docs-writinglisted

Write or revise Treq technical documentation under web/docs/, plus product pages that document shipped app behavior (roadmap, security, settings copy). Activate whenever an agent drafts, updates, or reviews technical docs for Treq: concept pages, how-tos, tutorials, reference, security, roadmap feature status, or related sidebar/index links. Owns accuracy against the current code and product state (shipped vs WIP), prerequisite honesty, cross-page consistency, and the doc revision checklist. Voice and banlists live in explain-to-me; Learn-site article structure and interlinking live in writing. Use this skill first for web/docs/** work.
treq-dev/treq · ★ 4 · AI & Automation · score 70

Install: claude install-skill treq-dev/treq

# docs-writing (technical docs for Treq) ## When to use Use this skill every time you write or revise **technical product documentation** for Treq: - Anything under `web/docs/**` (concepts, how-tos, tutorials, reference, security) - Product status pages that claim what ships today (`web/src/pages/roadmap.mdx`, changelog feature framing when it asserts availability) - Sidebar / index / guides copy that points readers at those features Do **not** treat changelog PR titles alone as proof a feature is user-ready. For Learn articles (`web/learn/**`), READMEs that are not product how-tos, and voice-only edits, prefer the `writing` and `explain-to-me` skills. When a Learn article documents a concrete Treq UI behavior, still apply the accuracy rules below. ## Skill stack | Concern | Skill | |---|---| | Product-doc accuracy, shipped vs WIP, prerequisites | **This skill (`docs-writing`)** | | Voice, Orwell, ASD-STE100, banlists, readability script | `explain-to-me` | | Learn-site skeleton, DefinitionCards, interlinking audit | `writing` | | Formatting baseline | `web/STYLE_GUIDE.md` | Read `explain-to-me` before drafting prose. Run its readability checker before you call the doc done. ## Mandatory research before drafting Never draft from memory or from a changelog bullet alone. 1. **Find the code path.** Locate the UI entry points and backend handlers (components, hooks, Tauri commands, native Node addon surface). Prefer reading those files over summarizing commit messages.