kicad-happy
SkillCommunity
Eleven design-review skills that parse KiCad schematics, boards and Gerbers, then check power trees, EMC risk and SPICE behaviour. By aklofas.
1.6k starsUpdated 2 days agoGitHub data from 5 Nov 2026
At a glance
- Type
- Skill
- Tool versions
- KiCad 5 to 10 (KiCad 5 legacy .sch and .lib included)
- Operating systems
- Windows, macOS, Linux
- Needs a KiCad licence
- No
- AI clients documented
- Claude Code, Codex, GitHub Copilot CLI, Google Antigravity, opencode
- Licence
- MIT
- Language
- Python
What it can do
- Parses .kicad_sch, .kicad_pcb and Gerber files with pure Python scripts, with no KiCad install needed, and traces nets, regulators and feedback dividers into a power tree.
- Checks ESD coverage on connectors, decoupling, crystal load capacitance and BOM readiness, and suggests applicable EMC certifications.
- A spice skill writes testbenches for detected subcircuits and runs them in ngspice, LTspice or Xyce, including Monte Carlo tolerance runs.
- An emc skill runs 44 pre-compliance rule checks; other skills cover datasheets, BOM sourcing and suppliers such as DigiKey, Mouser, LCSC, JLCPCB and PCBWay.
- Also runs as a GitHub Action that reviews pull requests touching KiCad files.
Limitations
- Findings come from file analysis and closed-form checks, not from KiCad's own ERC or DRC engine.
- The author notes that Claude Code's /plugin update may miss new versions; reinstall to update.
Install
/plugin marketplace add aklofas/kicad-happy
/plugin install kicad-happy@kicad-happySource: github.com/aklofas/kicad-happy
agy plugin install https://github.com/aklofas/kicad-happy.gitSource: github.com/aklofas/kicad-happy
MCP servers and skills run code on your computer. Review the source before installing.
AI-generated models, drawings and results must be checked by a qualified engineer before use.