Find and add components, modules, and reference designs to a Zener project. Use this workflow any time you need a part or subcircuit that isn't already in the workspace or covered by stdlib generics.
Works with
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versioncomponent-searchExecute the skills CLI command in your project's root directory to begin installation:
Fetches component-search from diodeinc/pcb and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate component-search. Access via /component-search in your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Create detailed user stories, acceptance criteria, and feature specs
Example
Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios
Reduce spec writing time by 50%, ensure comprehensive coverage
Research competitors, compare features, identify gaps
Example
Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities
Complete competitive research in 2 hours instead of 2 days
Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs
Example
Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale
0
total installs
0
this week
204
GitHub stars
0
upvotes
Run in your terminal
0
installs
0
this week
204
stars
Find and add components, modules, and reference designs to a Zener project. Use this workflow any time you need a part or subcircuit that isn't already in the workspace or covered by stdlib generics.
If pcb search and pcb new component do not produce a usable part, do not manually create the component, symbol, or footprint by default. Briefly say what failed, say you can try making it manually, and get explicit user confirmation first. In interactive mode, prefer ask.
Always search in this order. Move down only when the higher tier doesn't have what fits.
pcb search -m registry:modules <query> -f json — Pre-designed, validated subcircuits (modules and reference designs). Best option: the design work is already done, with passives, layout, and validation included.pcb search -m registry:components <query> -f json — Pre-packaged component definitions in the registry. Good: symbol, footprint, and .zen file already exist and are ready to use.pcb search -m web:components <MPN> -f json — Diode's web component database (CSE, LCSC sources). Fallback: returns a component_id that must be imported with pcb new component.If the user asks for a specific MPN, still try registry first before falling back to web.
"buck converter 3.3V", "Texas Instruments LDO", "USB-C connector"."TPS54331", "STM32F103C8T6". Do NOT include descriptions, keywords, or functional terms in the query — they will cause the search to fail or return irrelevant results. Strip everything except the MPN.-f json. Parse results programmatically to evaluate options.dependencies (what they use) and dependents (who uses them) for context.model_availability showing whether ECAD and STEP models are available. The same MPN may appear from multiple sources (DigiKey, CSE, LCSC) with different model availability; check all returned results before concluding models are unavailable.pcb doc --package <url>@<version> to inspect a registry module's io/config interface before using it.Pick when there's a clear winner. Present tradeoffs and ask only when genuinely ambiguous.
Selection heuristics in priority order:
availability fields for stock counts and pricing.dependents in registry results means more battle-tested.Registry modules and components (Flows 1 and 2) are used directly via Module() with the registry URL. Auto-dep handles pcb.toml updates automatically — just use the URL and build.
# Reference design from registry:modules search
LDO = Module("github.com/diodeinc/registry/reference/AP2112Kx/AP2112Kx.zen")
LDO(
name="LDO_3V3",
VIN=vbus_5v0,
VOUT=vdd_3v3,
GND=gnd,
)
# Component from registry:components search
TPS54331 = Module("github.com/diodeinc/registry/components/TPS54331D/TPS54331D.zen")
Use pcb doc --package <url>@<version> to check available io/config before wiring into a design.
Web component results (Flow 3) require an import step before use.
pcb search -m web:components <MPN> -f jsoncomponent_id, part_number, and manufacturer.pcb new component --component-id <ID> --part-number <MPN> --manufacturer <MFR>
This downloads the symbol, footprint, and STEP model, scans the datasheet, and generates a .zen file into components/<manufacturer>/<mpn>/. If the component already exists in the workspace, it skips and reports the existing path.
Module() with the local workspace path:ESP32 = Module("./components/Espressif_Systems/ESP32-S3-WROOM-1-N16R8/ESP32-S3-WROOM-1-N16R8.zen")
# Modules and reference designs (fast, local index)
pcb search -m registry:modules <query> -f json
# Pre-packaged components (fast, local index)
pcb search -m registry:components <query> -f json
# Web component database (network, slower, MPN-ONLY queries)
pcb search -m web:components <MPN> -f json
# Import a web component into the workspace
pcb new component --component-id <ID> [--part-number <MPN>] [--manufacturer <MFR>]
# Read a registry package's io/config interface
pcb doc --package <url>@<version>
pcb bomAfter adding components to a design, use pcb bom to check sourcing and availability:
pcb bom boards/MyBoard/MyBoard.zen -f json
The JSON output is a list of BOM entries, each with:
designator, mpn, manufacturer, package, value, descriptionavailability — per-entry sourcing data:
us / global — regional summary with price, stock, alt_stockoffers — individual distributor offers with region, distributor, stock, pricepart=Part(mpn=..., manufacturer=...) where appropriate.stock counts across regions. Parts with zero stock and only alt_stock may have long lead times.Make data-driven prioritization decisions faster
Draft PRDs, status updates, and stakeholder presentations
Example
Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement
Save 3-5 hours/week on communication overhead
Prerequisites
Time Estimate
30-60 minutes to see productivity improvements
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.
✗ Avoid when
Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.
kostja94/marketing-skills
mattpocock/skills
parcadei/continuous-claude-v3
cursor/plugins
ailabs-393/ai-labs-claude-skills
ailabs-393/ai-labs-claude-skills
component-search has been reliable in day-to-day use. Documentation quality is above average for community skills.
component-search reduced setup friction for our internal harness; good balance of opinion and flexibility.
Keeps context tight: component-search is the kind of skill you can hand to a new teammate without a long onboarding doc.
component-search is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
component-search fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
I recommend component-search for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
We added component-search from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
Useful defaults in component-search — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
component-search is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
Keeps context tight: component-search is the kind of skill you can hand to a new teammate without a long onboarding doc.
showing 1-10 of 40