docs: clarify Chunk 3 skill library source and naming convention

Skills-index is now explicitly the canonical build reference for trigger
descriptions, constraints, and categories. Roadmap entry updated with
category breakdown, flat-path naming reconciliation (ADR-0009), authoring
standard reference, and delete-when-done instruction. Spec overview updated
to match.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

docs/spec/overview.md

@@ -11,6 +11,8 @@ Current deployed state of this repo — what you get if you run `install.sh` tod
 
 Current skills: `caveman`, `diagnose`, `grill-me`, `grill-with-docs`, `improve-codebase-architecture`, `prototype`, `tdd`, `to-issues`, `to-prd`, `triage`, `write-a-skill`, `zoom-out`.
 
+**Chunk 3 target:** the full skill library defined in `docs/research/ai-coding-factory/ai-coding-factory-skills-index.md`. That file is the canonical build reference — trigger descriptions, constraints, and category for each skill. Skills are stored flat (`skill-name/SKILL.md`) per ADR-0009; the `category/skill-name` notation in the skills-index is for identification only. Core categories: roles, design, factory, implement, test, review, deploy, operate, cross-cutting. Global optional: iac, gitea. Delete the skills-index once all skills exist.
+
 ### Claude Code configuration
 - `~/.claude/CLAUDE.md` — global config index; always-on rules + content index pointers
 - `~/.claude/core/instructions/` — coding, git, testing, governance instruction files