- Home
- Skills
- Agents & Orchestration
- FPGA 10/13 · Saleae Claude — Measurement as Proof
Works with the AI tools you already use
FPGA 10/13 · Saleae Claude — Measurement as Proof
Verifies FPGA hardware behavior by comparing real-world Saleae logic captures against simulation predictions.
$10
FPGA 10/13 · Saleae Claude — Measurement as Proof
Example session with this skill installed
Plan a Saleae capture for my SPI accelerator. The driver uses CPOL=0, CPHA=1 at 10MHz. I need to compare the physical MISO/MOSI pins against my sim_trace.vcd and seal the resulting .sal file.
- Read your context and instructions
- Compiled the fpga 10 13
I have set the capture plan: 100MS/s sample rate (10x margin), SPI decoder to Mode 1 (CPOL=0, CPHA=1). Comparison target is sim_trace.vcd. After recording, run scripts/sal_seal.py capture_spi_2023-10-27.sal to generate the SHA-256 custody line for HANDOVER_SPI.md.
Connects securely to your tools. The creator never sees your data.
What you get
About this skill
The problem
Relying on simulation or internal debug cores creates a feedback loop where systematic errors remain hidden. Without independent external measurement, performance claims are self-reported predictions rather than verified hardware reality.
What it does
- Plans hardware captures by calculating required sample rate margins and trigger points against simulation predictions.
- Configures protocol decoders for UART, SPI, and I2C based on actual driver implementation rather than generic datasheets.
- Executes bit-for-bit comparisons between physical signal captures and RTL simulation traces to identify regressions.
- Calculates separate timing metrics for raw kernel execution versus end-to-end system paths to prevent inflated speedup claims.
- Generates cryptographically sealed capture archives with SHA-256 hashes for chain-of-custody verification.
Frameworks & tools
Saleae Logic hardware and software, SPI, I2C, UART protocols, RTL simulation traces, and Python-based sealing scripts.
Why this beats prompting it yourself
Generic prompts often miss subtle protocol misconfigurations like SPI clock phase mismatches or insufficient oversampling. This skill enforces a strict measurement-before-prediction workflow and automates the custody hashing required for rigorous hardware audits.
Use cases
- Verifying FPGA accelerator throughput against simulated benchmarks.
- Debugging communication mismatches between driver software and RTL implementations.
- Auditing hardware performance for official technical reports and client delivery.
- Disclosing logic overhead caused by internal embedded logic analyzers.
Known limitations
Requires physical Saleae logic analyzer hardware and broken-out signal pins or headers for external measurement.
How to install
Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.
- 1
Download the ZIP
Free skills download straight away. Paid skills unlock right after purchase.
- 2
Unzip into your skills folder
Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.
- 3
Ask your agent to use it
Restart the agent if it was already running. It picks the skill up automatically - no config needed.
Skills folder by agent
Click the path to copy it. Create the folder if it does not exist yet.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean 1 month ago
- Passed all security checks, Safe to install