Release v1.0.0 — concept-prototype/vertical-slice split, workflow restructure, polish (#50)

* Add /vertical-slice skill, prototype overhaul, and workflow integration

- Add /vertical-slice skill for pre-production validation (Phase 4 gate)
- Overhaul /prototype skill with two-mode design: concept prototype (Phase 1)
  vs vertical slice (Phase 4), with clearer differentiation and higher standards for VS
- Update prototyper agent to own both prototype and vertical-slice workflows
- Add prototype-report.md and vertical-slice-report.md output templates
- Update WORKFLOW-GUIDE, quick-start, skills-reference, agent-coordination-map,
  and skill-flow-diagrams to fully integrate both skills into the 7-phase pipeline
- Remove orphaned empty quick-prototype/ directory

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

* sync v1 counts + polish

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

* Add entity inventory flow, relax vertical-slice gate, improve UX authoring prompts

- /asset-spec: new Phase 0b entity & screen inventory when no argument and no
  existing inventory — reads GDDs/art-bible, proposes categorized list, writes
  design/assets/entity-inventory.md collaboratively
- /asset-spec: entity/character target falls back to inline user description
  when no source doc exists, rather than failing
- /gate-check: vertical slice changed from blocking to CONCERNS-only when
  absent; built-but-broken slice still fails; adds entity inventory as gate artifact
- /ux-design: convert inline approval prompts to AskUserQuestion for structured
  option capture at key authoring decision points
- workflow-catalog.yaml: entity-inventory step added to pre-production; UX spec
  min_count raised to 3; vertical-slice and prototype marked required: false with
  updated descriptions
- .gitignore: exclude marrow/ eval tooling directory

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

* Add missing AskUserQuestion widgets to 7 skills

Audit found 11 decision points across 7 skills where structured option
prompts were missing — using plain text, auto-selection, or no gate at all.

Skills patched:
- create-epics: per-epic approval + producer CONCERNS verdict
- sprint-plan: producer CONCERNS verdict with scope/timeline options
- milestone-review: AT RISK / OFF TRACK producer verdicts require acknowledgement
- retrospective: existing-retro handling converted from plain text [A]/[B]
- quick-design: classification confirmation + draft approve/revise/redirect
- tech-debt add mode: category (6 options) + effort (S/M/L/XL) structured capture
- regression-suite: no-arg mode selection instead of silent auto-detect
- hotfix: severity confirmation gate before workflow begins

Also added AskUserQuestion to allowed-tools headers for retrospective,
quick-design, tech-debt, regression-suite, and hotfix.

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

* Prep v1 stable: fix WORKFLOW-GUIDE counts, stale agent names, and skill model fields

- WORKFLOW-GUIDE.md: correct agent count (48→49), skill count (66/68→73),
  add 6 missing skills to Appendix B, fix Creative category count (2→4),
  replace 3 non-existent agent names with correct ue-*/unity-* specialists,
  add missing godot-csharp/gdextension specialists to hierarchy,
  fix production/stories/ paths → production/epics/
- coordination-rules.md: replace "not yet used" with opt-in env var note
- quick-start.md: rename duplicate "Validate the concept" label → "Prototype the mechanic"
- skill-flow-diagrams.md: remove duplicate legacy UX pipeline section
- All 62 skills missing model: field now have explicit model: sonnet

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

* fix: comprehensive skill audit — consistency, UX, and flow gaps

Two-pass audit fixing ~35 bugs across 41 files.

Pre-production flow:
- Brainstorm next-steps split into Path A (design-first) and Path B
  (prototype-first) — eliminates "prototype after architecture" confusion
- /architecture-review added to pre-production flow in brainstorm and
  create-architecture handoffs
- gate-check traceability check corrected to requirements-traceability.md
- dev-story TR registry error now points to /architecture-review (not /create-epics)
- start now writes production/stage.txt on first onboarding

AskUserQuestion gaps filled:
- balance-check, code-review, hotfix, day-one-patch, consistency-check
  all gain closing widgets and/or missing allowed-tools declarations
- hotfix git branch creation now requires user confirmation
- sprint-plan review-mode setup moved to Phase 0 (before gates run)
- team-combat gains architecture→implementation approval gate
- design-review APPROVED path consolidated from 3 widgets to 1 multiSelect

