short-drama-develop Eval
========================

Status: review
Score: 74/100
Risk: medium
Decision: manual_review
Policy: review
Reason: Require human approval before installing into a real workspace.

Install:
npx skills add zenstory-ai/drama-skills --skill short-drama-develop

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
- WARN Permission surface: shell or command execution

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.
- Permission surface: shell or command execution
- High-risk permission hints: Shell or command execution
- SKILL.md references local scripts (selftest.py, episode_intake.py) and reference files that are partially shown in the excerpt; the full repository should verify these files exist and are functional.
- The SKILL.md does not explicitly document security boundaries such as handling of user-provided material permissions, though it does say '只读取用户在当前会话明确提供或授权的材料' in the reference intake doc and restricts output to project development files.
- The skill includes a 'premise device' contract section that could be misused to retroactively justify supernatural powers; while it enforces accepted status, the reviewer should note this is a craft-level control, not a security control.
- Compliance is mostly clear: MIT license, no obvious third-party code copy, but the repository's full compliance posture (attribution, dependency licenses) is not verifiable from the excerpt.
- 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 references local scripts (selftest.py, episode_intake.py) and reference files that are partially shown in the excerpt; the full repository should verify these files exist and are functional.
- No OpenAgentSkill engagement data yet
- High-risk permission hints: Shell or command execution
- The SKILL.md does not explicitly document security boundaries such as handling of user-provided material permissions, though it does say '只读取用户在当前会话明确提供或授权的材料' in the reference intake doc and restricts output to project development files.
- The skill includes a 'premise device' contract section that could be misused to retroactively justify supernatural powers; while it enforces accepted status, the reviewer should note this is a craft-level control, not a security control.
- Compliance is mostly clear: MIT license, no obvious third-party code copy, but the repository's full compliance posture (attribution, dependency licenses) is not verifiable from the excerpt.

URLs:
- Skill: https://www.openagentskill.com/skills/zenstory-ai-short-drama-develop
- Audit: https://www.openagentskill.com/skills/zenstory-ai-short-drama-develop/audit
- JSON: https://www.openagentskill.com/api/agent/evals?slug=zenstory-ai-short-drama-develop