Skills by donchitos

• A
  adoptDonchitos/Claude-Code-Game-Studios · 25k

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

• A
  architecture-decisionDonchitos/Claude-Code-Game-Studios · 25k

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

• A
  architecture-reviewDonchitos/Claude-Code-Game-Studios · 25k

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

• A
  art-bibleDonchitos/Claude-Code-Game-Studios · 25k

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

• A
  asset-auditDonchitos/Claude-Code-Game-Studios · 25k

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

• A
  asset-specDonchitos/Claude-Code-Game-Studios · 25k

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

• A
  balance-checkDonchitos/Claude-Code-Game-Studios · 25k

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

• A
  brainstormDonchitos/Claude-Code-Game-Studios · 25k

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

• A
  bug-reportDonchitos/Claude-Code-Game-Studios · 25k

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

• A
  bug-triageDonchitos/Claude-Code-Game-Studios · 25k

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

• A
  changelogDonchitos/Claude-Code-Game-Studios · 25k

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

• A
  code-reviewDonchitos/Claude-Code-Game-Studios · 25k

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

• A
  consistency-checkDonchitos/Claude-Code-Game-Studios · 25k

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

• A
  content-auditDonchitos/Claude-Code-Game-Studios · 25k

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

• A
  create-architectureDonchitos/Claude-Code-Game-Studios · 25k

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

• A
  create-control-manifestDonchitos/Claude-Code-Game-Studios · 25k

  Flat must-do/never-do rules sheet per system and layer, extracted from Accepted ADRs. ADRs explain why; this is actionable.

• A
  create-epicsDonchitos/Claude-Code-Game-Studios · 25k

  Turn GDDs plus architecture into epics — one per architectural module, with untraced requirements. Then /create-stories [epic-slug].

• A
  create-storiesDonchitos/Claude-Code-Game-Studios · 25k

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

• A
  day-one-patchDonchitos/Claude-Code-Game-Studios · 25k

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

• A
  design-reviewDonchitos/Claude-Code-Game-Studios · 25k

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

• A
  design-systemDonchitos/Claude-Code-Game-Studios · 25k

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

• A
  dev-storyDonchitos/Claude-Code-Game-Studios · 25k

  Implement a story: ADR guidelines, right programmer agent, code plus test. After /story-readiness, before /code-review and /story-done.

• A
  estimateDonchitos/Claude-Code-Game-Studios · 25k

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

• A
  gate-checkDonchitos/Claude-Code-Game-Studios · 25k

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

• A
  helpDonchitos/Claude-Code-Game-Studios · 25k

  What should I do next? Use when stuck or you don't know what to do.

• A
  hotfixDonchitos/Claude-Code-Game-Studios · 25k

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

• A
  launch-checklistDonchitos/Claude-Code-Game-Studios · 25k

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

• A
  localizeDonchitos/Claude-Code-Game-Studios · 25k

  Localization pipeline — find hardcoded strings, extract string tables, cultural review, VO, RTL, enforce string freeze.

• A
  map-systemsDonchitos/Claude-Code-Game-Studios · 25k

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

• A
  milestone-reviewDonchitos/Claude-Code-Game-Studios · 25k

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

• A
  onboardDonchitos/Claude-Code-Game-Studios · 25k

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

• A
  patch-notesDonchitos/Claude-Code-Game-Studios · 25k

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

• A
  perf-profileDonchitos/Claude-Code-Game-Studios · 25k

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

• A
  playtest-reportDonchitos/Claude-Code-Game-Studios · 25k

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

• A
  project-stage-detectDonchitos/Claude-Code-Game-Studios · 25k

  Analyze project state, detect stage, identify gaps, recommend next steps. 'Where are we in development?'

• A
  propagate-design-changeDonchitos/Claude-Code-Game-Studios · 25k

  A GDD changed — scan ADRs and the traceability index for now-stale architectural decisions. Impact report, guides resolution.

• A
  prototypeDonchitos/Claude-Code-Game-Studios · 25k

  Concept prototype before GDDs — throwaway HTML, Engine or Paper build, PROCEED/PIVOT/KILL. After /brainstorm and /setup-engine.

• A
  qa-planDonchitos/Claude-Code-Game-Studios · 25k

  QA test plan for a sprint — classifies stories by Logic/Integration/Visual/UI, covers automated tests, manual cases, smoke scope.

• A
  quick-designDonchitos/Claude-Code-Game-Studios · 25k

  Lightweight spec for small changes — tuning adjustments, minor mechanics. Embeds directly into stories; skips full GDD.

• A
  regression-suiteDonchitos/Claude-Code-Game-Studios · 25k

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

• A
  release-checklistDonchitos/Claude-Code-Game-Studios · 25k

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

• A
  retrospectiveDonchitos/Claude-Code-Game-Studios · 25k

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

• A
  reverse-documentDonchitos/Claude-Code-Game-Studios · 25k

  Generate missing design or architecture docs from existing implementation — works backwards from code and prototypes.

• A
  review-all-gddsDonchitos/Claude-Code-Game-Studios · 25k

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

• A
  scope-checkDonchitos/Claude-Code-Game-Studios · 25k

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

• A
  security-auditDonchitos/Claude-Code-Game-Studios · 25k

  Security audit — save tampering, cheat vectors, network exploits, data exposure, input validation. Before public or multiplayer release.

