Files
Claude-Code-Game-Studios/.claude/docs/workflow-catalog.yaml
Donchitos 4ca6500a21 Split /create-epics-stories into /create-epics + /create-stories; add /dev-story
- NEW /create-epics (agent: technical-director): architect-level epic scoping,
  one epic per architectural module. Does not create stories.
- NEW /create-stories (agent: lead-programmer): decomposes a single epic into
  story files with embedded TR-IDs, ADR guidance, and test evidence paths.
- NEW /dev-story: the missing implementation skill — reads a story, loads full
  context (TR registry, ADR, control manifest, engine prefs), routes to the
  correct programmer agent via Task, and drives implementation to completion
  including writing the test.
- DEPRECATED /create-epics-stories: added redirect notice; original content
  preserved for reference.
- Updated /gate-check: Pre-Prod→Production artifact check and follow-up actions
  now reference the two new skills.
- Updated workflow-catalog.yaml: replaced create-epics-stories step with two
  separate steps; implement step now references /dev-story with command field.

Story loop is now explicit:
  /story-readiness → /dev-story → /code-review → /story-done

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-16 14:57:39 +11:00

318 lines
11 KiB
YAML
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
# Workflow Catalog
# Used by /help to determine where a user is and what comes next.
#
# Artifact checks:
# glob: file glob pattern — complete if ≥1 file matches (or min_count)
# pattern: text pattern that must appear in the file (checked after glob)
# min_count: minimum matching files required (default: 1)
# note: human-readable fallback when completion can't be auto-detected
#
# required: true → blocks progression to next phase (shown as REQUIRED)
# required: false → optional enhancement (shown as OPTIONAL)
# repeatable: true → runs multiple times (one per system, story, etc.)
phases:
concept:
label: "Concept"
description: "Develop your game idea into a documented concept"
next_phase: systems-design
steps:
- id: brainstorm
name: "Brainstorm"
command: /brainstorm
required: false
description: "Explore the game concept using MDA, verb-first, and player psychology frameworks"
- id: engine-setup
name: "Engine Setup"
command: /setup-engine
required: true
artifact:
glob: ".claude/docs/technical-preferences.md"
pattern: "Engine: [^[]"
description: "Configure engine, pin version, set naming conventions and performance budgets"
- id: game-concept
name: "Game Concept Document"
command: /brainstorm
required: true
artifact:
glob: "design/gdd/game-concept.md"
description: "Formalize concept with pillars, MDA analysis, and scope tiers"
- id: design-review-concept
name: "Concept Review"
command: /design-review
required: false
description: "Validate the game concept (recommended before proceeding)"
- id: map-systems
name: "Systems Map"
command: /map-systems
required: true
artifact:
glob: "design/gdd/systems-index.md"
description: "Decompose concept into systems with dependency ordering and priority tiers"
systems-design:
label: "Systems Design"
description: "Author a GDD for each system in the systems index"
next_phase: technical-setup
steps:
- id: design-system
name: "System GDDs"
command: /design-system
required: true
repeatable: true
artifact:
note: "Check design/gdd/systems-index.md — each MVP system needs Status: Approved"
description: "Author per-system GDDs (guided, section-by-section). Run once per system."
- id: design-review
name: "Per-System Design Review"
command: /design-review
required: true
repeatable: true
description: "Validate each GDD (8 required sections, no MAJOR REVISION verdict). Run per system."
- id: review-all-gdds
name: "Cross-GDD Review"
command: /review-all-gdds
required: true
artifact:
glob: "design/gdd/gdd-cross-review-*.md"
description: "Holistic consistency check + design theory review across all GDDs simultaneously"
technical-setup:
label: "Technical Setup"
description: "Architecture decisions, UX foundations, engine validation"
next_phase: pre-production
steps:
- id: create-architecture
name: "Architecture Document"
command: /create-architecture
required: true
artifact:
glob: "docs/architecture/architecture.md"
description: "Author the master architecture document covering all systems"
- id: architecture-decision
name: "Architecture Decisions (ADRs)"
command: /architecture-decision
required: true
repeatable: true
artifact:
glob: "docs/architecture/adr-*.md"
min_count: 3
description: "Document key technical decisions as ADRs. Minimum 3 Foundation-layer ADRs required."
- id: architecture-review
name: "Architecture Review"
command: /architecture-review
required: true
artifact:
glob: "docs/architecture/architecture-review-*.md"
description: "Validate completeness, dependency ordering, engine compatibility"
- id: control-manifest
name: "Control Manifest"
command: /create-control-manifest
required: true
artifact:
glob: "docs/architecture/control-manifest.md"
description: "Flat programmer rules sheet generated from all Accepted ADRs"
- id: accessibility-doc
name: "Accessibility Requirements"
required: true
artifact:
glob: "design/accessibility-requirements.md"
