote. DFM may reveal issues that affect manufacturability or cost.
Assembly quotes combine fabrication and BOM costing in one call. Use quote_assembly when the user wants a complete per-unit cost including both PCB fabrication and component assembly.
Handling Partial Failures
Real-world sourcing often has partial results. Handle gracefully:
Some parts not found in BOM:
- Report the unmatched count clearly
- Attempt
search_partsfor each unmatched part - If still unmatched, list them for the user with their reference designators and values
- Calculate cost for matched parts, noting the incomplete total
Some parts unavailable:
- Report which parts are out of stock
- Automatically call
find_alternativesfor each unavailable part - Present alternatives with their specifications and pricing
- Let the user decide on substitutions
Price comparison with missing suppliers:
- Report how many suppliers were checked
- Note if key suppliers (the user's preferred ones) returned no results
- Present available pricing data without waiting for all suppliers
KiCad Project Workflow
When working with KiCad projects:
1. find_kicad_projects() → Discover available projects
2. analyze_kicad_project(project_path=...) → Understand project structure
3. extract_bom_from_kicad(project_path=...) → Get component list
4. match_components_to_parts(components=...) → Match to real parts
5. Follow the BOM processing pattern above for unmatched components
KiCad CLI requirement: BOM extraction may invoke kicad-cli if no existing BOM file is found in the project. Ensure KiCad 8+ is installed.
Local mode only: All KiCad tools require local mode (stdio transport). They are not available in hosted/HTTP mode.
Cost Optimization Tips
When helping users optimize costs:
- Check quantity breaks: Call
compare_priceswith different quantities (1, 10, 100, 1000) to show price break curves - Suggest alternatives: If a part is expensive, call
find_alternativesand compare pricing - Preferred suppliers: Use
preferred_suppliersincalculate_bom_costto bias toward the user's existing supplier relationships - Consolidation: When multiple parts come from the same supplier, note the potential for consolidated shipping
Response Patterns
When a user asks to "source a part":
→ search_parts → get_part_details → compare_prices → check_availability
Present: part details, best price, stock status, and any concerns.
When a user provides a BOM file:
→ upload_bom → poll check_bom_status → report matched/unmatched → calculate_bom_cost
Present: match rate, unmatched items, total cost, per-line breakdown.
When a user asks "is this in stock?":
→ check_availability with quantities
Present: stock levels, number of suppliers with stock, whether quantity is meetable.
When a user asks about a datasheet:
→ list_datasheet_sections → read_datasheet with targeted query
Present: the specific information requested, citing page numbers.
When a user asks for a manufacturing quote:
→ submit_dfm (if not already done) → quote_fabrication or quote_assembly
Present: DFM issues (if any), estimated cost, lead time.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
login-flows
Common login automation patterns for web apps using Playwright
document-extraction
Use this skill for intelligent document processing and content extraction using LandingAI's Agentic Document Extraction (ADE). Trigger when users need to (1) Parse documents (PDFs, images, spreadsheets, presentations) into structured Markdown with layout understanding, (2) Extract specific structured data from documents using schemas (invoice fields, form data, table data, etc.), (3) Classify and separate multi-document batches by type (invoices vs receipts, statements vs forms, etc.), (4) Process large documents asynchronously (up to 1GB/1000 pages), (5) Get visual grounding (bounding boxes, page numbers) for extracted content — use when users mention bounding boxes, word locations, grounding, highlighting extracted content, or showing where data appears in a document. Use this skill when the task involves understanding document content for a set of documents. In particular this skill can help you write code that run on sets of documents. This will increase speed, and reduce the cost of loading the documents on the Agent context window because you can use a single script to extract the information needed.
document-workflows
Use this skill for building end-to-end document processing workflows and pipelines using LandingAI ADE. Trigger when users need to: (1) Process batches of documents in parallel or async, (2) Build classify-then-extract pipelines for mixed document types, (3) Prepare parsed documents for RAG systems with chunking and vector DB ingestion, (4) Load extraction results into databases like Snowflake or export to CSV/DataFrames, (5) Visualize extraction results: draw bounding box overlays on pages, crop chunk images, or highlight/annotate specific words or phrases found in documents, (6) Build Streamlit or web UIs for document processing, (7) Find and highlight specific terms within document sections using word-level grounding (e.g. highlight "L2S" in the Introduction, redact PII, annotate extracted values on the original page). This skill complements the document-extraction skill which covers ADE SDK basics. Use document-extraction to write code that executes parse/extract/split operations with more precision and less cost than adding the document image to the prompt and asking the LLM to find the relevant info. Use document-workflows when composing those operations into pipelines, or when you need visualization, annotation, or word-level grounding on parsed documents.
new-project
Build a new AI agent with Olakai monitoring from scratch — project setup, SDK integration, KPI configuration, and end-to-end validation
integrate
Add Olakai monitoring to existing AI code — wrap your LLM client, configure custom KPIs, and validate the integration end-to-end
tavily-best-practices
Build production-ready Tavily integrations with best practices for web search, content extraction, crawling, and research in agentic workflows, RAG systems, and autonomous agents
Didn't find tool you were looking for?