Skill Detail

Project Skill Audit

This skill audits a project's recurring workflows to recommend other skills. It prefers evidence from memory, rollout summaries, and existing skill folders.

GitHub:sickn33/antigravity-awesome-skills project-skill-audit
version 3d1ca7aaa538
static analysis only
no human review yet
Trusted

Current public label

Trusted

The only finding is a broken reference in the documentation, which is a low-severity issue. This does not affect the skill's functionality.

This label is currently coming from the automated scorecard.

Automated result

Trusted

Driftloom found a broken relative reference in the skill's documentation.

1 low Final label: trusted.

Human review

No human review has been recorded yet.

The current public label is still relying on automation. A human has not weighed in yet.

What happened

Driftloom completed a static scan. It inspected the skill files, recorded findings, and generated a scorecard.

Runtime evidence

No sandbox runtime result has been recorded yet.

What did not happen

  • Driftloom did not run this skill in an isolated sandbox yet.
  • This label is not a guarantee that the skill is safe, bug-free, or appropriate for every environment.
  • A good score does not replace human judgment when a skill touches secrets, shell access, or external systems.

Source provenance

Source: Workspace import

Originally ingested from a local workspace copy.

Scorecard

Safety
100
Quality
94
Transparency
100
Operational
92
Maintenance
82

1 low Final label: trusted.

Severity mix: 1 low

What Driftloom checked

  • Read the skill files and metadata to understand what the skill claims to do.
  • Looked for shell commands and risky command patterns, even if none stood out strongly.
  • Looked for external URLs and network behavior.
  • Looked for secrets and credential handling clues.
  • Checked for broken internal references and missing files.

Findings

Broken relative reference detected
reference.missing_relative_path · quality
Low

The source references `/Users/dimillian/.codex/skills/.system/skill-creator/SKILL.md`, but that path does not exist.

File: SKILL.md
Evidence: If the user asks to actually create or update one of the recommended skills, switch to [$skill-creator](/Users/dimillian/.codex/skills/.system/skill-creator/SKILL.md) and implement the chosen skill rather than continuing the audit.
Driftloom is following the boring, correct architecture: Django control plane first, isolated runner later. Miraculously, restraint survives.