- Home
- Skills
- Agents & Orchestration
- FPGA 05/13 · RTL Claude — Simulation vs the Oracle
Works with the AI Agents you already use
FPGA 05/13 · RTL Claude — Simulation vs the Oracle
Clock-by-clock RTL simulation and verification against golden Python oracles with 4-state logic preservation.
$10
FPGA 05/13 · RTL Claude — Simulation vs the Oracle
Example session with this skill installed
Run the RTL simulation for the dsp_macro block against the Python oracle. Ensure the comparison happens after nonblocking assignments and check for pipeline hazards.
- Read your context and instructions
- Compiled the fpga 05 13
Simulation trace tb_dsp_macro.trace generated. 4-state logic preserved. Compared 10,000 vectors. Read-after-write hazard test cases passed. Comparison report: bad==0. Pre-synthesis behavioral pass complete. Post-synthesis run scheduled. Blind spots: 2 unsynchronized CDCs flagged for Station 07.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Functional simulations often pass while hardware fails because "no warnings" doesn't mean "correct data." Subtle bugs like off-by-one clock shifts or silent range overflows remain invisible without cycle-accurate value comparison.
What it does
- Performs tick-for-tick value comparisons between RTL and a golden Python oracle.
- Preserves 4-state logic (X/Z) during comparison to prevent unknown states from collapsing into false zeros.
- Validates designs before and after synthesis using gate-level netlists with realistic delays.
- Injects targeted hazard vectors to catch read-after-write hazards and pipeline conflicts.
- Generates a definitive
bad==0report based on trace file analysis.
Frameworks & tools
Verilog RTL, Python oracles, Vivado, gate-level simulators, and event-driven simulation environments.
Why this beats prompting it yourself
Generic prompts ignore the nuances of event-driven simulation timing. This skill enforces strict comparison points after all nonblocking assignments, ensuring zero simulator-dependent jitter and accurate hazard detection that simple "check my code" prompts miss.
Use cases
- Verifying a new RTL block against a golden mathematical model.
- Catching synthesis-induced regressions in gate-level netlists.
- Debugging pipeline hazards and memory port conflicts with targeted vectors.
- Documenting simulation blind spots like CDC and metastability for downstream teams.
Known limitations
Cannot detect metastability, sub-cycle glitches, or clock-domain crossing issues, as these are invisible to event-driven simulators.
Does not model metastability, sub-cycle glitches, or analogue timing. Cannot prove CDC correctness; requires separate linting or timing analysis.
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 2 months ago