# audit-scoring-stinger

audit-scoring-stinger rolls up multi-category audit scores into an Excel scorecard, handles missing metrics, and caps the grade whenever critical security flaws appear.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf (Devin Desktop), Claude.ai · ★ 96 repo stars
- Author: Legion Code Inc.
- License: AGPL-3.0-or-later · policy=link-only · description only; the file stays with the author
- Source: https://github.com/legioncodeinc/vibe-coding-tools/tree/HEAD/plugins/website-audit-tools/skills/audit-scoring-stinger/SKILL.md
- Updated: 2026-10-18
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/audit-scoring-stinger

## What it does

This skill manages mathematical rollups inside a multi-agent website audit pipeline. It reads findings from category folders ranging from `03-seo/` through `12-ecommerce/`, validates entries against `leaf-finding.schema.json`, and records them directly into `scoring/audit-scorecard.xlsx`. Calculations account for skipped checks at every hierarchical tier.

Safety logic is strictly hardcoded. When any security check drops to a score of 1, the overall final grade cannot rise above a C. Text values beginning with `=`, `+`, `-`, or `@` receive an apostrophe prefix to neutralize spreadsheet formula injection vulnerabilities.

The skill does not inspect web pages or create original evidence on its own. It acts purely on data from earlier pipeline stages, so attempting to run it without completed category outputs halts execution. Final processed rows are exported into `scoring/findings-register.csv` for handoff.

## Install

### Claude Code (native platform)

1. **Plugin marketplace**
In the agent chat (not a shell):
```text
/plugin marketplace add legioncodeinc/vibe-coding-tools
```
In the agent chat (not a shell):
```text
/plugin install website-audit-tools@wasp-nest
```
This installs the whole website-audit-tools plugin with all its skills

2. **Skills CLI (Vercel)**
```bash
npx skills add legioncodeinc/vibe-coding-tools --skill audit-scoring-stinger -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add legioncodeinc/vibe-coding-tools --skill audit-scoring-stinger -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add legioncodeinc/vibe-coding-tools --skill audit-scoring-stinger -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install legioncodeinc/vibe-coding-tools plugins/website-audit-tools/skills/audit-scoring-stinger
```

2. **Manually: put the files in place**
- File: `.github/skills/audit-scoring-stinger/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add legioncodeinc/vibe-coding-tools --skill audit-scoring-stinger -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/legioncodeinc/vibe-coding-tools --path plugins/website-audit-tools/skills/audit-scoring-stinger
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/audit-scoring-stinger/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/legioncodeinc/vibe-coding-tools/tree/HEAD/plugins/website-audit-tools/skills/audit-scoring-stinger/SKILL.md

## When to use it
- roll raw audit scores into tiered category and final metrics
- validate leaf findings against the project JSON schema
- apply safety overrides to cap overall grades on severe vulnerabilities
- sanitize spreadsheet exports against formula injection payloads

## Example prompts
- Aggregate all completed category findings into scoring/audit-scorecard.xlsx.
- Validate incoming findings and export the sanitized scoring/findings-register.csv.
- Recalculate rollup scores and verify whether the critical security cap was triggered.

## Similar
- [selection-toolkit](https://affpapa.org/en/nevibecode/skills/selection-toolkit.md) — skill · 135 installs
- [datapack-builder](https://affpapa.org/en/nevibecode/skills/datapack-builder.md) — skill · 1900 installs
- [scoring-checks](https://affpapa.org/en/nevibecode/skills/scoring-checks.md) — skill · ★ 1319 repo stars
- [agent-xlsx](https://affpapa.org/en/nevibecode/skills/agent-xlsx.md) — skill · 782 installs
- [kimi-xlsx](https://affpapa.org/en/nevibecode/skills/kimi-xlsx.md) — skill · 437 installs
- [music-supervision-scoring](https://affpapa.org/en/nevibecode/skills/music-supervision-scoring.md) — skill · 263 installs

From the same set: [legioncodeinc/vibe-coding-tools](https://affpapa.org/en/nevibecode/by/legioncodeinc/vibe-coding-tools.md) — 172 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
