griffinhilly/claude-code-synthesis/review
Claude Code and agent skill by griffinhilly/claude-code-synthesis
- community
Checking that the SKILL.md file is still in the repository.
Review completed work against success criteria and flag issues
Install
npx vskill@latest install griffinhilly/claude-code-synthesis/reviewSKILL.md
Review
Evaluate completed work against its success criteria. Find problems before they compound.
Input
What to review: $ARGUMENTS
If no arguments, review whatever was most recently implemented in the conversation.
Process
Step 1: Pre-check
- If
/verifyhasn't been run on the target, suggest running it first — /verify catches completeness issues, /review catches quality issues. Different concerns. - Read relevant COMP files (CLAUDE.md for conventions, MEMORY.md for gotchas)
- Identify the success criteria (from /plan-task output, PLAN.md, or conversation)
Step 2: Launch Review
Read ~/.claude/skills/review/review-dimensions.md for what to check based on the type of work (code, data, writing).
Launch the review using a fresh-context subagent (use the code-reviewer agent persona for code). Apply the strengthened review discipline (per CLAUDE.md "Fresh eyes for review"):
- Spec-blind: Do NOT include the original spec, plan, or coder context in the reviewer's prompt. Pass the diff (or the artifact) and have the reviewer reason backward. The reviewer's lack of spec-knowledge is a feature — it surfaces unstated assumptions the spec hid.
- Multiple uncorrelated passes: Launch the reviewer 2-3 times in parallel with the same prompt. Union their findings. If the same model produces overlapping findings, that's signal; if they find different things, the union is the value.
- Treat-as-adversary: Frame the reviewer's findings as questions about the work, not defects to auto-fix. Pass each finding through "is this actually wrong, or is it the reviewer pattern-matching without context?" Keep the credible ones; reject the rest with reasoning.
Step 3: Present Findings
Read ~/.claude/skills/review/output-format.md for how to organize findings.
Step 4: Escalation Check
- For significant reviews, consider suggesting
/dialectic-reviewfor adversarial depth - If the review surfaces architectural concerns, suggest
/dialectic-review --premortembefore proceeding with fixes
Rules
Read ~/.claude/skills/review/rules.md for review rules and gotchas.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/review/SKILL.md
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
[](https://verified-skill.com/skills/griffinhilly/claude-code-synthesis/review)