* 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>
3.7 KiB
Contributing to Claude Code Game Studios
CCGS is a coordination framework for indie game development using Claude Code. Contributions are welcome — bug fixes, new skills that fill a real gap, agent improvements, and hook fixes. PRs that don't fit the framework's direction will be closed without lengthy explanation.
What Makes a Good PR
- Bug fixes — something is broken, here's the fix
- New skills that address a workflow gap not already covered
- Improvements to existing agents, skills, or hooks
- Documentation corrections — wrong info, broken references, outdated steps
Feature requests submitted as PRs will be closed. Open an issue instead.
What this repo isn't: CCGS is the system that helps you build games, not a place to store the games you build with it. GDDs, ADRs, PRDs, game concepts, level designs, narrative docs, or any other output generated by CCGS for your own project won't be merged here — keep those in your own repo.
The Non-Negotiable Technical Rules
These are the things that will get your PR rejected if you miss them.
Skill files
- Skills live in
.claude/skills/<name>/SKILL.md— the subdirectory format is required. Flat.mdfiles are silently ignored by Claude Code. - SKILL.md must include YAML frontmatter:
name,description,argument-hint,allowed-tools, andmodel - Model tier:
haikufor read-only status checks,opusfor multi-document synthesis and phase gates,sonnetfor everything else
Hooks
- Use
grep -E— nevergrep -P(Perl regex breaks on Windows Git Bash) - Include fallbacks for systems without
jqorpythoninstalled - Hooks run on every session start — they must exit quickly and gracefully
(
exit 0) when not applicable
Agents
- New agents must include a Collaboration Protocol section that describes how the agent asks questions and defers decisions to the user
- Agents must not modify files outside their documented domain without explicit user delegation
Reference docs
- If your PR adds or changes a skill, agent, or hook, update the matching reference doc (agent-roster, skills-reference, hooks-reference, or rules-reference). PRs that add things without updating the index will be sent back.
The Collaborative Principle
CCGS is not an autonomous system. Every workflow follows: Question → Options → Decision → Draft → Approval → Write
Skills and agents must ask before acting. Nothing writes to files without explicit user confirmation. If your contribution has an agent making decisions or writing files unilaterally, it won't be merged.
Testing Your Changes
Run it in a Claude Code session and confirm it works end-to-end. For skills, invoke the skill and verify the output matches what the skill claims to do. For hooks, trigger the relevant event and confirm the hook fires correctly and exits cleanly.
Include a brief note in your PR description describing what you tested and what the output looked like.
Commit Format
Use Conventional Commits:
feat: add /retrospective skill for end-of-sprint reviews
fix: correct grep -P usage in session-start hook
docs: update skills-reference with new /qa-plan entry
Types: feat, fix, docs, chore, refactor, test
PR Process
- Your PR will be auto-assigned to the maintainer via CODEOWNERS
- Reviews happen when they happen — this is a solo-maintained project
- If your PR sits open without feedback for a few weeks, a nudge comment is fine
- Merged contributors are credited in release notes
Platform Compatibility
CCGS must work on Windows (Git Bash), macOS, and Linux. If your hook or script uses anything platform-specific, it will be rejected. When in doubt, test on Windows.