pjcau

Full PCB verification loop using local kicad-cli (DRC + 3D render + gerbers)

Create a new Claude Code skill for this project. Use when you need to add a new skill, improve an existing skill, or convert a workflow into a reusable skill.

Verifies that every PCB pad-to-net assignment matches the manufacturer datasheet pin specifications. Use when changing board.py/routing.py/footprints.py, after GPIO remapping, before releases, or when adding new components. Automated guard against wiring errors like unconnected VBUS, wrong pin assignments, or missing GND connections.

Design intent adversary — cross-checks GPIO, nets, power chains, signal paths across firmware/schematic/PCB/datasheet sources to find lost connections and inconsistencies

Analyze a DFM report and fix all issues in the PCB generation scripts

Run DFM guard tests and add new regression tests after fixing PCB issues

Scan all documentation against source-of-truth files (config.py, board_config.h, routing.py, BOM, PCB) and report/fix outdated values. Use after PCB changes, GPIO remapping, BOM updates, or before releases.

Full KiCad DRC audit — catches net shorts, unconnected pads, dangling vias, and clearance violations that custom scripts miss

Epic feature development — break a large feature into phased stories, then execute each phase via /feature. Use when building multi-phase features, large initiatives, or features that span multiple components/layers.

Review code changes for quality, security, and correctness. Use this before merging PRs, after significant refactors, or when reviewing agent output.

Review and optimize LLM API costs in the orchestrator. Analyze model routing, budget tracking, prompt caching, and retry logic for cost efficiency.

Deploy services using Docker/OrbStack. Use this to build and deploy containers, run health checks, and manage deployments.

Review production code and update all documentation under docs/ to match the current codebase state.

Build and manage Docker containers via OrbStack. Use this to build images, run containers, check service health, and manage docker-compose services.

End-to-end feature development — implement, iterate with user feedback, test, SOLID review, document, commit & push. Use when building a new feature or making a significant code change that needs quality assurance.

Fetch GitHub starred repos, analyze one with LLM, and propose improvements via PR

Learning-path test for the orchestrator. Pick a project goal, run it through the local stack, issue 5 follow-up iterations (modifications or new features), verify the final output against the accumulated requirements, and append a dated log under docs/learning-path-tests/ so runs can be compared over time. Produces a confidence score (0-100) with breakdown and 3 concrete improvement proposals.