# quality-score

quality-score is a Claude Code skill that evaluates generated assets and animations on a 10-point scale. It triggers on explicit score requests or pipeline asset tasks.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf (Devin Desktop), Claude.ai · ★ 98 repo stars
- Author: LihFolk
- License: LicenseRef-Proprietary · policy=link-only · description only; the file stays with the author
- Source: https://github.com/lihfolk-cy/v2-vault/tree/HEAD/skills/quality-score/SKILL.md
- Updated: 2026-10-29
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/quality-score

## What it does

This skill grades generated assets and animations against structured rubrics with an 8.5 cut-off. Any failure during baseline automated checks caps the total grade at 5.0 points. Criteria carry explicit weights and require measurable evidence, such as automated test numbers or test renders.

The evaluation follows a closed feedback loop. Before producing an asset, the agent inspects past entries in `.lihfolk/ledger.jsonl` alongside project recipes to avoid recurring mistakes. Fixes target only the lowest-scoring criterion with the heaviest weight. The agent runs at most three repair passes. Three independent blind graders calculate median scores for the final decision.

Every run appends a record to `.lihfolk/ledger.jsonl`. When a specific asset type accumulates around 10 entries, the skill updates `.lihfolk/recipes.md` with parameters from winning drafts.

## Install

### Claude Code (native platform)

1. **Plugin marketplace**
In the agent chat (not a shell):
```text
/plugin marketplace add lihfolk-cy/v2-vault
```
In the agent chat (not a shell):
```text
/plugin install lihfolk@lihfolk
```
This installs the whole lihfolk plugin with all its skills

2. **Skills CLI (Vercel)**
```bash
npx skills add lihfolk-cy/v2-vault --skill quality-score -a claude-code
```

3. **Manually: put the files in place**
- File: `~/.claude/skills/quality-score/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/quality-score/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add lihfolk-cy/v2-vault --skill quality-score -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/quality-score/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add lihfolk-cy/v2-vault --skill quality-score -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/quality-score/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install lihfolk-cy/v2-vault skills/quality-score
```

2. **Manually: put the files in place**
- File: `.github/skills/quality-score/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add lihfolk-cy/v2-vault --skill quality-score -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/lihfolk-cy/v2-vault --path skills/quality-score
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/quality-score/SKILL.md` — The legacy .windsurf/skills/ path still works

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/lihfolk-cy/v2-vault/tree/HEAD/skills/quality-score/SKILL.md

## When to use it
- grade 3D assets and animations on an objective 10-point scale
- identify the weakest asset criteria before merging drafts
- log evaluation metrics and parameter fixes to a project ledger

## Example prompts
- Score this generated crate model against the model rubric.
- Evaluate the sword slash animation and log the score to the ledger.
- Check the inventory UI draft and run a fix round on the lowest criterion.

## Similar
- [workflow-score-to-target](https://affpapa.org/en/nevibecode/skills/workflow-score-to-target.md) — skill · 700 installs
- [build-hybrid-game-assets](https://affpapa.org/en/nevibecode/skills/build-hybrid-game-assets.md) — skill · 1600 installs
- [3d-model-generation](https://affpapa.org/en/nevibecode/skills/3d-model-generation.md) — skill · 1500 installs
- [Houdini](https://affpapa.org/en/nevibecode/skills/houdini.md) — skill · 1900 installs
- [data-quality-check](https://affpapa.org/en/nevibecode/skills/data-quality-check.md) — skill · 118 installs
- [animation-quality-gate](https://affpapa.org/en/nevibecode/skills/animation-quality-gate.md) — skill · 1500 installs

From the same set: [lihfolk-cy/v2-vault](https://affpapa.org/en/nevibecode/by/lihfolk-cy/v2-vault.md) — 29 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
