babyworm/rtl-agent-team/rtl-p5-verify

Claude Code and agent skill by babyworm/rtl-agent-team

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Phase 5 legacy bundled verification: functional + silicon checks in one flow. Triggers 'verify', 'Phase 5', 'run all checks'. New flows: prefer split P5A/P5B.

Install

npx vskill@latest install babyworm/rtl-agent-team/rtl-p5-verify

SKILL.md

<Purpose> Execute Phase 5 verification pipeline. Runs three-stage verification (module → top → final) covering 9 verification categories with module graduation gates and compliance review. This is a legacy bundled bridge while teams transition to split P5A/P5B. </Purpose>

<Use_When>

  • Phase 4 RTL implementation is complete with lint passing
  • User says "verify", "verification", "Phase 5", "run all checks"
  • Need comprehensive verification: lint, formal, CDC, functional, coverage, synthesis
  • Need one legacy-style Phase-5 command that bundles functional + silicon-oriented checks
  • Need migration bridge while adopting split flows (rtl-p5a-functional-closure + rtl-p5b-silicon-validation)
  • Team workflow intentionally keeps the combined legacy Phase-5 interface

</Use_When>

<Do_Not_Use_When>

  • RTL modules don't exist yet (run rtl-p4-rapid-impl or rtl-p4-implement first)
  • Only need functional regression (use rtl-p5s-func-verify)
  • Only need a specific verification category (use the category-specific skill)
  • Want strict separation of functional closure and silicon validation

(use rtl-p5a-functional-closure first, then rtl-p5b-silicon-validation)

  • Starting a new verification flow with explicit two-stage closure

(default to split rtl-p5a-functional-closure + rtl-p5b-silicon-validation) </Do_Not_Use_When>

Prerequisites

Phase 4 completion required:

  • rtl/**/*.sv files must exist
  • One of the following completion proofs must exist:
  • reviews/phase-4-rtl/lint-report.md (full rtl-p4-implement path)
  • .rat/state/p4-state.json with gates.p4_exit.verdict = pass (rapid rtl-p4-rapid-impl path)

If prerequisites are missing: WARNING — recommend running /rtl-agent-team:rtl-p4-rapid-impl or /rtl-agent-team:rtl-p4-implement. Proceed with available artifacts — orchestrator will adapt scope.

Execution

Task(subagent_type="rtl-agent-team:p5-verify-orchestrator", prompt="Execute Phase 5 verification. User input: $ARGUMENTS")

Do not perform any work directly. The orchestrator agent manages all stages, module graduation, parallel agent spawning, and compliance review.

Compliance Notes

  • Verification must confirm all iron requirement acceptance_criteria are met.

When structured acceptance_criteria (with ac_id) exist from P3, verification tracks compliance at the individual criterion level (ac_id granularity). When acceptance_criteria is in string-array format (P1/P2), verification operates at REQ level.

  • Final compliance check compares test results against P1+P2+P3 acceptance_criteria
  • Phase 5 PASS requires zero unmet iron requirements across all verification categories

Output

  • reviews/phase-5-verify/ — 9 category verification reports (lint, formal, CDC, protocol, functional, coverage, performance, synthesis, code review)
  • reviews/phase-5-verify/final-compliance.md — overall PASS/FAIL verdict with requirement traceability

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/babyworm/rtl-agent-team/rtl-p5-verify/badge)](https://verified-skill.com/skills/babyworm/rtl-agent-team/rtl-p5-verify)

Something wrong with this skill or its page? Tell us.