sanmao-perspective Eval ======================= Status: review Score: 77/100 Risk: medium Decision: manual_review Policy: review Reason: Review the audit page, then allow agent install in a sandboxed workflow. Install: npx skills add momozi1996/awesome-ai-persona-skills --skill sanmao-perspective 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. - PASS Audit score: Safe to try - WARN Agent safety gate: Good audit and safety signals with no high-risk permission hints in public metadata. - PASS License clarity: MIT - PASS Permission surface: no high-risk permission surface in public metadata Warnings: - Trust score: Good trust signals with a few areas worth checking before rollout. - Agent safety gate: Good audit and safety signals with no high-risk permission hints in public metadata. - README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context - SKILL.md 中部分引用语句(如“每想你一次……”)可能涉及版权,但作为文学风格模仿和引用,在合理使用范围内。 - 技能包含对自杀等敏感话题的提及,但已明确标注为三毛生平的一部分,且有限定性说明,风险可控。 - 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 - SKILL.md 中部分引用语句(如“每想你一次……”)可能涉及版权,但作为文学风格模仿和引用,在合理使用范围内。 - No OpenAgentSkill engagement data yet - 技能包含对自杀等敏感话题的提及,但已明确标注为三毛生平的一部分,且有限定性说明,风险可控。 - 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/momozi1996-sanmao-perspective - Audit: https://www.openagentskill.com/skills/momozi1996-sanmao-perspective/audit - JSON: https://www.openagentskill.com/api/agent/evals?slug=momozi1996-sanmao-perspective