Add v0.6.0: full skill/agent QA pass, 3 new agents tested, template cleanup

Skills fixed: sprint-status (stale escalation, threshold), retrospective
(existing file detection, missing data fallback), changelog (misc category,
task-ref count), patch-notes (BLOCKED on missing changelog, tone/template
paths), story-readiness (Phase 0 mode resolution, QL-STORY-READY gate),
art-bible, brainstorm, design-system, ux-design, dev-story, story-done,
create-architecture, create-control-manifest, map-systems, propagate-design-change,
quick-design, prototype, asset-spec.

Agents fixed: all 4 directors (gate verdict token format), engine-programmer,
ui-programmer, tools-programmer, technical-artist (engine version safety),
gameplay-programmer (ADR compliance), godot-gdextension-specialist (ABI warning),
systems-designer (escalation path to creative-director), accessibility-specialist
(model, tools, WCAG criterion format, findings template), live-ops-designer
(escalation paths, battle pass value language), qa-tester (model, test case
format, evidence routing, ambiguous criteria, regression scope).

Specs updated: smoke-check and adopt specs rewritten to match actual skill
behavior. catalog.yaml reset to blank template state. Removed
session-state marketing research file, removed session-state from gitignore.

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

CCGS Skill Testing Framework/skills/utility/adopt.md

@@ -2,17 +2,16 @@
 
 ## Skill Summary
 
-`/adopt` performs brownfield onboarding: it reads an existing non-Claude-Code
-project's source files, detects the engine and language, and generates a
-matching CLAUDE.md stub plus a populated `technical-preferences.md` to bring
-the project under the Claude Code Game Studios framework. It may also produce
-skeleton GDD files if enough design intent can be inferred from the code.
+`/adopt` audits an existing project's artifacts — GDDs, ADRs, stories, infrastructure
+files, and `technical-preferences.md` — for format compliance with the template's
+skill pipeline. It classifies every gap by severity (BLOCKING / HIGH / MEDIUM / LOW),
+composes a numbered, ordered migration plan, and writes it to `docs/adoption-plan-[date].md`
+after explicit user approval via `AskUserQuestion`.
 
-Each generated file is gated behind a "May I write" ask. If an existing CLAUDE.md
-or `technical-preferences.md` is detected, the skill offers to merge rather than
-overwrite. The skill has no director gates. Verdicts: COMPLETE (full analysis done
-and files written), PARTIAL (analysis complete but some fields are ambiguous),
-or BLOCKED (cannot proceed — no source code found or user declined all writes).
+This skill is distinct from `/project-stage-detect` (which checks what exists).
+`/adopt` checks whether what exists will actually work with the template's skills.
+
+No director gates apply. The skill does NOT invoke any director agents.
 
 ---
 
@@ -22,149 +21,194 @@ Verified automatically by `/skill-test static` — no fixture needed.
 
 - [ ] Has required frontmatter fields: `name`, `description`, `argument-hint`, `user-invocable`, `allowed-tools`
 - [ ] Has ≥2 phase headings
-- [ ] Contains verdict keywords: COMPLETE, PARTIAL, BLOCKED
-- [ ] Contains "May I write" collaborative protocol language before each file creation
-- [ ] Has a next-step handoff at the end (e.g., `/setup-engine` to refine or `/brainstorm`)
+- [ ] Contains severity tier keywords: BLOCKING, HIGH, MEDIUM, LOW
+- [ ] Contains "May I write" or `AskUserQuestion` language before writing the adoption plan
+- [ ] Has a next-step handoff at the end (e.g., offering to fix the highest-priority gap immediately)
 
 ---
 
 ## Director Gate Checks
 
-None. `/adopt` is a brownfield onboarding utility. No director gates apply.
+None. `/adopt` is a brownfield audit utility. No director gates apply.
 
