archival-fragments Eval
=======================

Status: review
Score: 71/100
Risk: medium
Decision: manual_review
Policy: review
Reason: Require human approval before installing into a real workspace.

Install:
npx skills add ttfake92-lab/skills --skill archival-fragments

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.
- WARN License clarity: Unknown
- PASS Permission surface: no high-risk permission surface in public metadata

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.
- License clarity: Unknown
- License is unclear
- Repository license is unknown/no LICENSE file detected, so reuse rights are not clearly granted.
- The actual setup and credential commands are in references/00-setup.md, which was not included in the reviewed excerpt; those commands should be verified against official sources and secret-handling best practices.
- The workflow depends on paid third-party services (MiniMax, Fish Audio, LibTV CLI); without a stated cost ceiling a user could accidentally run a long and expensive batch.
- Quality score needs review
- Stars/forks activity: 212 stars, 33 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
- Repository license is unknown/no LICENSE file detected, so reuse rights are not clearly granted.
- No OpenAgentSkill engagement data yet
- License is unclear
- The actual setup and credential commands are in references/00-setup.md, which was not included in the reviewed excerpt; those commands should be verified against official sources and secret-handling best practices.
- The workflow depends on paid third-party services (MiniMax, Fish Audio, LibTV CLI); without a stated cost ceiling a user could accidentally run a long and expensive batch.
- Quality score needs review

URLs:
- Skill: https://www.openagentskill.com/skills/ttfake92-lab-archival-fragments
- Audit: https://www.openagentskill.com/skills/ttfake92-lab-archival-fragments/audit
- JSON: https://www.openagentskill.com/api/agent/evals?slug=ttfake92-lab-archival-fragments