All 9 team-* skills:
- Phase 0 review-mode resolution added (solo/lean/full now respected)
- team-audio output path fixed (design/gdd/ → design/audio/)
- team-level final doc compilation delegated to level-designer subagent
- team-narrative localization-lead added to composition list
- team-qa sprint path fixed (flat files, not directories)
- team-release NO-GO override captures written justification
- team-live-ops Cancel verdict now explicitly BLOCKED

Other fixes:
- Art bible path standardized to design/art/art-bible.md (3 wrong refs)
- AD-PHASE-GATE added to lean-mode skip list in director-gates.md
- design-system duplicate 5d heading fixed; skeleton decline path added;
  mandatory agent spawns now respect review mode
- story-readiness acceptance criteria thresholds now type-aware
- create-stories gains multi-ADR and no-ADR handling guidance
- consistency-check creates docs/consistency-failures.md on first run
- retrospective frontmatter bash injection replaced with explicit Bash call
- smoke-check ls -t gains PowerShell fallback
- Conventional Commits format documented in coding-standards.md
- gate-check: ADR acceptance gate, QA plan check, chain-of-verification
  tool-action requirement all added

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

* fix: expose --review flag in argument-hints for all team-* skills

All 9 team-* skills already implement Phase 0 review-mode resolution
internally (full/lean/solo), but none advertised [--review full|lean|solo]
in their argument-hint. Users had no way to discover the per-run override.

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

* docs: add SECURITY.md with coordinated disclosure policy

Defines scope, reporting process (GitHub private vulnerability reporting),
contributor security guidelines for hooks/skills/agents, and 90-day
coordinated disclosure timeline.

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

* docs: add CONTRIBUTING.md with framework contribution guidelines

Covers what PRs are welcome, skill/hook/agent technical requirements,
the collaborative principle, testing expectations, commit format,
and platform compatibility requirements.

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

* docs: add v1.0.0-beta → v1.0 upgrade section to UPGRADING.md

Documents the 17 commits since the beta tag: new /vertical-slice gate,
entity inventory flow in /map-systems, AskUserQuestion widgets across
7 skills, --review flag exposure on team-* skills, bug fixes
(#21, #36, #42, #43, #45), and the new CONTRIBUTING.md and SECURITY.md.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>

.claude/docs/templates/game-concept.md

@@ -309,8 +309,9 @@ the combat-crafting loop engaging for 30+ minute sessions"]
 - [ ] Get concept approval from creative-director
 - [ ] Fill in CLAUDE.md technology stack based on engine choice (`/setup-engine`)
 - [ ] Create game pillars document (`/design-review` to validate)
-- [ ] Decompose concept into systems (`/map-systems` — maps dependencies, assigns priorities, guides per-system GDD writing)
-- [ ] Create first architecture decision record (`/architecture-decision`)
-- [ ] Prototype core loop (`/prototype [core-mechanic]`)
+- [ ] **Prototype core idea** (`/prototype [core-mechanic]`) — before writing GDDs, validate the concept is worth designing
+- [ ] If prototype PROCEEDS: Decompose concept into systems (`/map-systems`)
+- [ ] Design each system (`/design-system [system-name]`) — use prototype learnings in Tuning Knobs and Formulas sections
+- [ ] Build vertical slice in Pre-Production (`/vertical-slice`) — validate full game loop before committing to Production
 - [ ] Validate core loop with playtest (`/playtest-report`)
 - [ ] Plan first milestone (`/sprint-plan new`)

.claude/docs/templates/hud-design.md

@@ -7,7 +7,7 @@
 > **Platform Targets**: [All platforms this HUD must work on — e.g., PC, PS5, Xbox Series X, Steam Deck]
 > **Related GDDs**: [Every system that exposes information through the HUD — e.g., `design/gdd/combat.md`, `design/gdd/progression.md`, `design/gdd/quests.md`]
 > **Accessibility Tier**: Basic | Standard | Comprehensive | Exemplary
-> **Style Reference**: [Link to art bible HUD section if it exists — e.g., `design/gdd/art-bible.md § HUD Visual Language`]
+> **Style Reference**: [Link to art bible HUD section if it exists — e.g., `design/art/art-bible.md § HUD Visual Language`]
 
 > **Note — Scope boundary**: This document specifies all elements that overlay the
 > game world during active gameplay — health bars, ammo counters, minimaps, quest

.claude/docs/templates/interaction-pattern-library.md

@@ -7,7 +7,7 @@
 > **Engine**: [Godot 4.6 / Unity 6 / Unreal Engine 5]
 > **UI Framework**: [Godot Control nodes / Unity UI Toolkit / Unreal UMG]
 > **Related Documents**:
-> - `docs/art-bible.md` — visual standards (colors, typography, iconography)
+> - `design/art/art-bible.md` — visual standards (colors, typography, iconography)
 > - `docs/accessibility-requirements.md` — accessibility commitments per feature
 > - `docs/ux/ux-spec-[screen].md` — individual screen specs that reference patterns
 

