cs-xiaohuang-skill Eval
=======================

Status: review
Score: 72/100
Risk: medium
Decision: manual_review
Policy: review
Reason: Require human approval before installing into a real workspace.

Install:
npx skills add ChenShuo2004/cs-skills --skill cs-xiaohuang-skill

Required checks:
- PASS Task fit: Task wording matches this skill metadata.
- PASS Install path: Install handoff is available.
- PASS Install command safety: standard package or runtime install path
- WARN Trust score: Good trust signals with a few areas worth checking before rollout.
- WARN Audit score: Needs review
- WARN Agent safety gate: Usable candidate, but the agent should surface permission and audit notes before installation.
- PASS License clarity: MIT
- PASS Permission surface: filesystem or document access

Warnings:
- Trust score: Good trust signals with a few areas worth checking before rollout.
- Audit score: Needs review
- Agent safety gate: Usable candidate, but the agent should surface permission and audit notes before installation.
- SKILL.md references several supporting files (assets/reference-xiaohuang.png, references/style-dna.md, references/prompt-template.md, references/qa-checklist.md, etc.) that are not fully shown in the excerpt; if any are missing from the packaged skill, core workflows will break.
- The skill instructs agents to read a reference image as the identity anchor. If that image ever contains embedded text or instructions, an agent could treat it as guidance; this is a minor prompt-injection surface, though no dangerous actions are requested.
- Quality score needs review
- Stars/forks activity: 118 stars, 13 forks; issue activity unavailable in current metadata

Validation plan:
1. Inspect repository, README/SKILL.md, license, and recent commits before production use.
2. Install in an isolated workspace or sandbox with no production secrets available.
3. Run the smallest representative task and record files touched, commands run, network access, and outputs.
4. Compare the selected skill against at least one alternative when the eval status is review or failed.
5. Promote only after the agent reports a successful verification result and unresolved warnings are accepted.

Do not use when:
- teams that need a vendor-supported SLA
- production agents without a repository review
- SKILL.md references several supporting files (assets/reference-xiaohuang.png, references/style-dna.md, references/prompt-template.md, references/qa-checklist.md, etc.) that are not fully shown in the excerpt; if any are missing from the packaged skill, core workflows will break.
- No OpenAgentSkill engagement data yet
- The skill instructs agents to read a reference image as the identity anchor. If that image ever contains embedded text or instructions, an agent could treat it as guidance; this is a minor prompt-injection surface, though no dangerous actions are requested.
- Quality score needs review
- Stars/forks activity: 118 stars, 13 forks; issue activity unavailable in current metadata
- Production credentials, payments, or irreversible account changes without explicit human review

URLs:
- Skill: https://www.openagentskill.com/skills/chenshuo2004-cs-xiaohuang-skill
- Audit: https://www.openagentskill.com/skills/chenshuo2004-cs-xiaohuang-skill/audit
- JSON: https://www.openagentskill.com/api/agent/evals?slug=chenshuo2004-cs-xiaohuang-skill