 ---
 
 ## Test Cases
 
-### Case 1: Happy Path — Existing Unity project with C# code detected
+### Case 1: Happy Path — All GDDs compliant, no gaps, COMPLIANT
 
 **Fixture:**
-- `src/` contains `.cs` files with Unity-specific namespaces (`using UnityEngine;`)
-- No CLAUDE.md overrides, no `technical-preferences.md` beyond placeholders
-- Project has a recognizable folder structure (Assets/, Scripts/)
+- `design/gdd/` contains 3 GDD files; each has all 8 required sections with content
+- `docs/architecture/adr-0001.md` exists with `## Status`, `## Engine Compatibility`,
+  and all other required sections
+- `production/stage.txt` exists
+- `docs/architecture/tr-registry.yaml` and `docs/architecture/control-manifest.md` exist
+- Engine configured in `technical-preferences.md`
 
 **Input:** `/adopt`
 
 **Expected behavior:**
-1. Skill scans `src/` and detects C# files with Unity API imports
-2. Skill identifies engine as Unity, language as C#
-3. Skill produces a draft `technical-preferences.md` with engine/language fields populated
-4. Skill produces a draft CLAUDE.md stub with detected project structure
-5. Skill asks "May I write `technical-preferences.md`?" and then "May I write CLAUDE.md?"
-6. Files are written after approval; verdict is COMPLETE
+1. Skill emits "Scanning project artifacts..." then reads all artifacts silently
+2. Reports detected phase, GDD count, ADR count, story count
+3. Phase 2 audit: all 3 GDDs have all 8 sections, Status field present and valid
+4. ADR audit: all required sections present
+5. Infrastructure audit: all critical files exist
+6. Phase 3: zero BLOCKING, zero HIGH, zero MEDIUM, zero LOW gaps
+7. Summary reports: "No blocking gaps — this project is template-compatible"
+8. Uses `AskUserQuestion` to ask about writing the plan; user selects write
+9. Adoption plan is written to `docs/adoption-plan-[date].md`
+10. Phase 7 offers next action: no blocking gaps, offers options for next steps
 
 **Assertions:**
-- [ ] Engine detected as Unity (not Godot or Unreal)
-- [ ] Language detected as C#
-- [ ] Draft is shown to user before any "May I write" ask
-- [ ] "May I write" is asked separately for each file
-- [ ] Verdict is COMPLETE after both files are written
+- [ ] Skill reads silently before presenting any output
+- [ ] "Scanning project artifacts..." appears before the silent read phase
+- [ ] Gap counts show 0 BLOCKING, 0 HIGH, 0 MEDIUM (or only LOW)
+- [ ] `AskUserQuestion` is used before writing the adoption plan
+- [ ] Adoption plan file is written to `docs/adoption-plan-[date].md`
+- [ ] Phase 7 offers a specific next action (not just a list)
 
 ---
 
-### Case 2: Mixed Languages — Partial analysis, asks user to clarify
+### Case 2: Non-Compliant Documents — GDDs missing sections, NEEDS MIGRATION
 
 **Fixture:**
-- `src/` contains both `.gd` (GDScript) and `.cs` (C#) files
-- Engine cannot be definitively identified from the mix
+- `design/gdd/` contains 2 GDD files:
+  - `combat.md` — missing `## Acceptance Criteria` and `## Formulas` sections
+  - `movement.md` — all 8 sections present
+- One ADR (`adr-0001.md`) is missing `## Status` section
+- `docs/architecture/tr-registry.yaml` does not exist
 
 **Input:** `/adopt`
 
 **Expected behavior:**
-1. Skill scans source and detects conflicting language signals
-2. Skill reports: "Mixed language signals detected (GDScript + C#) — cannot auto-identify engine"
-3. Skill presents the ambiguous findings and asks the user to confirm: Godot with C# or Unity?
-4. After user clarifies, skill resumes analysis with confirmed engine
-5. Produces a PARTIAL analysis noting fields that required manual clarification
+1. Skill scans all artifacts
+2. Phase 2 audit finds:
+   - `combat.md`: 2 missing sections (Acceptance Criteria, Formulas)
+   - `adr-0001.md`: missing `## Status` — BLOCKING impact
+   - `tr-registry.yaml`: missing — HIGH impact
+3. Phase 3 classifies:
+   - BLOCKING: `adr-0001.md` missing `## Status` (story-readiness silently passes)
+   - HIGH: `tr-registry.yaml` missing; `combat.md` missing Acceptance Criteria (can't generate stories)
+   - MEDIUM: `combat.md` missing Formulas
+4. Phase 4 builds ordered migration plan:
+   - Step 1 (BLOCKING): Add `## Status` to `adr-0001.md` — command: `/architecture-decision retrofit`
+   - Step 2 (HIGH): Run `/architecture-review` to bootstrap tr-registry.yaml
+   - Step 3 (HIGH): Add Acceptance Criteria to `combat.md` — command: `/design-system retrofit`
+   - Step 4 (MEDIUM): Add Formulas to `combat.md`
+5. Gap Preview shows BLOCKING items as bullets (actual file names), HIGH/MEDIUM as counts
+6. `AskUserQuestion` asks to write the plan; writes after approval
+7. Phase 7 offers to fix the highest-priority gap (ADR Status) immediately
 