.claude/docs/templates/prototype-report.md

@@ -0,0 +1,114 @@
+# Concept Prototype Report: [Concept Name]
+
+> **Date**: [YYYY-MM-DD]
+> **Prototype Path**: [HTML / Engine / Paper]
+> **Concept File**: design/gdd/game-concept.md (if exists)
+
+---
+
+## Hypothesis
+
+[The falsifiable hypothesis this prototype set out to test:
+"If the player [does X], they will feel [Y] — evidenced by [measurable signal Z]."]
+
+---
+
+## Riskiest Assumption Tested
+
+[What was identified as the biggest risk in the concept, and whether it proved out.]
+
+---
+
+## Approach
+
+[What was built, how long it took, what shortcuts were taken deliberately.]
+
+**Path chosen:** [HTML / Engine / Paper]
+**Reason for path:** [Why this path was appropriate for this hypothesis]
+
+**Shortcuts taken (intentional):**
+- [e.g., hardcoded values, placeholder art, no menus, etc.]
+
+---
+
+## Result
+
+[What actually happened — specific observations, not opinions. Quote playtesters
+directly where possible.]
+
+---
+
+## Metrics
+
+| Metric | Value |
+|--------|-------|
+| Path used | [HTML / Engine / Paper] |
+| Iterations to playable | [N — Engine path only; N/A otherwise] |
+| Prototype duration | [e.g., 4 hours] |
+| Playtesters | [N internal / N external] |
+| Feel assessment | [Specific — "response felt sluggish at 200ms" not "felt bad"] |
+| Hypothesis verdict | [CONFIRMED / PARTIALLY CONFIRMED / REFUTED] |
+
+---
+
+## Recommendation: [PROCEED / PIVOT / KILL]
+
+[One paragraph explaining the recommendation with evidence from the result above.]
+
+---
+
+## If Proceeding
+
+[What the prototype revealed that should directly inform GDD writing:]
+
+- **Core tuning values discovered:** [e.g., "jump height of 3.5 units felt best"]
+- **Assumptions confirmed:** [What the concept doc assumed that proved true]
+- **Assumptions disproved:** [What the concept doc assumed that proved wrong]
+- **Emergent mechanics:** [Behaviors that appeared during testing worth formalizing]
+
+> Note: If HTML path was used and feel is uncertain, consider an engine prototype
+> targeting feel specifically before committing to GDDs.
+
+**Next steps:**
+1. `/design-review design/gdd/game-concept.md`
+2. `/gate-check`
+3. `/map-systems`
+4. `/design-system [mechanic]` (use learnings in Tuning Knobs and Formulas sections)
+
+---
+
+## If Pivoting
+
+[What alternative direction the results suggest — what felt almost right and what
+to adjust. Be specific about what to change, not just that something needs changing.]
+
+**Pivot direction:** [What to try differently]
+**What to keep:** [What worked and should be preserved]
+**Next step:** `/prototype [revised-concept]`
+
+---
+
+## If Killing
+
+[Why this concept does not work — what specific signal led to this verdict.
+This report is the deliverable; no further action needed on this concept.]
+
+**Next step:** `/brainstorm [new-direction]`
+
+---
+
+## Lessons Learned
+
+- **What assumptions were broken by actually building this?**
+  [...]
+
+- **What surprised us that didn't show up in the brainstorm?**
+  [...]
+
+- **What would we test differently next time?**
+  [...]
+
+---
+
+> *Prototype code location: `prototypes/[concept-name]-concept/`*
+> *This code is throwaway. Never refactor into production.*

.claude/docs/templates/sprint-plan.md

@@ -1,4 +1,4 @@
-# Sprint [N] -- [Start Date] to [End Date]
+# Sprint [N] — [Start Date] to [End Date]
 
 ## Sprint Goal
 
@@ -12,14 +12,9 @@
 
 ## Capacity
 
-| Resource | Available Days | Allocated | Buffer (20%) | Remaining |
-|----------|---------------|-----------|-------------|-----------|
-| Programming | | | | |
-| Design | | | | |
-| Art | | | | |
-| Audio | | | | |
-| QA | | | | |
-| **Total** | | | | |
+- **Total days**: [X]
+- **Buffer (20%)**: [Y days reserved for unplanned work]
+- **Available**: [Z days]
 
