docs: Chunk 3 issues 0015-0028 and doc updates

14 issues created covering AGENTS.md refactor prerequisite, skill
implementation workflow grill, bootstrap skills (write-eval, write-skill),
remaining factory skills, and one issue per skill category group through
to chunk closure. All HITL; acceptance criteria for 0017-0028 to be
refined after 0016 grill session.

Doc updates: CONTEXT.md PRD/issue scope clarified (HOW distribution
across architecture-review and issue design notes); ROADMAP.md housekeeping
updated with bootstrap order and issue range; spec/overview.md recent
changes entry added; PRD updated (skills-index: delete → update).

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

docs/issues/0028-chunk-3-closure.md

@@ -0,0 +1,40 @@
+# 0028 — Chunk 3 closure: update skills-index, update spec, behavioral tests
+
+**Type:** HITL  
+**Parent PRD:** `docs/prd/chunk-3-skills-library.md`
+
+## What to build
+
+Close out Chunk 3 once all 42 skills are complete: update the skills index to reflect the implemented state, update the living spec, and run the full behavioral acceptance test suite.
+
+**Tasks:**
+1. Update `docs/research/ai-coding-factory/ai-coding-factory-skills-index.md` — replace the pre-implementation build reference with the as-implemented state: actual flat skill names, categories, trigger descriptions as deployed, any deviations from the original index noted
+2. Update `docs/spec/overview.md` — reflect the full 42-skill library as the current deployed state; remove "Chunk 3 target" language; mark Chunk 3 ✅ complete
+3. Update `docs/spec/architecture.md` — reflect the `.agents/evals/` directory structure added in Chunk 3; any other structural changes from implementation
+4. Update `docs/ROADMAP.md` — mark Chunk 3 ✅ complete in the chunk table
+5. Run behavioral acceptance tests — for each skill, invoke with its trigger phrase in a fresh Claude session and verify the output meets the authoring standard; document results
+
+**Behavioral test scope:** All 42 skills (including `write-eval`, `write-skill`, and the 4 preserved skills). The `caveman` skill is exempt — it has no content-generating behavior to verify.
+
+**LESSONS.md:** Extract any cross-session learnings from Chunk 3 implementation and add entries per the LESSONS.md format. Three or more observations on the same pattern graduate to the relevant standing file.
+
+## Acceptance criteria
+
+- [ ] `docs/research/ai-coding-factory/ai-coding-factory-skills-index.md` updated to reflect as-implemented state; deviations from original plan noted
+- [ ] `docs/spec/overview.md` updated; Chunk 3 marked ✅ complete; all 42 skills listed as deployed
+- [ ] `docs/spec/architecture.md` updated with `.agents/evals/` structure
+- [ ] `docs/ROADMAP.md` Chunk 3 row updated to ✅
+- [ ] Behavioral test run completed; all skills pass their trigger test; failures documented as issues for resolution
+- [ ] `LESSONS.md` updated with Chunk 3 observations
+- [ ] **HITL:** human verifies the complete skills library in a fresh session before marking Chunk 3 done
+
+## Blocked by
+
+- 0020 (design skills)
+- 0021 (implement skills)
+- 0022 (test skills)
+- 0023 (review skills)
+- 0024 (deploy skills)
+- 0025 (operate skills)
+- 0026 (IaC skills)
+- 0027 (cross-cutting skills)