fai-suggest-instructions — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited fai-suggest-instructions (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.
Suggest .instructions.md files based on project context and stack.
| Category | Examples | ApplyTo Pattern |
|---|---|---|
| WAF Pillars | waf-reliability, waf-security | **/*.{ts,py,bicep} |
| Languages | python-waf, csharp-waf | **/*.py, **/*.cs |
| Frameworks | fastapi-, aspnet- | **/api/** |
| IaC | bicep-, terraform- | **/*.bicep, **/*.tf |
| AI | rag-, prompt-, eval-* | **/*.py |
INSTRUCTION_MAP = {
"python": ["python-waf.instructions.md"],
"typescript": ["typescript-waf.instructions.md"],
"csharp": ["csharp-waf.instructions.md"],
"bicep": ["bicep-best-practices.instructions.md"],
"fastapi": ["fastapi-patterns.instructions.md"],
"security": ["waf-security.instructions.md"],
"reliability": ["waf-reliability.instructions.md"],
"cost": ["waf-cost-optimization.instructions.md"],
}
def suggest_instructions(stack: list[str]) -> list[dict]:
suggestions = []
for tech in stack:
for key, files in INSTRUCTION_MAP.items():
if key in tech.lower():
for f in files:
suggestions.append({"file": f, "reason": f"Matches {tech}"})
# Always include WAF security
suggestions.append({"file": "waf-security.instructions.md", "reason": "Required for all projects"})
return suggestions# .github/instructions/waf-security.instructions.md
---
description: Security patterns for AI applications
applyTo: "**/*.{ts,js,py,bicep,json,yaml,yml}"
---
[instruction content]| Issue | Cause | Fix |
|---|---|---|
| Instructions not activating | Wrong applyTo glob | Check glob matches file extensions |
| Too many instructions loaded | Broad globs | Narrow applyTo to relevant paths |
| Conflicting guidance | Multiple overlapping | Deduplicate, set priority order |
| Instructions outdated | No review cadence | Review quarterly with stack changes |
| Practice | Rationale |
|---|---|
| Start simple, add complexity when needed | Avoid over-engineering |
| Automate repetitive tasks | Consistency and speed |
| Document decisions and tradeoffs | Future reference for the team |
| Validate with real data | Don't rely on synthetic tests alone |
| Review with peers | Fresh eyes catch blind spots |
| Iterate based on feedback | First version is never perfect |
fai-implementation-plan-generator — Planning and milestonesfai-review-and-refactor — Code review patternsfai-quality-playbook — Engineering quality standards~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.