OpenAgentSkill
GitHub200+

Pre-install eval

cs-writer 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
71
Eval report
72
Trust
76
Audit
60
Agent 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

94

pass

Task wording matches this skill metadata.

  • Evaluate cs-writer before installing it in an agent workflow
  • research
  • Research agents workflows; Claude Code teams; builders willing to evaluate younger projects

Install path

92

pass

Install handoff is available.

  • npx skills add ChenShuo2004/cs-skills --skill cs-writer

Install command safety

92

pass

standard package or runtime install path

  • npx skills add ChenShuo2004/cs-skills --skill cs-writer

Trust score

72

warn

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

  • Strong shortlist
  • 118 GitHub stars
  • MIT

Audit score

76

warn

Needs review

  • No critical security risks found; the skill is text-processing only and does not request destructive actions, secrets, or external code execution.

Agent safety gate

60

warn

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

  • Require human approval before installing into a real workspace.
  • No critical security risks found; the skill is text-processing only and does not request destructive actions, secrets, or external code execution.

License clarity

86

pass

MIT

  • MIT

Permission surface

100

pass

no high-risk permission surface in public metadata

  • Browser automation: medium
  • 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
  • No critical security risks found; the skill is text-processing only and does not request destructive actions, secrets, or external code execution.
  • The description includes very broad trigger phrases such as "帮我写", which could cause the skill to activate for generic writing requests outside its intended ChenShuo-style workflow.
  • The SKILL.md excerpt ends mid-sentence in the Self Check section; if this reflects the actual file, the self-check may be incomplete.
  • Quality score needs review

Supporting checks

Trust signals behind the decision

README/SKILL.md completeness

pass

86

Metadata includes enough usage and workflow context

Recent maintenance

pass

88

2mo since push

Alternatives available

pass

82

Alternative skills are available for comparison.