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>
This commit is contained in:
Donchitos
2026-05-13 20:15:08 +10:00
committed by GitHub
parent 7ad8ab31c9
commit 984023ddac
97 changed files with 2883 additions and 710 deletions

View File

@@ -3,7 +3,7 @@
> **How to go from zero to a shipped game using the Agent Architecture.**
>
> This guide walks you through every phase of game development using the
> 48-agent system, 68 slash commands, and 12 automated hooks. It assumes you
> 49-agent system, 73 slash commands, and 12 automated hooks. It assumes you
> have Claude Code installed and are working from the project root.
>
> The pipeline has 7 phases. Each phase has a formal gate (`/gate-check`)
@@ -159,6 +159,11 @@ with defined pillars and a player journey. This is where you figure out
Player motiv. core loop, USP document
|
v
/prototype
(concept prototype — 1-3 days)
PROCEED ↓ PIVOT → /brainstorm
|
v (PROCEED)
/map-systems
|
v
@@ -558,28 +563,23 @@ Vertical Slice that proves the core loop is fun.
### Phase 4 Pipeline
```
/ux-design --> /prototype --> /create-epics --> /create-stories --> /sprint-plan
| | | | |
v v v v v
UX specs Throwaway Epic files in Story files in First sprint with
design/ux/ prototypes production/ production/ prioritized stories
in prototypes/ epics/*/EPIC.md epics/*/story-*.md production/sprints/
(one per module) (one per behaviour) sprint-*.md
| |
v v
/ux-review /story-readiness
(validates specs (validates each story
before epics) before pickup)
|
v
/dev-story
(implements the story,
routes to right agent)
|
v
Vertical Slice
(playable build,
3 unguided sessions)
/ux-design --> /vertical-slice --> /create-epics --> /create-stories --> /sprint-plan
| | | | |
v v v v v
UX specs Production-quality Epic files in Story files in First sprint with
design/ux/ end-to-end build production/ production/ prioritized stories
in prototypes/ epics/*/EPIC.md epics/*/story-*.md production/sprints/
PROCEED/PIVOT/KILL (one per module) (one per behaviour) sprint-*.md
| |
v v
/ux-review /story-readiness
(validates specs (validates each story
before epics) before pickup)
|
v
/dev-story
(implements the story,
routes to right agent)
```
### Step 4.1: UX Specs for Key Screens
@@ -624,25 +624,34 @@ etc.) with animation and sound standards.
Validates UX specs for GDD alignment and accessibility tier compliance.
Produces APPROVED / NEEDS REVISION / MAJOR REVISION NEEDED verdict.
### Step 4.2: Prototype Risky Mechanics
### Step 4.2: Build the Vertical Slice
Not everything needs a prototype. Prototype when:
- A mechanic is novel and you are not sure it is fun
- A technical approach is risky and you are not sure it is feasible
- Two design options both seem viable and you need to feel the difference
The vertical slice is the production-quality proof that you can build the full
game loop end-to-end before committing to full Production.
```
/prototype "grappling hook movement with momentum"
/vertical-slice
```
**What happens:** The skill collaborates with you to define a hypothesis,
success criteria, and minimal scope. The `prototyper` agent works in an
isolated git worktree (`isolation: worktree`) so throwaway code never
pollutes `src/`.
**What it proves:** Does a player, starting from nothing, experience the core
fantasy within a few minutes, without developer guidance?
**Key rule:** The `prototype-code` rule intentionally relaxes coding standards --
hardcoded values OK, no tests required -- but a README with hypothesis and
findings is mandatory.
**What it builds:** A near-production-quality playable build covering at least
one complete [start → challenge → resolution] cycle. Uses real architecture
layers, real naming conventions, no hardcoded values — but not final art or
audio. This is not a throwaway like the concept prototype; it demonstrates
production pipeline feasibility.
**Note on concept prototyping:** If you ran `/prototype` in Phase 1 (Concept),
you already validated the core idea is fun. The vertical slice now validates
you can build it properly. They answer different questions. If you skipped the
concept prototype, now is a reasonable time to run one first before investing
in the full slice.
**Verdict:** The vertical slice produces a PROCEED / PIVOT / KILL verdict.
- **PROCEED** → move to Step 4.3 (epics and stories)
- **PIVOT** → revise affected GDDs with `/design-system [mechanic]`, then re-run `/vertical-slice`
- **KILL** → return to `/brainstorm` with what you learned
### Step 4.3: Create Epics and Stories From Design Artifacts
@@ -668,7 +677,7 @@ automatically to the correct programmer agent.
### Step 4.4: Validate Stories Before Pickup
```
/story-readiness production/stories/combat-damage-calc.md
/story-readiness production/epics/combat/story-combat-damage-calc.md
```
Checks: Design completeness, Architecture coverage, Scope clarity, Definition
@@ -677,7 +686,7 @@ of Done. Verdict: READY / NEEDS WORK / BLOCKED.
### Step 4.5: Effort Estimation
```
/estimate production/stories/combat-damage-calc.md
/estimate production/epics/combat/story-combat-damage-calc.md
```
Provides effort estimates with risk assessment.
