circuit-synth
Create and design PCB circuits using Python and KiCad with AI assistance. Generate circuits from natural language descriptions, existing documentation, or templates. Search components, manage BOMs, and produce manufacturing-ready outputs.
What this skill does
# Circuit-Synth: AI-Assisted PCB Design
Professional circuit design using Python + KiCad + AI. Define circuits in code, leverage pre-made patterns, and generate manufacturing-ready outputs.
**Tool Reference:** This skill uses [circuit-synth](https://github.com/circuit-synth/circuit-synth), a Python library for programmatic PCB design with KiCad integration.
**Additional Resources:**
- `reference.md` - Quick reference for commands, patterns, and workflows
- [Official Documentation](https://circuit-synth.readthedocs.io)
## What is Circuit-Synth?
Circuit-synth brings software engineering practices to hardware design:
- Define circuits in Python instead of GUI clicking
- Hierarchical design with modular subcircuits
- Version control friendly (text-based definitions)
- AI-accelerated design workflows
- Professional KiCad output (.kicad_pro, .kicad_sch, .kicad_pcb)
- Manufacturing exports (BOM, Gerbers, PDF schematics)
## Quick Start (60 seconds)
```python
# 1. Install
uv add circuit-synth reportlab
# 2. Create circuit (circuits/my_board.py)
from circuit_synth import circuit, Component, Net
@circuit(name="MyBoard")
def my_circuit():
vcc = Net('VCC')
gnd = Net('GND')
led = Component(
symbol="Device:LED",
ref="D",
value="Red",
footprint="LED_SMD:LED_0805_2012Metric"
)
res = Component(
symbol="Device:R",
ref="R",
value="330R",
footprint="Resistor_SMD:R_0805_2012Metric"
)
# Connect: VCC -> Resistor -> LED -> GND
res["1"] += vcc
res["2"] += led["A"]
led["K"] += gnd
if __name__ == "__main__":
import os
os.makedirs("circuits", exist_ok=True)
my_circuit()
# 3. Generate
# uv run python circuits/my_board.py
# 4. Open in KiCad
# kicad circuits/MyBoard/MyBoard.kicad_pro
```
**That's it!** For advanced usage, see sections below or check `reference.md`.
## When to Use This Skill
Use circuit-synth when:
- Creating new PCB designs from scratch
- Generating circuits from natural language descriptions
- Converting hardware documentation/pinouts into formal schematics
- Reverse-engineering existing hardware into KiCad format
- Searching for components with real-time stock/pricing
- Designing with pre-made manufacturing-ready patterns
- Producing manufacturing outputs (BOM, Gerbers, PDF)
## When NOT to Use This Skill
Skip circuit-synth when:
- User just wants schematic symbols/footprints without circuit design
- Working with non-KiCad tools (Altium, Eagle, etc.)
- Project requires Python < 3.12
- Simple one-off circuit not worth the setup
## Installation and Setup
### Quick Start Installation
**Check if already installed:**
```bash
pip list | grep circuit-synth
```
**If not installed:**
In existing Python project (has `pyproject.toml`):
```bash
uv add circuit-synth
```
In non-Python project or new setup:
```bash
uv init --bare # Creates pyproject.toml
uv add circuit-synth
```
Fallback with pip:
```bash
pip install circuit-synth
```
**Recommended: Install reportlab for PDF schematic generation:**
```bash
uv add reportlab
# or
pip install reportlab
```
Without reportlab, you'll see warnings and won't be able to generate PDF schematics.
That's it! No need to ask permission - just provide these commands when needed.
### Python Version Requirement
Circuit-synth requires **Python 3.12 or higher**.
Check Python version:
```bash
python --version
# or
python3 --version
```
If Python < 3.12, inform user and ask if they want to proceed with installation anyway or upgrade Python first.
### Common Installation Issues
| Error | Fix |
|-------|-----|
| `No module named 'circuit_synth'` | Run `uv add circuit-synth` or `pip install circuit-synth` |
| `No pyproject.toml found` | Run `uv init --bare` first, then `uv add circuit-synth` |
| `Python version too old` | Requires Python 3.12+, upgrade with pyenv or conda |
## Common Pin Naming Issues
**Most common source of errors!** When you get `Pin 'XXX' not found` errors, the error message shows available pins. Use those names.
