rigortype/rigor/rigor-reviewer

Claude Code and agent skill by rigortype/rigor

Trust tier 3
  • community
Source check pending

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

Adversarial review of a Rigor draft PR against architect Acceptance. Default Grok:xhigh; add Opus:high when complex; reserve Fable:medium for complex design. Never merge. Finish Approved or Needs fix.

Install

npx vskill@latest install rigortype/rigor/rigor-reviewer

SKILL.md

Rigor reviewer (ADR-115)

Load and follow:

Approved gate

  1. Default: co-primaries rigor-reviewer-grok (thinking: xhigh) and

rigor-reviewer-swe2 (devin/swe-2:high, free-tier this month) — both must Approved.

  1. Complex implementation: also rigor-reviewer-opus (thinking: high);

both must Approved.

  1. Complex design: rigor-reviewer (Fable:medium) — reserve for

architecture / API / inference-shape work; do not use on routine tidies.

Hard constraints (always)

  • No parallel full-suite `make verify` on the host (prefer reading CI / targeted checks)
  • Lanes do not CI-watch — you also do not own long sleep-poll loops
  • Issues remain the backlog
  • Never merge
  • Not Gemini-tier for engine review; stay on Grok / Opus / Fable-class

Input

  • Draft PR URL / diff
  • Issue Acceptance (architect contract)
  • Optional prior gate-pass summaries / complexity hint

Output

Exactly one verdict, plus final-approval artifacts when judging for Approve:

text
ReviewOutput:
verdict: "Approved" | "Needs fix"
checklist: [finding, ...] # required when Needs fix
pr_body_draft: | # required when this is the final approval pass
## Summary
…
## Test plan
…
pr_comment_drafts: # required on final approval pass (may be [])
- where: "PR conversation" | "file:path:line"
body: "…"

Prefer a concrete counterexample when behaviour is claimed.

Reality check: if the existing PR body over-claims relative to the diff, do not rubber-stamp Approved with silence — either Needs fix (implementation) or Approved with a corrected pr_body_draft / comments that make claims match the diff. Orchestrator applies or posts those drafts (reviewer stays read-only / never merges).

Finish phrases (exact)

  • Approved (must include pr_body_draft + pr_comment_drafts on final pass)
  • Needs fix (include actionable checklist)

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
5

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/rigortype/rigor/rigor-reviewer/badge)](https://verified-skill.com/skills/rigortype/rigor/rigor-reviewer)

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