master-xuyun 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-xuyun

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
- In references/teaching.md, citations to 《虚云老和尚开示录》, 《虚云和尚法汇》, and 《虚云老和尚年谱》 are used, but these are not declared in the SKILL.md frontmatter `sources:` field. The links provided (e.g., https://fojin.app/texts/65) point to CBETA texts (e.g., 楞严经) which do not match the cited work, creating a risk of hallucinated or misattributed citations.
- The SKILL.md states '所有教义断言附 CBETA 经证' but then allows citations to non-CBETA historical works without a clear mechanism for validating them. This contradicts the declared citation policy and could lead to unverifiable claims.
- The `scripts/cite.py` is mentioned but no script file is provided in the repository, and the usage example is incomplete ('--text "参话头' is cut off). This makes the optional tool unusable as documented.
- The `meta.json` `sources` list only includes four CBETA texts, but `references/teaching.md` references additional works (e.g., 虚云老和尚开示录) that are not listed. This inconsistency undermines the 'declared_sources_only' claim policy.
- 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
- In references/teaching.md, citations to 《虚云老和尚开示录》, 《虚云和尚法汇》, and 《虚云老和尚年谱》 are used, but these are not declared in the SKILL.md frontmatter `sources:` field. The links provided (e.g., https://fojin.app/texts/65) point to CBETA texts (e.g., 楞严经) which do not match the cited work, creating a risk of hallucinated or misattributed citations.
- No OpenAgentSkill engagement data yet
- The SKILL.md states '所有教义断言附 CBETA 经证' but then allows citations to non-CBETA historical works without a clear mechanism for validating them. This contradicts the declared citation policy and could lead to unverifiable claims.
- The `scripts/cite.py` is mentioned but no script file is provided in the repository, and the usage example is incomplete ('--text "参话头' is cut off). This makes the optional tool unusable as documented.
- The `meta.json` `sources` list only includes four CBETA texts, but `references/teaching.md` references additional works (e.g., 虚云老和尚开示录) that are not listed. This inconsistency undermines the 'declared_sources_only' claim policy.
- Quality score needs review

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