### Quick Reference Table
| IC Family | Common Wrong Names | Correct Names | Example |
|-----------|-------------------|---------------|---------|
| 74xx Latches (373, 573) | 1D, 1Q, 2D, 2Q | D0-D7, O0-O7 | D0 for data in, O0 for output |
| 74xx Buffers (245) | DIR, OE | A->B, CE | Direction control renamed |
| 74xx Decoders (138, 139) | 1G, 1A0, 1Y0 | E, A0, O0 | Single decoder uses generic names |
| Polarized Caps | +, - | 1, 2 | Pin 1 is positive, pin 2 negative |
| Generic symbols | Named pins | 1, 2, 3... | Use pin numbers for placeholders |
**How to fix:** When you see the error, it lists available pins - use those exact names in your code.
```python
# Error says: Available: 'D0', 'D1', ..., 'O0', 'O1', ...
# Wrong:
latch["1D"] += data_in # ❌
# Correct:
latch["D0"] += data_in # ✓
```
## Incremental Development (IMPORTANT!)
**Don't write the whole circuit at once!** Build and test incrementally to catch pin name errors early.
### Step 1: Minimal Test (1-2 components)
Start with just power and one IC:
```python
from circuit_synth import circuit, Component, Net
@circuit(name="Test")
def test_circuit():
vcc = Net('VCC_5V')
gnd = Net('GND')
# Test one IC first
ic = Component(
symbol="74xx:74HC373", # Or whatever you need
ref="U1",
value="Test",
footprint="Package_DIP:DIP-20_W7.62mm"
)
ic["VCC"] += vcc
ic["GND"] += gnd
ic["D0"] += Net('DATA0') # Try connecting one pin
ic["O0"] += Net('OUT0')
if __name__ == "__main__":
c = test_circuit()
c.generate_kicad_project(project_name="Test")
```
Run: `uv run python circuits/test.py`
### Step 2: Fix Pin Names from Error Messages
If it fails, read the error:
```
ComponentError: Pin 'D0' not found in U1 (74xx:74HC373).
Available: 'D0', 'D1', 'D2', ...
```
Use the available names shown in the error.
### Step 3: Add More Components Gradually
Once one IC works, add 2-3 more at a time, testing after each addition.
## Where Are My Files?
After running `circuit_obj.generate_kicad_project(project_name="MyBoard")`:
```
your-project/
└── circuits/ ← **CIRCUIT FOLDER**
├── your_circuit.py ← Your Python circuit definition
└── MyBoard/ ← **GENERATED HERE**
├── MyBoard.kicad_pro ← Open this in KiCad
├── MyBoard.kicad_sch
├── MyBoard.json
└── MyBoard.net
```
**Open it:** `kicad circuits/MyBoard/MyBoard.kicad_pro`
The `circuits/` folder keeps all circuit definitions and generated KiCad projects organized together.
## Common Errors & Quick Fixes
| Error | Cause | Fix |
|-------|-------|-----|
| `Pin 'X' not found` | Wrong pin name | Use exact names from error message |
| `Symbol 'XXX' not found` | Symbol doesn't exist in KiCad libraries | Try similar symbol (74HC139→74LS139) or use generic placeholder |
| `missing 1 required positional argument: 'project_name'` | Forgot parameter | Add `project_name="YourBoard"` |
| `No module named 'circuit_synth'` | Not installed | Run `uv add circuit-synth` |
| `No pyproject.toml found` | Not in uv project | Run `uv init --bare` first |
## Placeholder-First Approach for Custom/Unknown ICs
**Fast track for reverse-engineering or using ICs without KiCad symbols:**
### 1. Use Generic Symbols as Placeholders
Don't waste time searching for exact symbols. Start with placeholders:
```python
# Unknown or custom IC? Use Device:C (capacitor) as 2-pin placeholder
custom_ic = Component(
symbol="Device:C", # Quick 2-pin placeholder
ref="U1",
value="ActualPartNumber", # Document the real part
footprint="Package_DIP:DIP-20_W7.62mm" # Use actual footprint
)
# Connect using pin numbers
custom_ic["1"] += vcc
custom_ic["2"] += gnd
# Document actual connections in comments for later
# Pin 1: VCC, Pin 2: GND, Pin 3: DATA0, ... etc
```
### 2. Generate Schematic Quickly
- Get project structure in place
- See component layoRelated in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.