OpenAgentSkill
GitHub200+

Pre-install eval

mock-lab 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
64
Eval report
64
Trust
70
Audit
50
Agent safety

manual review

Test manually in an isolated workspace and compare against safer alternatives.

Required gates

Checks an agent must pass before install

Open JSON

Task fit

94

pass

Task wording matches this skill metadata.

  • Evaluate mock-lab before installing it in an agent workflow
  • automation
  • Browser automation workflows; Claude Code teams; builders willing to evaluate younger projects

Install path

92

pass

Install handoff is available.

  • npx skills add riwonswain-ovo/OfferLoop --skill mock-lab

Install command safety

92

pass

standard package or runtime install path

  • npx skills add riwonswain-ovo/OfferLoop --skill mock-lab

Trust score

64

warn

Potentially useful, but at least one trust signal needs human inspection.

  • Manual review
  • 13 GitHub stars
  • MIT

Audit score

70

warn

Needs review

  • The skill reads and processes user-supplied materials such as JD, resume, and Feishu documents, but SKILL.md does not explicitly instruct the model to treat those materials as untrusted data and ignore any embedded instructions. This creates a prompt-injection risk.

Agent safety gate

50

warn

Sparse or mixed signals. Useful for discovery, but not for autonomous installation.

  • Test manually in an isolated workspace and compare against safer alternatives.
  • The skill reads and processes user-supplied materials such as JD, resume, and Feishu documents, but SKILL.md does not explicitly instruct the model to treat those materials as untrusted data and ignore any embedded instructions. This creates a prompt-injection risk.

License clarity

86

pass

MIT

  • MIT

Permission surface

74

warn

network or browser access, database access

  • Network access: medium
  • Filesystem access: medium
  • Database 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
  • Low GitHub adoption signal
  • The skill reads and processes user-supplied materials such as JD, resume, and Feishu documents, but SKILL.md does not explicitly instruct the model to treat those materials as untrusted data and ignore any embedded instructions. This creates a prompt-injection risk.
  • SKILL.md instructs running `../.offerloop-runtime/scripts/artifact_contract.py` without documenting what the script does, pinning its content, or verifying it is safe. If that script is not part of the reviewed skill directory, it is also a supply-chain risk.
  • The skill depends on `../.offerloop-runtime/...` and several referenced `references/...` files that are not all present in the submitted excerpt. If those dependencies are missing in the actual repository, the skill will fail during startup.

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.