# Pre Review

> Multi-agent code review before opening a PR. Surfaces critical issues, suggestions, and improvements.

- Skill: `ledgerhq/pre-review-2` (Agent Skill)
- Install (CLI): `npx skillmds@latest add ledgerhq/pre-review-2`
- Raw SKILL.md: https://api.skillmd.com/api/skills/ledgerhq/pre-review-2/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: ledgerhq (https://skillmd.com/u/ledgerhq)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/ledgerhq/pre-review-2

---


# Pre-Review

## Process

1. Run `git diff develop..HEAD` to get the full diff.

2. Launch 3 `code-reviewer` agents **in parallel**, each focused differently:

   - **A** — Correctness & edge cases: null/undefined handling, error states, off-by-one, async races
   - **B** — TypeScript quality: avoid `any`/`!`, correct types, missing exports, API design
   - **C** — Library conventions: `catalog:` devDeps, build outputs, changeset needed, tests missing, DX

   Each agent prompt: _"Review this diff against develop. Focus on [FOCUS]. Return findings with file:line, severity, and suggested fix."_

3. Merge and deduplicate findings. Present grouped by severity:

   ```
   🔴 Critical   — path/to/file.ts:42 — issue → fix
   🟡 Suggestion — ...
   🟢 Nice to have — ...

   Summary: X critical, Y suggestions, Z nice-to-haves
   ```

4. Ask which items to fix: **"all criticals"**, **"all"**, **"#1,#3"**, or **"skip"** → then `/github-pr`