- Home
- Skills
- Agents & Orchestration
- hw system review
hw system review
Standardized hardware design review flow with engineering calculators for power, thermal, and PCB layout verification.
$10
Works with the AI Agents you already use
hw system review
Example session with this skill installed
Perform a thermal and derating check for a power MOSFET. Dissipation is 8W, ambient temp is 45C, Rjc 1.2, Rcs 0.5, Rsa 4.0. Voltage is 21V on a 25V rated part. Limit is 0.8.
- Read your context and instructions
- Compiled the hw system review
I have completed the S4 Thermal and Reliability assessment for the specified MOSFET using the hardware calculation toolkit.
Thermal and Derating Assessment Report
1. Calculation Results
| Parameter | Value | Formula/Method | Result |
|---|---|---|---|
| Junction Temp (Tj) | 90.6°C | Ta + Pd * (Rjc + Rcs + Rsa) | PASS (Assuming Tj_max 125°C) |
| Voltage Stress | 0.84 | Applied / Rated (21V / 25V) | FAIL (Limit: 0.80) |
| Total Thermal Resistance | 5.7 °C/W | Rjc + Rcs + Rsa | - |
2. S4 Reliability Findings
[P0] Derating Violation: The voltage stress ratio (0.84) exceeds the project limit of 0.80. Operating a 25V MOSFET at 21V provides insufficient margin for inductive spikes or transient surges.
[P1] Thermal Margin: Tj is calculated at 90.6°C. While below a typical 125°C or 150°C limit, the junction-to-ambient path is heavily dependent on the RSA (heatsink) performance.
3. Verification & Logic
The junction temperature was derived using the thermal command: python3 scripts/hw_calc.py thermal --pd 8 --ta 45 --rjc 1.2 --rcs 0.5 --rsa 4.0. The derating check used the derating command: python3 scripts/hw_calc.py derating --rated 25 --applied 21 --limit 0.8 --kind voltage.
Next steps
- Replace the MOSFET with a 30V or 40V rated alternative to meet the 0.80 derating requirement.
- Verify the Rsa (case-to-ambient) value against the actual heatsink datasheet or local copper pour area.
- Add an RC snubber if high-frequency switching transients are expected on the 21V rail.
Connects securely to your tools. The creator never sees your data.
About this skill
High-stakes hardware design demands more than casual checks. This skill provides a structured framework for board-level engineering reviews, moving from architecture and power trees to thermal analysis and DFM. It eliminates guesswork by forcing a staged review process supported by a dedicated Python-based calculator for physical parameters.
What it does
- Staged review flow executes a mandatory six-step sequence covering architecture, schematics, PCB layout, thermal reliability, DFM/DFT, and bring-up planning.
- Parametric calculations provides precise values for trace width, via current capacity, power budgets, junction temperatures, and target impedance using IPC-2221 logic.
- Risk classification categorizes every finding into P0, P1, or P2 priority levels to prevent critical blockers from reaching production.
- Derating verification validates component stress levels against rated limits for voltage, current, and power.
- Reporting automation generates structured design review gate documents (DR1/DR2/DR3) and DFMEA inputs.
How it works
- Initialize review by selecting one of the six stages (S1-S6) to load the relevant checklist and reference criteria.
- Execute calculations using the
hw_calc.pyscript to verify trace geometry, thermal resistance, or decoupling requirements. - Audit findings against the provided checklists for schematics, signal integrity, and manufacturing constraints.
- Generate report using the fixed template to summarize Go/No-Go decisions and critical risk items.
Frameworks & tools
This tool uses a standard-library-only Python 3 calculator for core engineering physics. It relies on Markdown-based checklists and templates compatible with any git-based documentation workflow or engineering notebook.
Why this beats prompting it yourself
Generic AI often gives qualitative advice or ignores physical constraints like copper weight and thermal resistance. This skill enforces a professional hardware lifecycle that treats engineering as a series of verifiable gate reviews rather than just a chat conversation.
Use cases
- Pre-layout review to validate power trees and timing margins before starting PCB routing.
- Reliability auditing to check component derating and junction temperatures for industrial or high-heat environments.
- Manufacturing prep to run DFM/DFT checks and ensure test coverage before releasing files to the fab house.
- Root cause analysis to systematically investigate board failures by working backwards through the staged review flow.
Known limitations
Calculations are approximations based on standards like IPC-2221 and simple thermal resistance models. It does not replace full 3D FEM simulation or sign-off from a certified compliance body.
Calculations are approximations (e.g. IPC-2221). Requires Python 3 for the calculator script. Does not perform automated EDA file parsing; manual input of parameters is required.
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 any payment.
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
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 13 days ago