fai-tutorial-generator — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited fai-tutorial-generator (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.
Use this skill to create practical tutorials that users can execute end-to-end without guessing hidden steps.
| Input | Required | Description |
|---|---|---|
| topic | Yes | Tutorial subject (for example: Azure OpenAI setup). |
| audience | Yes | Beginner, intermediate, advanced, or mixed. |
| runtime | No | Environment (Python, Node, .NET, Bash, etc.). |
| target_time_minutes | No | Time box for completion, default 30. |
| constraints | No | Cost, security, region, policy limits. |
A complete tutorial must include all sections below:
{
"title": "Build a Cost-Optimized RAG API",
"objective": "Deploy and test a small RAG API with guarded prompts.",
"estimated_time_minutes": 45,
"audience": "intermediate",
"sections": [
"Prerequisites",
"Project setup",
"Index creation",
"API implementation",
"Validation",
"Troubleshooting"
]
}Each step should include:
# Example verification step
python -m pytest tests/test_smoke.py -q# Example expected output assertion
assert response.status_code == 200
assert "citations" in response.json()| Gate | Pass Condition |
|---|---|
| Build gate | Project compiles/runs locally. |
| Functional gate | Key workflow returns expected output. |
| Reliability gate | Retry/fallback behavior works on transient failure. |
| Safety gate | Harmful/prompt-injection samples are blocked. |
| Cost gate | Estimated cost remains under budget threshold. |
| Symptom | Probable Cause | Fix |
|---|---|---|
| Command not found | Missing dependency or PATH issue | Install required tool and reopen shell. |
| Auth failure | Credential not set or expired | Re-authenticate and verify environment variables. |
| Timeout | Resource/network constraints | Increase timeout and validate endpoint health. |
| Wrong output format | Prompt/schema mismatch | Enforce strict output schema and re-test. |
Before finalizing a tutorial, verify:
# <Tutorial Title>
## Objective
<One measurable goal>
## Prerequisites
- Tool A version x.y
- Tool B version x.y
## Steps
### 1. <Step>
Why:
Command/code:
Expected result:
## Verification
<commands and expected outputs>
## Troubleshooting
<table>
## Next Steps
<2-3 upgrades>~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.