Seedance 2.0 Skill OS Eval
==========================

Status: review
Score: 84/100
Risk: medium
Decision: manual_review
Policy: review
Reason: Require human approval before installing into a real workspace.

Install:
python scripts/install_codex_skill.py --force

Required checks:
- PASS Task fit: Task wording matches this skill metadata.
- PASS Install path: Install handoff is available.
- PASS Install command safety: simple repository or package 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: 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.
- 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
- Installer replaces an existing local seedance-20 skill directory when --force is used; review scripts/install_codex_skill.py before running.

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
- Installer replaces an existing local seedance-20 skill directory when --force is used; review scripts/install_codex_skill.py before running.
- High-risk permission hints: Shell or command execution
- Production credentials, payments, or irreversible account changes without explicit human review
- Sensitive private data before reviewing repository code, license, and permission surface
- Automatic installation in a production workspace

URLs:
- Skill: https://www.openagentskill.com/skills/emily2040-seedance-2-0
- Audit: https://www.openagentskill.com/skills/emily2040-seedance-2-0/audit
- JSON: https://www.openagentskill.com/api/agent/evals?slug=emily2040-seedance-2-0