Star0

Pre-install eval

Seedance 2.0 Skill OS eval report.

A machine-readable install decision for agents: task fit, Trust Score, Audit Score, install safety, permission surface, and a concrete validation plan before this skill touches a workspace.

Needs reviewMEDIUM RISKREVIEW POLICY
84
Eval
80
Trust
90
Audit
66
Safety

manual review

Require human approval before installing into a real workspace.

Required gates

Checks an agent must pass before install

Open JSON

Task fit

84

pass

Task wording matches this skill metadata.

  • Evaluate Seedance 2.0 Skill OS before installing it in an agent workflow
  • Creative
  • Multimodal media workflows; Claude Code teams; teams that value GitHub adoption signals

Install path

92

pass

Install handoff is available.

  • python scripts/install_codex_skill.py --force

Install command safety

92

pass

simple repository or package install path

  • python scripts/install_codex_skill.py --force

Trust score

80

warn

Good trust signals with a few areas worth checking before rollout.

  • Strong shortlist
  • 796 GitHub stars
  • MIT

Audit score

90

pass

Safe to try

  • Installer replaces an existing local seedance-20 skill directory when --force is used; review scripts/install_codex_skill.py before running.

Agent safety gate

66

warn

Usable candidate, but the agent should surface permission and audit notes before installation.

  • Require human approval before installing into a real workspace.
  • High-risk permission hints: Shell or command execution

License clarity

86

pass

MIT

  • MIT

Permission surface

76

warn

shell or command execution

  • Shell or command execution: high
  • Network access: medium

Validation plan

What the agent should do next

  1. 1Inspect repository, README/SKILL.md, license, and recent commits before production use.
  2. 2Install in an isolated workspace or sandbox with no production secrets available.
  3. 3Run the smallest representative task and record files touched, commands run, network access, and outputs.
  4. 4Compare the selected skill against at least one alternative when the eval status is review or failed.
  5. 5Promote only after the agent reports a successful verification result and unresolved warnings are accepted.

Do not use when

Conditions that require another skill

  • 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

Supporting checks

Trust signals behind the decision

README/SKILL.md completeness

pass

100

Metadata includes enough usage and workflow context

Recent maintenance

pass

100

18d since push

Alternatives available

info

55

No close alternatives were found in the current shortlist.