Brownfield audit — do existing artifacts actually work? Numbered migration plan. Unlike /project-stage-detect, checks compliance not existence.
Idioma do texto original: inglês
Carregando o README do repositório…
Mostrando 40 de 74 skills coletadas.
Brownfield audit — do existing artifacts actually work? Numbered migration plan. Unlike /project-stage-detect, checks compliance not existence.
Idioma do texto original: inglês
Create an ADR documenting a technical decision: context, alternatives considered, consequences.
Idioma do texto original: inglês
Traceability matrix mapping GDD requirements to ADRs. Finds gaps, cross-ADR conflicts, engine compatibility. PASS/CONCERNS/NOT ASSESSED/FAIL.
Idioma do texto original: inglês
Author the Art Bible — visual identity gating asset production. Run before /map-systems.
Idioma do texto original: inglês
Audit assets against naming conventions, file size budgets, format standards. Finds orphaned assets, missing references.
Idioma do texto original: inglês
Per-asset visual specs plus AI generation prompts from GDDs and character profiles. After the art bible.
Idioma do texto original: inglês
Find balance outliers, broken progressions, degenerate strategies, economy imbalances in formulas and data. 'Check game balance'.
Idioma do texto original: inglês
Guided concept ideation using professional studio techniques, player psychology, creative exploration.
Idioma do texto original: inglês
Structured bug report from a description, or analyze code for potential bugs. Reproduction steps, severity.
Idioma do texto original: inglês
Re-evaluate open bugs — priority vs severity, assign to sprints, surface systemic trends. Run when the count grows.
Idioma do texto original: inglês
Auto-generate a changelog from git commits and sprint data. Internal and player-facing versions.
Idioma do texto original: inglês
Architectural code review — coding standards, SOLID, testability, performance concerns.
Idioma do texto original: inglês
Scan GDDs against the entity registry for cross-document conflicts. Grep-first approach targets conflicting sections, different stats.
Idioma do texto original: inglês
Audit GDD content counts against what's implemented — planned vs built.
Idioma do texto original: inglês
Author the architecture blueprint before code is written. Validates decisions against the pinned engine, flags knowledge gaps.
Idioma do texto original: inglês
Break one epic into implementable stories embedding TR-ID, ADR guidance, acceptance criteria. Reads the control manifest. After /create-epics.
Idioma do texto original: inglês
Day-one launch patch — focused fix for known issues found after gold master. Mini-sprint with QA gate and rollback.
Idioma do texto original: inglês
Reviews one design document for completeness, internal consistency, implementability, and design standards. Before handing to programmers.
Idioma do texto original: inglês
Section-by-section GDD authoring for one system — walks through each required section, cross-references dependencies.
Idioma do texto original: inglês
Implement a story: ADR guidelines, right programmer agent, code plus test. Then /story-done (/story-readiness before, /code-review after, at standard/full).
Idioma do texto original: inglês
Estimate task effort from complexity, dependencies, velocity, risk. Structured estimate with confidence levels.
Idioma do texto original: inglês
Ready to advance between development phases? PASS/CONCERNS/NOT ASSESSED/FAIL with blockers and required artifacts. 'Can we move to production?'
Idioma do texto original: inglês
Emergency fix bypassing normal sprint process — hotfix branch, approvals tracked, backport verified, full audit trail.
Idioma do texto original: inglês
Launch readiness across every department: code, content, store, marketing, community, infrastructure, legal, go/no-go sign-offs.
Idioma do texto original: inglês
Decompose a concept into individual systems, map dependencies, prioritize design order, create the systems index.
Idioma do texto original: inglês
Milestone progress review — completeness, quality metrics, risk, go/no-go recommendation. At checkpoints or before a deadline.
Idioma do texto original: inglês
Onboarding doc for a new contributor or agent — project state, conventions, priorities relevant to the specified role.
Idioma do texto original: inglês
Player-facing patch notes from git history and changelogs. Translates developer language into player communication.
Idioma do texto original: inglês
Performance profiling — find bottlenecks, measure against budgets, produce ranked optimization recommendations.
Idioma do texto original: inglês
Structured playtest report template, or turn existing playtest notes into structured feedback.
Idioma do texto original: inglês
Concept prototype before GDDs — throwaway HTML, Engine or Paper build, PROCEED/PIVOT/KILL/NOT ASSESSED. After /brainstorm and /setup-engine.
Idioma do texto original: inglês
Map test coverage to GDD critical paths, find fixed bugs lacking regression tests, flag drift from new features.
Idioma do texto original: inglês
Pre-release checklist — build verification, certification requirements, store metadata, launch readiness.
Idioma do texto original: inglês
Sprint or milestone retrospective from completed work, velocity, blockers. Actionable insights for the next iteration.
Idioma do texto original: inglês
Holistic cross-GDD review — contradictions between systems, dominant strategies, economic imbalance, cognitive overload, pillar drift.
Idioma do texto original: inglês
Scope creep check — current scope versus the original plan. Flags additions, quantifies bloat, recommends cuts. 'Any scope creep?'
Idioma do texto original: inglês
View or change project config — effective merged values, or set locally in project.local.yaml.
Idioma do texto original: inglês
Configure engine and version. Pins it in CLAUDE.md; WebSearch fills reference docs when the version is beyond LLM training data.
Idioma do texto original: inglês
Improve a skill via a test-fix-retest loop — static checks, targeted fixes, keep or revert on score change.
Idioma do texto original: inglês
Validate skill files for structural compliance and behavioral correctness. Four modes: static linter, spec, category rubric, audit.
Idioma do texto original: inglês
Copie este prompt para o assistente de IA que você usa.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/Donchitos/Claude-Code-Game-Studios.Não foi possível carregar o README. Você ainda pode explorar os Skills do repositório abaixo.