• A
  settingsDonchitos/Claude-Code-Game-Studios · 25k

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

• A
  setup-engineDonchitos/Claude-Code-Game-Studios · 25k

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

• A
  skill-improveDonchitos/Claude-Code-Game-Studios · 25k

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

• A
  skill-testDonchitos/Claude-Code-Game-Studios · 25k

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

• A
  smoke-checkDonchitos/Claude-Code-Game-Studios · 25k

  Critical-path smoke gate before QA hand-off — runs the automated suite. A failed check means the build is not QA-ready.

• A
  soak-testDonchitos/Claude-Code-Game-Studios · 25k

  Soak test protocol for extended play — what to observe and log for slow leaks, fatigue, late-appearing edge cases.

• A
  sprint-planDonchitos/Claude-Code-Game-Studios · 25k

  New or updated sprint plan from the current milestone, completed work, and available capacity.

• A
  sprint-statusDonchitos/Claude-Code-Game-Studios · 25k

  Fast, concise sprint snapshot — burndown and emerging risks for situational awareness. 'How is the sprint going?'

• A
  startDonchitos/Claude-Code-Game-Studios · 25k

  First-time onboarding — asks where you are, then guides you to the right workflow.

• A
  story-doneDonchitos/Claude-Code-Game-Studios · 25k

  End-of-story completion review — verifies each acceptance criterion, checks GDD/ADR deviations, prompts code review, updates status.

• A
  story-readinessDonchitos/Claude-Code-Game-Studios · 25k

  Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.

• A
  team-audioDonchitos/Claude-Code-Game-Studios · 25k

  Orchestrate the audio team — audio-director, sound-designer, technical-artist, gameplay-programmer — direction through implementation.

• A
  team-combatDonchitos/Claude-Code-Game-Studios · 25k

  Orchestrate the combat team — game-designer, gameplay-programmer, ai-programmer, technical-artist, sound-designer, qa-tester — design through implement and validate.

• A
  team-levelDonchitos/Claude-Code-Game-Studios · 25k

  Orchestrate the level team — level-designer, narrative-director, world-builder, art-director, systems-designer, qa-tester — for complete area creation.

• A
  team-live-opsDonchitos/Claude-Code-Game-Studios · 25k

  Orchestrate the live-ops team — live-ops-designer, economy-designer, analytics-engineer, community-manager, writer — for a season or live event.

• A
  team-narrativeDonchitos/Claude-Code-Game-Studios · 25k

  Orchestrate the narrative team — narrative-director, writer, world-builder, level-designer — for story, world lore, narrative-driven levels.

• A
  team-polishDonchitos/Claude-Code-Game-Studios · 25k

  Orchestrate the polish team — performance-analyst, technical-artist, sound-designer, qa-tester — to optimize and harden a feature or area.

• A
  team-qaDonchitos/Claude-Code-Game-Studios · 25k

  Orchestrate the QA team through a full testing cycle — qa-lead strategy and test plan, qa-tester case writing, execution, sign-off.

• A
  team-releaseDonchitos/Claude-Code-Game-Studios · 25k

  Orchestrate the release team — release-manager, qa-lead, devops-engineer, producer — to execute a release from candidate to deployment.

• A
  team-uiDonchitos/Claude-Code-Game-Studios · 25k

  Orchestrate the UI team through the UX pipeline — authoring, visual design, implementation, review, polish. Uses /ux-design, /ux-review, studio templates.

• A
  tech-debtDonchitos/Claude-Code-Game-Studios · 25k

  Track, categorize and prioritize technical debt across the codebase — scans for debt indicators, maintains a register.

• A
  test-evidence-reviewDonchitos/Claude-Code-Game-Studios · 25k

  Quality review of test files and evidence — goes beyond existence, evaluates assertion coverage. ADEQUATE/INCOMPLETE/MISSING/NOT ASSESSED per story.

• A
  test-flakinessDonchitos/Claude-Code-Game-Studios · 25k

  Find flaky tests from CI logs — aggregates pass rates, spots intermittent failures, recommends quarantine. After multiple runs.

• A
  test-helpersDonchitos/Claude-Code-Game-Studios · 25k

  Generate engine-specific test helper libraries — assertion utilities, factory functions, mocks in tests/helpers/. Reduces boilerplate.

• A
  test-setupDonchitos/Claude-Code-Game-Studios · 25k

  Scaffold the test framework and CI — tests/ directory, engine test runner, GitHub Actions workflow. Once, before the first sprint.

• C
  ux-designDonchitos/Claude-Code-Game-Studios · 25k

  Section-by-section UX spec authoring for a screen, flow or HUD. Reads the player journey to provide context; also project-wide accessibility.

• A
  ux-reviewDonchitos/Claude-Code-Game-Studios · 25k

  Validate a UX spec, HUD design or pattern library — accessibility, GDD alignment, readiness. APPROVED / NOT ASSESSED / NEEDS REVISION / MAJOR REVISION NEEDED.

• A
  vertical-sliceDonchitos/Claude-Code-Game-Studios · 25k

  Pre-production validation — end-to-end build to confirm the full loop is achievable before committing to Production. After GDDs, architecture, UX specs.

All agent skills →