Donchitos/Claude-Code-Game-Studios

adopt

Brownfield audit — do existing artifacts actually work? Numbered migration plan. Unlike /project-stage-detect, checks compliance not existence.

Langue du texte source : anglais

architecture-decision

Create an ADR documenting a technical decision: context, alternatives considered, consequences.

Langue du texte source : anglais

architecture-review

Traceability matrix mapping GDD requirements to ADRs. Finds gaps, cross-ADR conflicts, engine compatibility. PASS/CONCERNS/NOT ASSESSED/FAIL.

Langue du texte source : anglais

art-bible

Author the Art Bible — visual identity gating asset production. Run before /map-systems.

Langue du texte source : anglais

asset-audit

Audit assets against naming conventions, file size budgets, format standards. Finds orphaned assets, missing references.

Langue du texte source : anglais

asset-spec

Per-asset visual specs plus AI generation prompts from GDDs and character profiles. After the art bible.

Langue du texte source : anglais

balance-check

Find balance outliers, broken progressions, degenerate strategies, economy imbalances in formulas and data. 'Check game balance'.

Langue du texte source : anglais

brainstorm

Guided concept ideation using professional studio techniques, player psychology, creative exploration.

Langue du texte source : anglais

bug-report

Structured bug report from a description, or analyze code for potential bugs. Reproduction steps, severity.

Langue du texte source : anglais

bug-triage

Re-evaluate open bugs — priority vs severity, assign to sprints, surface systemic trends. Run when the count grows.

Langue du texte source : anglais

changelog

Auto-generate a changelog from git commits and sprint data. Internal and player-facing versions.

Langue du texte source : anglais

code-review

Architectural code review — coding standards, SOLID, testability, performance concerns.

Langue du texte source : anglais

consistency-check

Scan GDDs against the entity registry for cross-document conflicts. Grep-first approach targets conflicting sections, different stats.

Langue du texte source : anglais

content-audit

Audit GDD content counts against what's implemented — planned vs built.

Langue du texte source : anglais

create-architecture

Author the architecture blueprint before code is written. Validates decisions against the pinned engine, flags knowledge gaps.

Langue du texte source : anglais

create-stories

Break one epic into implementable stories embedding TR-ID, ADR guidance, acceptance criteria. Reads the control manifest. After /create-epics.

Langue du texte source : anglais

day-one-patch

Day-one launch patch — focused fix for known issues found after gold master. Mini-sprint with QA gate and rollback.

Langue du texte source : anglais

design-review

Reviews one design document for completeness, internal consistency, implementability, and design standards. Before handing to programmers.

Langue du texte source : anglais

design-system

Section-by-section GDD authoring for one system — walks through each required section, cross-references dependencies.

Langue du texte source : anglais

dev-story

Implement a story: ADR guidelines, right programmer agent, code plus test. Then /story-done (/story-readiness before, /code-review after, at standard/full).

Langue du texte source : anglais

estimate

Estimate task effort from complexity, dependencies, velocity, risk. Structured estimate with confidence levels.

Langue du texte source : anglais

gate-check

Ready to advance between development phases? PASS/CONCERNS/NOT ASSESSED/FAIL with blockers and required artifacts. 'Can we move to production?'

Langue du texte source : anglais

hotfix

Emergency fix bypassing normal sprint process — hotfix branch, approvals tracked, backport verified, full audit trail.

Langue du texte source : anglais

launch-checklist

Launch readiness across every department: code, content, store, marketing, community, infrastructure, legal, go/no-go sign-offs.

Langue du texte source : anglais

map-systems

Decompose a concept into individual systems, map dependencies, prioritize design order, create the systems index.

Langue du texte source : anglais

milestone-review

Milestone progress review — completeness, quality metrics, risk, go/no-go recommendation. At checkpoints or before a deadline.

Langue du texte source : anglais

onboard

Onboarding doc for a new contributor or agent — project state, conventions, priorities relevant to the specified role.

Langue du texte source : anglais

patch-notes

Player-facing patch notes from git history and changelogs. Translates developer language into player communication.

Langue du texte source : anglais

perf-profile

Performance profiling — find bottlenecks, measure against budgets, produce ranked optimization recommendations.

Langue du texte source : anglais

playtest-report

Structured playtest report template, or turn existing playtest notes into structured feedback.

Langue du texte source : anglais

prototype

Concept prototype before GDDs — throwaway HTML, Engine or Paper build, PROCEED/PIVOT/KILL/NOT ASSESSED. After /brainstorm and /setup-engine.

Langue du texte source : anglais

regression-suite

Map test coverage to GDD critical paths, find fixed bugs lacking regression tests, flag drift from new features.

Langue du texte source : anglais

release-checklist

Pre-release checklist — build verification, certification requirements, store metadata, launch readiness.

Langue du texte source : anglais

retrospective

Sprint or milestone retrospective from completed work, velocity, blockers. Actionable insights for the next iteration.

Langue du texte source : anglais

review-all-gdds

Holistic cross-GDD review — contradictions between systems, dominant strategies, economic imbalance, cognitive overload, pillar drift.

Langue du texte source : anglais

scope-check

Scope creep check — current scope versus the original plan. Flags additions, quantifies bloat, recommends cuts. 'Any scope creep?'

Langue du texte source : anglais

settings

View or change project config — effective merged values, or set locally in project.local.yaml.

Langue du texte source : anglais

setup-engine

Configure engine and version. Pins it in CLAUDE.md; WebSearch fills reference docs when the version is beyond LLM training data.

Langue du texte source : anglais

skill-improve

Improve a skill via a test-fix-retest loop — static checks, targeted fixes, keep or revert on score change.

Langue du texte source : anglais

skill-test

Validate skill files for structural compliance and behavioral correctness. Four modes: static linter, spec, category rubric, audit.

Langue du texte source : anglais