# Self-Review Skill

> Automatically review agent output quality before sending to user.

- Skill: `modbender/self-review-skill` (Agent Skill, multi-file: 4 files)
- Install (CLI): `npx skillmds@latest add modbender/self-review-skill`
- Raw SKILL.md: https://api.skillmd.com/api/skills/modbender/self-review-skill/raw
- Safety review: pending (external: skill-scanner PASS, skillspector CAUTION)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: modbender (https://skillmd.com/u/modbender)
- Updated: 2026-09-09
- Page: https://skillmd.com/skills/modbender/self-review-skill

---


# Self-Review Skill

Automatically review agent output quality before sending to user.

- Checks: clarity, conciseness, actionability, structure
- Simple rule-based engine (no API cost)
- Exit code 0 = approved, 1 = needs improvement

## Usage

Pipe output to reviewer:

```bash
echo "Your response text" | node skills/self-review/index.js
```

Or integrate into agent pipeline (AGENTS.md step 6).

## Configuration

Edit `skills/self-review/index.js` to adjust thresholds.

## Advanced

For LLM-based review, see `self-review-llm` skill (separate package).

---

Author: dvinci达芬奇 (self-evolved)
Version: 1.0.0
Tags: quality, automation, token-optimization