fai-suggest-agents — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited fai-suggest-agents (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 agents from the FrootAI catalog based on task and context.
| Domain | Example Agents | Use For |
|---|---|---|
| RAG & Search | fai-rag-architect, fai-embedding-expert | Building retrieval pipelines |
| Security | fai-security-reviewer, fai-red-team-expert | Security audits, pen testing |
| Infrastructure | fai-architect, fai-landing-zone | Azure architecture, IaC |
| Multi-Agent | fai-autogen-expert, fai-swarm-supervisor | Agent orchestration |
| DevOps | fai-devops-expert, fai-github-actions-expert | CI/CD, deployment |
| Testing | fai-test-generator, fai-code-reviewer | Test generation, PR review |
| Cost | fai-cost-optimizer, fai-capacity-planner | FinOps, right-sizing |
AGENT_MAP = {
"rag": ["fai-rag-architect", "fai-embedding-expert"],
"security": ["fai-security-reviewer", "fai-content-safety-expert"],
"infrastructure": ["fai-architect", "fai-azure-openai-expert"],
"testing": ["fai-test-generator", "fai-code-reviewer"],
"deployment": ["fai-devops-expert", "fai-github-actions-expert"],
"cost": ["fai-cost-optimizer"],
}
def suggest_agents(task_description: str) -> list[str]:
keywords = task_description.lower()
suggestions = []
for domain, agents in AGENT_MAP.items():
if domain in keywords or any(a.replace("fai-","").replace("-"," ") in keywords for a in agents):
suggestions.extend(agents)
return suggestions[:3] or ["fai-architect"] # Default fallbackEach solution play has a builder/reviewer/tuner triad:
fai-play-{NN}-builder — Implements the solutionfai-play-{NN}-reviewer — Reviews for quality and securityfai-play-{NN}-tuner — Validates config and thresholds| Issue | Cause | Fix |
|---|---|---|
| Wrong agent suggested | Task description too vague | Ask for specific domain/technology |
| No matching agent | Task outside FAI catalog | Suggest fai-architect as generalist |
| Multiple agents needed | Multi-step workflow | Recommend builder→reviewer→tuner chain |
| 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.