master-zhiyi Eval
=================

Status: review
Score: 73/100
Risk: medium
Decision: manual_review
Policy: review
Reason: Require human approval before installing into a real workspace.

Install:
npx skills add xr843/Master-skill --skill master-zhiyi

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: Potentially useful, but at least one trust signal needs human inspection.
- 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: network or browser access

Warnings:
- Trust score: Potentially useful, but at least one trust signal needs human inspection.
- Audit score: Needs review
- Agent safety gate: Usable candidate, but the agent should surface permission and audit notes before installation.
- README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context
- Source ID inconsistencies between SKILL.md and meta.json: 玄義 is T1716 in SKILL.md but T33n1718 in meta.json; 文句 is T1718 in SKILL.md but T34n1718 in meta.json; 法華經 is T0262 in SKILL.md but T09n0262 in meta.json.
- references/teaching.md cites 《觀音玄義》 (T1726) which is not declared in the skill's sources list, violating its own citation policy.
- SKILL.md mentions optional scripts (cite.py, query.py) but they are not present in the repository; unclear if they are expected to be available.
- Quality score needs review

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
- Source ID inconsistencies between SKILL.md and meta.json: 玄義 is T1716 in SKILL.md but T33n1718 in meta.json; 文句 is T1718 in SKILL.md but T34n1718 in meta.json; 法華經 is T0262 in SKILL.md but T09n0262 in meta.json.
- references/teaching.md cites 《觀音玄義》 (T1726) which is not declared in the skill's sources list, violating its own citation policy.
- SKILL.md mentions optional scripts (cite.py, query.py) but they are not present in the repository; unclear if they are expected to be available.
- Quality score needs review
- Production credentials, payments, or irreversible account changes without explicit human review
- Sensitive private data before reviewing repository code, license, and permission surface

URLs:
- Skill: https://www.openagentskill.com/skills/xr843-master-zhiyi
- Audit: https://www.openagentskill.com/skills/xr843-master-zhiyi/audit
- JSON: https://www.openagentskill.com/api/agent/evals?slug=xr843-master-zhiyi