@@ -718,7 +727,7 @@ played the build unguided.
- At least 1 UX spec reviewed in `design/ux/`
- UX review completed (APPROVED or NEEDS REVISION with documented risks)
- At least 1 prototype with README
- Story files exist in `production/stories/`
- Story files exist in `production/epics/[epic-slug]/`
- At least 1 sprint plan exists
- At least 1 playtest report exists (Vertical Slice played in 3+ sessions)
@@ -762,7 +771,7 @@ The production phase centers on the **story lifecycle**:
**1. Story Readiness:** Before picking up a story, validate it:
```
/story-readiness production/stories/combat-damage-calc.md
/story-readiness production/epics/combat/story-combat-damage-calc.md
```
This checks design completeness, architecture coverage, ADR status (blocks
@@ -785,7 +794,7 @@ implement.
**3. Story Completion:** When a story is done:
```
/story-done production/stories/combat-damage-calc.md
/story-done production/epics/combat/story-combat-damage-calc.md
```
This runs an 8-phase completion review:
@@ -1213,9 +1222,12 @@ Tier 3 (Specialists): gameplay-programmer, engine-programmer,
live-ops-designer, prototyper, security-engineer,
community-manager, godot-specialist,
godot-gdscript-specialist, godot-shader-specialist,
unity-specialist, unity-csharp-specialist,
unreal-specialist, unreal-blueprint-specialist,
unreal-cpp-specialist
godot-csharp-specialist, godot-gdextension-specialist,
unity-specialist, unity-dots-specialist,
unity-shader-specialist, unity-addressables-specialist,
unity-ui-specialist, unreal-specialist,
ue-blueprint-specialist, ue-gas-specialist,
ue-replication-specialist, ue-umg-specialist
```
**Coordination rules:**
@@ -1410,9 +1422,9 @@ conflicts go to `producer`.
## Appendix B: Slash Command Quick-Reference
### All 66 Commands by Category
### All 73 Commands by Category
#### Onboarding and Navigation (5)
#### Onboarding and Navigation (6)
| Command | Purpose | Phase |
|---------|---------|-------|
@@ -1421,6 +1433,7 @@ conflicts go to `producer`.
| `/project-stage-detect` | Full project audit to determine current phase | Any |
| `/setup-engine` | Configure engine, pin version, set preferences | 1 |
| `/adopt` | Brownfield audit and migration plan | Any (existing projects) |
| `/skill-improve` | Improve a skill via test-fix-retest loop | Any |
#### Game Design (6)
@@ -1462,7 +1475,7 @@ conflicts go to `producer`.
| `/story-done` | 8-phase story completion review | 5 |
| `/estimate` | Effort estimation with risk assessment | 4-5 |
#### Reviews and Analysis (10)
#### Reviews and Analysis (13)
| Command | Purpose | Phase |
|---------|---------|-------|
@@ -1470,12 +1483,15 @@ conflicts go to `producer`.
| `/code-review` | Architectural code review | 5+ |
| `/balance-check` | Game balance formula analysis | 5-6 |
| `/asset-audit` | Asset naming, format, size verification | 6 |
| `/asset-spec` | Per-asset visual specs and AI generation prompts | 5-6 |
| `/content-audit` | GDD-specified content vs. implemented | 5 |
| `/consistency-check` | Cross-GDD entity and formula inconsistency scan | 2+ |
| `/scope-check` | Scope creep detection | 5 |
| `/perf-profile` | Performance profiling workflow | 6 |
| `/tech-debt` | Tech debt scanning and prioritization | 6 |
| `/gate-check` | Formal phase gate with PASS/CONCERNS/FAIL | All transitions |
| `/reverse-document` | Generate design docs from existing code | Any |
| `/security-audit` | Security vulnerability audit (save, network, input) | 6-7 |
#### QA and Testing (9)
@@ -1502,7 +1518,7 @@ conflicts go to `producer`.
| `/playtest-report` | Structured playtest session report | 4-6 |
| `/onboard` | Onboard a new team member | Any |
#### Release (5)
#### Release (6)
| Command | Purpose | Phase |
|---------|---------|-------|
@@ -1511,12 +1527,15 @@ conflicts go to `producer`.
| `/changelog` | Auto-generate internal changelog | 7 |
| `/patch-notes` | Player-facing patch notes | 7 |
| `/hotfix` | Emergency fix workflow | 7+ |
| `/day-one-patch` | Scoped patch for issues found after gold master | 7+ |
#### Creative (2)
#### Creative (4)
| Command | Purpose | Phase |
|---------|---------|-------|
| `/prototype` | Throwaway prototype in isolated worktree | 4 |
| `/prototype` | Concept prototype — validate core idea before GDDs | 1 |
| `/art-bible` | Guided Art Bible authoring — visual identity spec | 1-2 |
| `/vertical-slice` | Production-quality end-to-end build before Production | 4 |
| `/localize` | String extraction and validation | 6-7 |
#### Team Orchestration (9)