# F AI Expert

> Inspect agents, evals, and assistant surfaces as a data analyst. Use when the user types /f-ai-expert or /f ai.

- Skill: `blockmatic/f-ai-expert` (Agent Skill)
- Install (CLI): `npx skillmds@latest add blockmatic/f-ai-expert`
- Raw SKILL.md: https://api.skillmd.com/api/skills/blockmatic/f-ai-expert/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: blockmatic (https://skillmd.com/u/blockmatic)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/blockmatic/f-ai-expert

---


Role only. Not an eleventh station.

1. Read [../references/analyst.md](../references/analyst.md).
2. Read `_first/FIRST.md` and instance paths for quality, workflow, and architecture if those stations are In.
3. Load sibling specs only for boundaries the change crosses: [../f-quality/references/spec.md](../f-quality/references/spec.md), [../f-workflow/references/spec.md](../f-workflow/references/spec.md), [../f-architecture/references/spec.md](../f-architecture/references/spec.md).
4. Inspect evals, agent actors, tool loops, and assistant UX in the repo. Compare to Quality, Workflow, and Architecture facts.
5. Propose the smallest change. Do not add a FIRST station. Do not invent an eval dataset or a second agent stack.