Star200+

Pre-install eval

pfc-marshall-test 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
70
Eval report
68
Trust
75
Audit
63
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 pfc-marshall-test before installing it in an agent workflow
  • security
  • Security and compliance workflows; Claude Code teams; builders willing to evaluate younger projects

Install path

92

pass

Install handoff is available.

  • npx skills add Echo-aloha/asphalt-codex-skills-5 --skill pfc-marshall-test

Install command safety

92

pass

standard package or runtime install path

  • npx skills add Echo-aloha/asphalt-codex-skills-5 --skill pfc-marshall-test

Trust score

68

warn

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

  • Manual review
  • 17 GitHub stars
  • MIT

Audit score

75

warn

Needs review

  • No executable scripts are included in the skill itself; it depends on external fistPkg and other skills, which limits standalone verification but is not a security risk.

Agent safety gate

63

warn

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

  • Require human approval before installing into a real workspace.
  • No executable scripts are included in the skill itself; it depends on external fistPkg and other skills, which limits standalone verification but is not a security risk.

License clarity

86

pass

MIT

  • MIT

Permission surface

100

pass

no high-risk permission surface in public metadata

  • 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
  • Low GitHub adoption signal
  • No executable scripts are included in the skill itself; it depends on external fistPkg and other skills, which limits standalone verification but is not a security risk.
  • The SKILL.md excerpt appears truncated in the provided documentation, though the repository likely contains the full file; ensure the complete workflow and limitations are present.
  • References to JTG standards are provided as checklists and explicitly avoid reproducing copyrighted text, which is good, but users must still confirm they have legal copies of the standards.

Supporting checks

Trust signals behind the decision

README/SKILL.md completeness

pass

86

Metadata includes enough usage and workflow context

Recent maintenance

pass

100

1d since push

Alternatives available

pass

82

Alternative skills are available for comparison.