 ## Tasks
 
@@ -59,17 +54,13 @@
 
 ## Definition of Done
 
-- [ ] All Must Have tasks completed and passing acceptance criteria
+- [ ] All Must Have tasks completed
+- [ ] All tasks pass acceptance criteria
+- [ ] QA plan exists (`production/qa/qa-plan-sprint-[N].md`)
+- [ ] All Logic/Integration stories have passing unit/integration tests
+- [ ] Smoke check passed (`/smoke-check sprint`)
+- [ ] QA sign-off report: APPROVED or APPROVED WITH CONDITIONS (`/team-qa sprint`)
 - [ ] No S1 or S2 bugs in delivered features
-- [ ] Code reviewed and merged to develop
-- [ ] Design documents updated for any deviations from spec
-- [ ] Test cases written and executed for all new features
-- [ ] Asset naming and format standards met
+- [ ] Design documents updated for any deviations
+- [ ] Code reviewed and merged
 
-## Daily Status Tracking
-
-| Day | Tasks Completed | Tasks In Progress | Blockers | Notes |
-|-----|----------------|------------------|----------|-------|
-| Day 1 | | | | |
-| Day 2 | | | | |
-| Day 3 | | | | |

.claude/docs/templates/systems-index.md

@@ -143,4 +143,4 @@ These should be prototyped early regardless of priority tier.]
 - [ ] Design MVP-tier systems first (use `/design-system [system-name]`)
 - [ ] Run `/design-review` on each completed GDD
 - [ ] Run `/gate-check pre-production` when MVP systems are designed
-- [ ] Prototype the highest-risk system early (`/prototype [system]`)
+- [ ] Validate the highest-risk systems with `/vertical-slice` before committing to Production

.claude/docs/templates/test-evidence.md

@@ -65,9 +65,13 @@ If nothing notable: *No significant observations.*
 
 ## Sign-Off
 
-All three sign-offs are required before the story can be marked COMPLETE via
-`/story-done`. Visual/Feel stories require the designer or art-lead sign-off.
-UI stories require the UX lead or designer sign-off.
+All roles must sign off before the story can be marked COMPLETE via `/story-done`.
+Visual/Feel stories require the designer or art-lead sign-off. UI stories require
+the UX lead or designer sign-off.
+
+**Solo developers**: all sign-offs may be by the same person in each role. The
+intent is that someone deliberately reviews the evidence before marking complete —
+not that three separate people must participate.
 
 | Role | Name | Date | Signature |
 |------|------|------|-----------|

.claude/docs/templates/test-plan.md

@@ -114,31 +114,9 @@ A story is DONE when ALL of the following are true:
 
 ---
 
-## Test Results
-
-*Fill in after testing is complete.*
-
-| Story | Automated | Manual | Result | Notes |
-|-------|-----------|--------|--------|-------|
-| [title] | PASS | — | PASS | |
-| [title] | — | PASS | PASS | |
-| [title] | FAIL | — | BLOCKED | [describe failure] |
-
 ---
 
-## Bugs Found
-
-| ID | Story | Severity | Description | Status |
-|----|-------|----------|-------------|--------|
-| BUG-001 | | S[1-4] | | Open |
-
----
-
-## Sign-Off
-
-- **QA Tester**: [name] — [date]
-- **QA Lead**: [name] — [date]
-- **Sprint Owner**: [name] — [date]
+*Results and sign-off are tracked in the QA sign-off report generated by `/team-qa` — not in this plan file.*
 
 *Template: `.claude/docs/templates/test-plan.md`*
 *Generated by: `/qa-plan` — do not edit this line*

