From rtl-agent-team
Runs cocotb multi-seed RTL vs reference model regression with traceability matrix for P5 Tier 3 module verification.
How this skill is triggered — by the user, by Claude, or both
Slash command
/rtl-agent-team:rtl-p5s-func-verify [module-name --seeds=N][module-name --seeds=N]This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
<Purpose>
<Use_When>
<Do_Not_Use_When>
RTL modules required:
rtl/**/*.sv files must existIf prerequisite is missing: WARNING — recommend running /rtl-agent-team:rtl-p4-implement.
Proceed with available artifacts — orchestrator will adapt scope.
Task(subagent_type="rtl-agent-team:p5s-func-verify-orchestrator", prompt="Execute functional verification. User input: $ARGUMENTS")
Do not perform any work directly. The orchestrator agent manages pipelined TB generation, multi-seed parallel regression, coverage analysis, and requirement traceability.
npx claudepluginhub babyworm/rtl-agent-team --plugin rtl-agent-teamDefines internal Tier 3 functional verification policy for RTL modules: cocotb signal naming, multi-seed regression, coverage targets, and parallel execution strategy.
Generates Python-based Cocotb testbenches as alternatives to SystemVerilog for hardware verification. Useful for Python-native engineers creating tests for RTL like FIFOs.
Creates, edits, and verifies skills using a test-driven development approach with pressure scenarios and subagents.