From rtl-agent-team
Defines structured policy for LLM code reviews of RTL designs: severity taxonomy (S0-S3), evidence requirements, pass/fail gates, escalations, and markdown report format.
npx claudepluginhub babyworm/rtl-agent-team --plugin rtl-agent-teamThis skill uses the workspace's default tool permissions.
- RTL logic correctness and spec/uarch compliance
Generates design tokens/docs from CSS/Tailwind/styled-components codebases, audits visual consistency across 10 dimensions, detects AI slop in UI.
Records polished WebM UI demo videos of web apps using Playwright with cursor overlay, natural pacing, and three-phase scripting. Activates for demo, walkthrough, screen recording, or tutorial requests.
Delivers idiomatic Kotlin patterns for null safety, immutability, sealed classes, coroutines, Flows, extensions, DSL builders, and Gradle DSL. Use when writing, reviewing, refactoring, or designing Kotlin code.
S0 Blocker: data corruption, protocol/safety breakage, hard spec violationS1 Critical: high silicon risk, functional failure likely under valid stimulusS2 Major: maintainability/test-quality issues with medium defect riskS3 Minor: style/readability/non-blocking improvementsFAIL: any unresolved S0 or S1CONDITIONAL: only S2 findings remain and have approved remediation planPASS: only S3 or no findingsS0: immediate stop, escalate to orchestrator/user with fix-first recommendationS1 on same module after 2 fix loops: escalate to architecture ownerS0/S1: finding is invalid until evidence attachedS0/S1 finding must include reproducible evidence:
*_latest.sh, wave/report paths) over prose-only claimsUse the following report skeleton:
# Code Review Report
- Scope: module|block|top
- Verdict: PASS | CONDITIONAL | FAIL
## Findings
| ID | Severity | File:Line | Summary | Evidence |
|---|---|---|---|---|
## Required Actions
| Priority | Owner | Action | Recheck |
|---|---|---|---|
## Escalations
- [if any]