skill_blank — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited skill_blank (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
<!-- FILE NAMING: This folder is named skill_blank/ to distinguish it in the lab. When deploying to a project, copy this folder to: .github/skills/<skill-name>/ .claude/skills/<skill-name>/ ← also works for Claude Code .agents/skills/<skill-name>/ Remove the "_blank" suffix from the folder name.
The Agent Skills specification is an open standard — this skill works with:
The AI loads this skill when the task matches the description above, or when the user explicitly references the skill name.
FOLDER STRUCTURE: <skill-name>/ ├── SKILL.md ← this file (required) ├── scripts/ ← executable scripts the skill can call (optional) ├── resources/ ← reference files, templates, docs (optional) └── assets/ ← static files used by scripts (optional) -->
[Describe the specialised knowledge or behaviour this skill provides. What can the AI do with this skill loaded that it cannot do without it?]
[Describe the task types or triggers that should activate this skill. Be specific — this helps the AI decide whether to load it.]
[Step-by-step instructions the AI should follow when this skill is active.]
[Describe the expected output: file edits, terminal commands, a report, etc.]
Input: [describe the trigger or task] Expected output: [describe what the AI should produce]
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.