.claude/docs/templates/vertical-slice-report.md

@@ -0,0 +1,169 @@
+# Vertical Slice Report: [Concept Name]
+
+> **Date**: [YYYY-MM-DD]
+> **Slice Duration**: [N days]
+> **Target Scope**: 3–5 minutes of polished, continuous gameplay
+> **Source GDD**: design/gdd/game-concept.md
+
+---
+
+## Validation Question
+
+[The full game loop question this build was proving — both experience AND feasibility:
+"Does a player, starting from nothing, experience [core fantasy] within [N] minutes,
+without developer guidance — and can we build one such loop in [X] days at
+representative quality?"]
+
+---
+
+## Scope Built
+
+[Systems implemented, art quality level, what was intentionally omitted.]
+
+**Systems included:**
+- [System 1]
+- [System 2]
+- [...]
+
+**Art/audio quality level:** [Placeholder / Representative / Near-shipping]
+**Shortcuts taken deliberately:** [List]
+**What was cut from original scope:** [List]
+
+---
+
+## Build Velocity Log
+
+[Day-by-day record of what was completed. This is your real production rate data —
+use it in sprint planning.]
+
+| Day | Completed |
+|-----|-----------|
+| Day 1 | [What was built] |
+| Day 2 | [What was built] |
+| Day 3 | [What was built] |
+| ... | ... |
+
+**Total elapsed:** [N days] for [scope summary]
+**Velocity estimate:** [N hours per equivalent scope unit — e.g., "1 day per combat
+encounter, 0.5 days per UI screen"]
+
+---
+
+## Playtest Results
+
+| Attribute | Value |
+|-----------|-------|
+| Total sessions | [N] |
+| Internal testers | [N] |
+| External testers | [N — people who had not seen the game, if available] |
+| Avg session length | [N minutes (target: [N] minutes)] |
+| Time to first meaningful action | [N seconds (target: [N] seconds)] |
+
+---
+
+## Observations
+
+[Specific, non-opinion observations from playtest sessions. Quote testers where useful.]
+
+**Where testers succeeded without guidance:**
+- [...]
+
+**Where testers were confused or stuck:**
+- [...]
+
+**Emotional reactions observed:**
+- [...]
+
+---
+
+## Metrics
+
+| Metric | Target | Actual |
+|--------|--------|--------|
+| Time to first meaningful action | [N sec] | [N sec] |
+| Session length | [N min] | [N min] |
+| Critical fun blockers found | 0 | [N] |
+| Pipeline blockers found | 0 | [N] |
+| Architecture surprises | 0 | [N] |
+
+**Feel assessment:** [Specific — "combat feedback weak; no impact sound on hit" not "felt rough"]
+
+---
+
+## Recommendation: [PROCEED / PIVOT / KILL]
+
+[One paragraph with evidence — reference the validation question directly. Did a
+player experience the core fantasy within the target time, without developer guidance?
+Can the team build at this quality on the projected schedule?]
+
+---
+
+## If Proceeding
+
+**Production requirements** (what must change from slice to production):
+- [e.g., "Replace placeholder art with shipped assets"]
+- [e.g., "Combat system needs 2 more weapon types"]
+
+**Architecture adjustments needed:**
+- [ADR to update or create]
+
+**Sprint velocity estimate based on slice data:**
+- [e.g., "1 day per enemy type, 2 days per level section, 0.5 days per UI screen"]
+
+**Scope adjustments from original design:**
+- [What the slice revealed about the true production scope]
+
+**Performance targets:** [Confirmed / Revised — list changes if revised]
+
+**Playtest note:** Run `/playtest-report` to structure additional session data
+before running `/gate-check pre-production`.
+
+**Next steps:**
+1. `/gate-check pre-production` — formally advance to Production
+2. `/create-epics layer:foundation` — plan Foundation layer epics
+3. `/create-epics layer:core` — plan Core layer epics
+4. `/sprint-plan` — use velocity data from this report in the estimate
+
+---
+
+## If Pivoting
+
+[Which GDDs need revision and why — be specific about the failure mode observed.]
+
+**Systems requiring GDD revision:** [List]
+**Architecture decisions to revisit:** [List — use `/architecture-decision` to update]
+**Core loop change needed:** [What specifically to change]
+
+**Next steps:**
+1. `/design-system [mechanic]` — revise affected GDDs
+2. `/architecture-decision [decision]` — address architecture issues
+3. `/vertical-slice` — re-validate after revisions
+
+---
+
+## If Killing
+
+[Why the full game loop does not work at this quality level. What specifically
+prevented the player from experiencing the core fantasy. What to do instead.]
+
+**Next step:** `/brainstorm` to explore a new direction, or `/prototype [new-concept]`
+to test a different concept cheaply before investing in another vertical slice.
+
+---
+
+## Lessons Learned
+
+- **What assumptions were broken by building to near-production quality?**
+  [...]
+
+- **What surprised us about the pipeline or architecture?**
+  [...]
+
+- **What would we change about the slice scope if we ran this again?**
+  [...]
+
+---
+
+> *Vertical slice code location: `prototypes/[concept-name]-vertical-slice/`*
+> *This code is reference material only. Production implementation is written from scratch.*
+> *Never import or refactor this code into production.*