- Home
- Skills
- Agents & Orchestration
- pcb local ai
Works with the AI Agents you already use
pcb local ai
Assistant for KiCad PCB design workflows, component indexing, and automated engineering validation.
Free
pcb local ai
Example session with this skill installed
Review the theory for my power stage in task.txt and export a handoff prompt for the conversation provider.
- Read your context and instructions
- Compiled the pcb local ai
- Generated the UI component
Handoff prompt generated for the theory role. The output has been saved to outputs/task_20231027_143005.txt and the structured data to result.json.
PCB Theory Review Prompt
You are an expert PCB Engineering Assistant. Your task is to perform a rigorous theoretical review of the power stage described below. Do not accept previous design conclusions as evidence; use first principles (KCL/KVL).
Project Context
- Primary Load: 5V @ 2A steady state.
- Input Source: 12VDC +/- 10%.
- Target Efficiency: >85%.
- Thermal Constraints: Max 25°C rise above ambient.
Required Calculations
Loop Analysis: Solve for node voltages and branch currents. Treat coupling capacitors as open circuits for DC steady-state.
2.
Thermal/Trace Width: Based on rules/pcb_requirements.json, calculate the minimum trace width for a 2A load on 1oz copper to maintain target temperature rise.
3.
Component Stress: Verify power dissipation ($P = I^2R$ or $P = V \cdot I$) against the Absolute Maximum Ratings in the staging datasheets.
Status Indicators
- If data is missing for a specific component: NEEDS_DATA
- If a calculation shows a residual error or violation: FAIL
- If a decision is required between two valid topologies: NEEDS_DECISION
Next steps
- Copy the text above into your preferred LLM to receive the detailed theoretical analysis.
- Once the analysis is complete, save the results into the
staging/directory for verification. - Run
python scripts/local_worker.py decisionto integrate the AI's findings into the project state.
pcb-local-ai.tsx
TSX · React component
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
About this skill
Managing PCB design workflows across components, schematics, and layouts often leads to fragmented data and unverified manual checks. This skill provides a structured framework for KiCad PCB tasks, ensuring project requirements are preserved and engineering evidence is documented.
What it does
- Multi-Role Assistance dedicated modes for parts sourcing, schematic drafting, layout planning, theory review, and general project management.
- Automated Validation runs KiCad CLI for ERC, DRC, and schematic parity checks against specific JSON-defined rule sets.
- Data Integrity tracks component footprints, symbols, and datasheets with a local indexing system to prevent mismatched pins or specifications.
- Workflow Handoffs generates structured prompts for external AI models or utilizes local OpenAI-compatible inference servers.
- Engineering Evidence creates detailed audit trails in timestamped directories, including raw tool reports, command logs, and hash-verified results.
How it works
- Run
python scripts/local_worker.py setupto initialize the environment and configure local or conversation-based inference modes. - Select a role such as
partsorlayoutand provide a task file containing project requirements. - Execute the
workcommand to generate JSON deliverables or copy-pasteable prompts for external LLMs. - Use the
validate_project.pyscript to trigger KiCad's internal checking engines and compare results against project constraints.
Frameworks & tools
Python 3.10+, KiCad CLI, and OpenAI-compatible local inference servers (optional).
Why this beats prompting it yourself
Generic AI lacks the context of PCB manufacturing constraints and often hallucinates pinouts. This skill enforces a "proof of evidence" workflow where theoretical calculations and EDA tool outputs are required before any design phase is marked as complete.
Use cases
- Auditing a KiCad project for ERC/DRC violations using automated CLI scripts.
- Verifying theoretical circuit values like KCL/KVL and impedance before schematic entry.
- Managing local datasheet libraries and synchronizing component footprints across personal and built-in libraries.
Known limitations
Requires KiCad to be installed for engineering checks. Does not perform auto-routing, image-to-schematic recognition, or direct desktop automation.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.
Requires Python 3.10+ and pre-installed KiCad CLI for validation scripts. No built-in autorouting, PDF schematic recognition, or automated GUI interaction.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 9 days ago
- Free with an Agensi account
- Software
Python
Permissions
Allowed Hosts