tommy-ca/grok-build-plugins/review-lenses

Claude Code and agent skill by tommy-ca/grok-build-plugins

Trust tier 3
  • community
Source check pending

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

Stack decorrelated review lenses before landing long-horizon work. Use for /review-lenses, merge-ready swarm verify, or when interrogate alone is one lens.

Install

npx vskill@latest install tommy-ca/grok-build-plugins/review-lenses

SKILL.md

Review lenses

No single view catches every class of error. Stack decorrelated lenses. Review compute is cheaper than audited rework.

Builds on /interrogate, playbooks/shipping.md swarm-verify, show-me-your-work Attention. Does not auto-apply fixes.

Lenses

idSeesCatches
full-transcriptagent transcripthidden assumptions, skipped steps
output-onlyhandoff + diffclaimed vs delivered
codebase-onlyrepo at SHA, no chatintegration damage, megafiles
liverunning app via the real surfaceproxy-test lies
regressiontrunk vs SHAcollateral breakage
interrogatepstack /interrogateadversarial review

Steps

  1. Pick at least two lenses that do not share a model family when two families exist. Default merge-ready set: output-only plus codebase-only. Add live when the unit is behavioral. Add regression when the blast radius is more than one module.
  2. Parent fans out. Output-only and live use pstack:independent-verifier. Codebase-only may use pstack:how-explorer. The interrogate lens is /interrogate. Do not send extra spawn fields.
  3. Synthesize with the interrogate categories: Act on, Consider, Noted, Dismissed.
  4. Write the ledger row on the selected board only after the stacked verdict. All-clean (no Act on) is required to land. PASS+NOTES may land if every note is Dismissed or Noted with a reason.
  5. Record which lenses ran in the show-me-your-work trail.

Invariants

  • Verifier model family differs from the worker when a second slug exists. Else family: same-degraded.
  • Interrogate alone does not meet the two-lens bar.
  • A lens that only rereads the worker's self-report is not a lens.
  • CI green is an input, not a verdict.

Security

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

See the full security report

Quality evaluation

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

See evaluation results

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/tommy-ca/grok-build-plugins/review-lenses/badge)](https://verified-skill.com/skills/tommy-ca/grok-build-plugins/review-lenses)

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