 **Assertions:**
-- [ ] Skill does NOT guess or silently pick an engine when signals conflict
-- [ ] Ambiguous findings are reported to the user explicitly
-- [ ] User choice is incorporated into the generated config
-- [ ] Verdict is PARTIAL (not COMPLETE) when manual clarification was required
+- [ ] BLOCKING gaps are listed as explicit file-name bullets in the Gap Preview
+- [ ] HIGH and MEDIUM shown as counts in Gap Preview
+- [ ] Migration plan items are in BLOCKING-first order
+- [ ] Each plan item includes the fix command or manual steps
+- [ ] `AskUserQuestion` is used before writing
+- [ ] Phase 7 offers to immediately retrofit the first BLOCKING item
 
 ---
 
-### Case 3: CLAUDE.md Already Exists — Offers merge rather than overwrite
+### Case 3: Mixed State — Some docs compliant, some not, partial report
 
 **Fixture:**
-- `CLAUDE.md` exists with custom content (project name, existing imports)
-- `technical-preferences.md` exists with some fields populated
+- 4 GDD files: 2 fully compliant, 2 with gaps (one missing Tuning Knobs, one missing Edge Cases)
+- ADRs: 3 files — 2 compliant, 1 missing `## ADR Dependencies`
+- Stories: 5 files — 3 have TR-ID references, 2 do not
+- Infrastructure: all critical files present; `technical-preferences.md` fully configured
 
 **Input:** `/adopt`
 
 **Expected behavior:**
-1. Skill reads existing CLAUDE.md and detects it is already populated
-2. Skill reports: "CLAUDE.md already exists — offering to merge, not overwrite"
-3. Skill presents a diff of new fields vs. existing content
-4. Skill asks "May I merge new fields into CLAUDE.md?" (not "May I write")
-5. If user approves: only new or changed fields are added; existing content preserved
+1. Skill audits all artifact types
+2. Audit summary shows totals: "4 GDDs (2 fully compliant, 2 with gaps); 3 ADRs
+   (2 fully compliant, 1 with gaps); 5 stories (3 with TR-IDs, 2 without)"
+3. Gap classification:
+   - No BLOCKING gaps
+   - HIGH: 1 ADR missing `## ADR Dependencies`
+   - MEDIUM: 2 GDDs with missing sections; 2 stories missing TR-IDs
+   - LOW: none
+4. Migration plan lists HIGH gap first, then MEDIUM gaps in order
+5. Note included: "Existing stories continue to work — do not regenerate stories
+   that are in progress or done"
+6. `AskUserQuestion` to write plan; writes after approval
 
 **Assertions:**
-- [ ] Skill does NOT overwrite existing CLAUDE.md without explicit user approval for a full replace
-- [ ] Merge option is offered when the file already exists
-- [ ] Diff is shown before the merge ask
-- [ ] Existing custom content is preserved in the merged output
+- [ ] Per-artifact compliance tallies are shown (N compliant, M with gaps)
+- [ ] Existing story compatibility note is included in the plan
+- [ ] No BLOCKING gaps results in no BLOCKING section in migration plan
+- [ ] HIGH gap precedes MEDIUM gaps in plan ordering
+- [ ] `AskUserQuestion` is used before writing
 
 ---
 
-### Case 4: No Source Code Found — Stops with error
+### Case 4: No Artifacts Found — Fresh project, guidance to run /start
 
 **Fixture:**
-- Repository has only documentation files (`.md`) and no source code in `src/`
-- No engine-identifiable files anywhere in the repo
+- Repository has no files in `design/gdd/`, `docs/architecture/`, `production/epics/`
+- `production/stage.txt` does not exist
+- `src/` directory does not exist or has fewer than 10 files
+- No game-concept.md, no systems-index.md
 
