# Skill Quality Gate

> >

- **Type:** Skill
- **Install:** `agentstack add skill-arnie016-codex-prompt-templates-skill-quality-gate`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [Arnie016](https://agentstack.voostack.com/s/arnie016)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [Arnie016](https://github.com/Arnie016)
- **Source:** https://github.com/Arnie016/codex-prompt-templates/tree/main/skills/skill-quality-gate
- **Website:** https://github.com/Arnie016/codex-prompt-templates

## Install

```sh
agentstack add skill-arnie016-codex-prompt-templates-skill-quality-gate
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Skill Quality Gate

Run this before considering a skill pack usable.

## Checks

1. Every skill has frontmatter `name` and `description`.
2. Description names the job, triggers, and required tools.
3. Skill body is short enough to load cheaply.
4. Long details live in references.
5. Skills do not overlap heavily.
6. No skill silently installs or runs untrusted software.
7. Output contracts are explicit.
8. Scripts are executable and scoped.

## Local Audit

```bash
SUPERCHARGE_PLUGIN="${SUPERCHARGE_PLUGIN:-plugins/codex-supercharge}"
scripts/skill_audit.sh skills
scripts/skill_audit.sh --strict skills
python3 "$SUPERCHARGE_PLUGIN/scripts/plugin_discovery_audit.py" --plugin-root "$SUPERCHARGE_PLUGIN" --strict
python3 "$HOME/.codex/skills/.system/skill-creator/scripts/quick_validate.py" plugins/codex-supercharge/skills/
```

## Findings Format

Lead with issues:

```md
## Findings
- [P1] ...
- [P2] ...

## Duplicates

## Missing Tests

## Recommended Changes
```

Use `$low-token-context` if the audit output becomes large.

## Validation

- `skill_audit.sh` reports folded descriptions, missing skip/validation/provenance, and risky commands.
- `plugin_discovery_audit.py` reports index/defaultPrompt/router/boundary references with no stale skill or reference links.
- `quick_validate.py` passes for every changed skill folder.
- Findings distinguish blocking metadata failures from follow-up quality debt.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [Arnie016](https://github.com/Arnie016)
- **Source:** [Arnie016/codex-prompt-templates](https://github.com/Arnie016/codex-prompt-templates)
- **License:** MIT
- **Homepage:** https://github.com/Arnie016/codex-prompt-templates

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-arnie016-codex-prompt-templates-skill-quality-gate
- Seller: https://agentstack.voostack.com/s/arnie016
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.