# Flow Persona Author

> Per-persona behavioral persona-doc authoring sub-skill for the flow-architecture plugin (BC-14018; implements the persona half of CDR-023's doc set). Writes ONE markdown file at docs/product/personas/<slug.md per behavioral persona the project serves, conforming to the canonical persona template (5 FLOOR depth-spine sections, scored against quality-rubric P1–P5). Whole-file authoring — UNLIKE flow-doc-author / flow-journey-author there is NO deterministic frontmatter builder: a persona's front-matter (role/device/linearlabel/lastreviewed) carries no Linear-children fields, so Agent(persona-doc-author) returns the WHOLE file (front-matter + body) and only lastreviewed is dispatcher-supplied. Runs AFTER flow-journey-author so the per-domain journey docs (the persona's richest behavioral source) and the story docs (the personas: slug source) both exist. 1 agent per unique persona slug; parallel across personas with a concurrency cap of ~10 to avoid Claude Code background-agent queueing. 0 synchronous gates in default mode.

## Facts
- Page: https://tashan.sh/capability/skill-brite-nites-flow-persona-author
- tashan id: skill:Brite-Nites/flow-persona-author
- Source: https://github.com/Brite-Nites/brite-claude-plugins
- Type: skill
- Category: security
- tashan score: not scored (catalogued only — too little public evidence)
- Adoption: 9.0
- Upkeep: 95.0
- Freshness: 90.0
- Evidence coverage: 84% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- Official: no

## Install

```sh
cp -r flow-persona-author ~/.claude/skills/
```

## Security audit
Not scanned. We audit npm-published capabilities; this one has no npm package we can resolve, or has not reached the queue. This is not a clean bill of health.

---
Measured 2026-09-12 by tashan (https://tashan.sh) from public evidence. Scorer s5.