 **Input:** `/adopt`
 
 **Expected behavior:**
-1. Skill scans `src/` and all likely code locations — finds nothing
-2. Skill outputs: "No source code detected — cannot perform brownfield analysis"
-3. Skill suggests alternatives: run `/start` for a new project, or point to a
-   different directory if source is located elsewhere
-4. No files are written
+1. Phase 1 existence check finds no artifacts
+2. Skill infers "Fresh" — no brownfield work to migrate
+3. Uses `AskUserQuestion`:
+   - "This looks like a fresh project — no existing artifacts found. `/adopt` is for
+     projects with work to migrate. What would you like to do?"
+   - Options: "Run `/start`", "My artifacts are in a non-standard location", "Cancel"
+4. Skill stops — does not proceed to audit regardless of user selection
 
 **Assertions:**
-- [ ] Verdict is BLOCKED
-- [ ] Error message explicitly states no source code was found
-- [ ] Alternatives (`/start` or directory guidance) are provided
-- [ ] No "May I write" prompts appear (nothing to write)
+- [ ] `AskUserQuestion` is used (not a plain text message) when no artifacts are found
+- [ ] `/start` is presented as a named option
+- [ ] Skill stops after the question — no audit phases run
+- [ ] No adoption plan file is written
 
 ---
 
-### Case 5: Director Gate Check — No gate; adopt is a utility onboarding skill
+### Case 5: Director Gate Check — No gate; adopt is a utility audit skill
 
 **Fixture:**
-- Existing project with detectable source code
+- Project with a mix of compliant and non-compliant GDDs
 
 **Input:** `/adopt`
 
 **Expected behavior:**
-1. Skill completes full brownfield analysis and produces config files
+1. Skill completes full audit and produces migration plan
 2. No director agents are spawned at any point
 3. No gate IDs (CD-*, TD-*, AD-*, PR-*) appear in output
+4. No `/gate-check` is invoked during the skill run
 
 **Assertions:**
 - [ ] No director gate is invoked
 - [ ] No gate skip messages appear
-- [ ] Skill reaches COMPLETE or PARTIAL without any gate verdict
+- [ ] Skill reaches plan-writing or cancellation without any gate verdict
 
 ---
 
 ## Protocol Compliance
 
-- [ ] Scans source before generating any config content
-- [ ] Shows draft config to user before asking to write
-- [ ] Asks "May I write" (or "May I merge") before each file operation
-- [ ] Detects existing files and offers merge path rather than silent overwrite
-- [ ] Ends with COMPLETE, PARTIAL, or BLOCKED verdict
+- [ ] Emits "Scanning project artifacts..." before silent read phase
+- [ ] Reads all artifacts silently before presenting any results
+- [ ] Shows Adoption Audit Summary and Gap Preview before asking to write
+- [ ] Uses `AskUserQuestion` before writing the adoption plan file
+- [ ] Adoption plan written to `docs/adoption-plan-[date].md` — not to any other path
+- [ ] Migration plan items ordered: BLOCKING first, HIGH second, MEDIUM third, LOW last
+- [ ] Phase 7 always offers a single specific next action (not a generic list)
+- [ ] Never regenerates existing artifacts — only fills gaps in what exists
+- [ ] Does not invoke director gates at any point
 
 ---
 
 ## Coverage Notes
 
-- The Unreal Engine + Blueprint detection case (`.uasset`, `.umap` files)
-  follows the same happy path pattern as Case 1 and is not separately tested.
-- Multi-directory source layouts (monorepo style) are not tested; the skill
-  assumes a conventional single-project structure.
-- GDD skeleton generation from inferred design intent is noted as a capability
-  but not fixture-tested here — it follows from the PARTIAL analysis pattern.
+- The `gdds`, `adrs`, `stories`, and `infra` argument modes narrow the audit scope;
+  each follows the same pattern as the full audit but limited to that artifact type.
+  Not separately fixture-tested here.
+- The systems-index.md parenthetical status value check (BLOCKING) is a special case
+  that triggers an immediate fix offer before writing the plan; not separately tested.
+- The review-mode.txt prompt (Phase 6b) runs after plan writing if `production/review-mode.txt`
+  does not exist; not separately tested here.