description: "Commit accessibility tier (Basic/Standard/Comprehensive/Exemplary) and feature matrix"
- id: ux-design
name: "UX Specs (key screens)"
command: /ux-design
required: true
repeatable: true
artifact:
glob: "design/ux/*.md"
min_count: 1
description: "Author UX specs for main menu, core gameplay HUD, and pause screen"
- id: ux-review
name: "UX Review"
command: /ux-review
required: true
description: "Validate all key screen UX specs for accessibility and GDD alignment"
pre-production:
label: "Pre-Production"
description: "Prototype the core mechanic, define stories, validate fun"
next_phase: production
steps:
- id: prototype
name: "Prototype"
command: /prototype
required: true
artifact:
glob: "prototypes/*/README.md"
min_count: 1
description: "Build throwaway prototypes in isolated worktree to validate core mechanic"
- id: create-epics
name: "Create Epics"
command: /create-epics
required: true
repeatable: true
artifact:
glob: "production/epics/*/EPIC.md"
min_count: 1
description: "Translate GDDs + ADRs into epics — one per architectural module. Run per layer: /create-epics layer: foundation, then /create-epics layer: core"
- id: create-stories
name: "Create Stories"
command: /create-stories
required: true
repeatable: true
artifact:
glob: "production/epics/**/*.md"
min_count: 2
description: "Break each epic into implementable story files. Run per epic: /create-stories [epic-slug]"
- id: sprint-plan
name: "First Sprint Plan"
command: /sprint-plan
required: true
artifact:
glob: "production/sprints/sprint-*.md"
min_count: 1
description: "Plan the first sprint with prioritized stories from epics"
- id: vertical-slice
name: "Vertical Slice (playtested)"
required: true
artifact:
glob: "production/playtests/*.md"
min_count: 1
description: "Playable end-to-end core loop, playtested with ≥3 sessions. HARD GATE."
production:
label: "Production"
description: "Sprint-based feature development — pick, implement, close stories"
next_phase: polish
steps:
- id: sprint-plan
name: "Sprint Plan"
command: /sprint-plan
required: true
repeatable: true
artifact:
glob: "production/sprints/sprint-*.md"
description: "Plan the current sprint with prioritized, ready stories"
- id: story-readiness
name: "Story Readiness Check"
command: /story-readiness
required: false
description: "Validate a story is implementation-ready before a developer picks it up"
- id: implement
name: "Implement Stories"
command: /dev-story
required: true
repeatable: true
artifact:
note: "Check src/ for active code and production/epics/**/*.md for In Progress stories"
description: "Pick the next ready story and implement it with /dev-story [story-path]. Routes to the correct programmer agent. Then run /code-review and /story-done."
- id: story-done
name: "Story Done Review"
command: /story-done
required: true
repeatable: true
description: "Verify all acceptance criteria, check GDD/ADR deviations, close the story"
- id: scope-check
name: "Scope Check"
command: /scope-check
required: false
repeatable: true
artifact:
glob: "production/sprints/sprint-*.md"
note: "Run when stories are added mid-sprint, or before sprint retrospectives"
description: "Detect scope creep by comparing current sprint scope to original epic scope. Run (a) when stories are added mid-sprint, or (b) before sprint retrospectives."
- id: sprint-status
name: "Sprint Status"
command: /sprint-status
required: false
description: "Quick 30-line snapshot of sprint progress without a full report"
polish:
label: "Polish"
description: "Performance, balance, playtesting, bug fixing"
next_phase: release
steps:
- id: perf-profile
name: "Performance Profile"
command: /perf-profile
required: false
description: "Profile and optimize CPU/GPU/memory bottlenecks"
- id: balance-check
name: "Balance Check"
command: /balance-check
required: false
description: "Analyze game balance formulas and data for outliers and broken progressions"
- id: asset-audit
name: "Asset Audit"
command: /asset-audit
required: false
description: "Verify naming conventions, file format standards, and size budgets"
- id: playtest-polish
name: "Playtest Sessions (×3)"
command: /playtest-report
required: true
artifact:
glob: "production/playtests/*.md"
min_count: 3
description: "Cover: new player experience, mid-game systems, difficulty curve"
- id: team-polish
name: "Polish Team Pass"
command: /team-polish
required: true
description: "Coordinated polish pass across performance, audio, visual, and UX"
release:
label: "Release"
description: "Launch preparation, certification, and ship"
next_phase: null
steps:
- id: release-checklist
name: "Release Checklist"
command: /release-checklist
required: true
description: "Pre-release validation across all departments: code, content, store, legal"
- id: patch-notes
name: "Patch Notes"
command: /patch-notes
required: false
description: "Generate player-facing patch notes from git history and sprint data"
- id: changelog
name: "Changelog"
command: /changelog
required: false
description: "Auto-generate internal changelog from commits, sprints, and design docs"
- id: launch-checklist
name: "Launch Checklist"
command: /launch-checklist
required: true
description: "Final launch readiness — last gate before shipping to players"