fai-skill-template — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited fai-skill-template (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.
Author SKILL.md files following the Agent Skills specification.
| Field | Required | Constraints |
|---|---|---|
| name | Yes | 1-64 chars, lowercase, hyphens, match folder |
| description | Yes | 1-1024 chars, WHAT + WHEN keywords |
| license | No | License name or file reference |
| compatibility | No | Environment requirements |
| metadata | No | Arbitrary key-value map |
---
name: my-skill-name
description: |
[Verb] [domain objects] with [techniques/tools]. Use this skill when:
- [Scenario 1 that triggers this skill]
- [Scenario 2]
- [Scenario 3]
---
# [Skill Title]
[One-sentence summary of what the skill does.]
## When to Use
- [Specific trigger 1]
- [Specific trigger 2]
- [Specific trigger 3]
---
## [Pattern/Step/Section 1]
\`\`\`[language]
[Real, runnable code example]
\`\`\`
## [Pattern/Step/Section 2]
\`\`\`[language]
[Real, runnable code example]
\`\`\`
## Troubleshooting
| Issue | Cause | Fix |
|-------|-------|-----|
| [Problem 1] | [Root cause] | [Solution] |
| [Problem 2] | [Root cause] | [Solution] || for trigger list# Bad — too generic
description: "Helps with testing"
# Good — keyword-rich with triggers
description: |
Write pytest tests with coverage reporting, parametrized cases, and
async fixtures. Use when setting up Python test infrastructure or
enforcing coverage thresholds in CI.| Issue | Cause | Fix |
|---|---|---|
| Skill not discovered | Name doesn't match folder | Ensure name == folder name |
| Agent never invokes skill | Description too vague | Add specific trigger scenarios |
| Skill too expensive to load | Over 500 lines | Move detail to references/ folder |
| Code examples outdated | No review cadence | Review quarterly |
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.