superpowers
claudecodexCore skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Branch-based game Korean-localization workflow for Codex and Claude Code: no-API built-in imagegen best-of-three selection, original-feel Korean image QA, platform-scoped smoke testing, official-distribution direct runtime QA, recoverable cleanup, and release. Complete NSW and Steam/PC adapters plus SFC/PS1/PS2 skeletons and Unity/VN/LucaSystem engine modules.
Plugin game-translate from marketplace game-translate-skills in Leuconoe/GameTranslateSkills. Commands read from the repo's manifest — 3 days ago.
game-translateOrchestrate a fail-closed Korean game-localization workflow across overall analysis, text analyze/translate/QA/review, conditional image analyze/translate/QA/review, integrated QA, and release. Review stages prepare emulator-ready handoffs by default and wait for user approval only when the project
gt-analyzeOverall analysis entry stage for game localization: extract game files, identify platform/engine/text/image/font formats and language slots, build source inventory, and fail closed on unverifiable extraction or coverage. Use when starting or resuming a game translation project or analyzing ROM/game
gt-image-analyzeImage branch analysis after overall and text handoff: inventory every text-bearing texture and lock its original typography, color, outline, material, lighting, spacing, atmosphere, edit regions, anchors, canvas, alpha, atlas, style, and image scope before translation. Use when starting or resuming
gt-image-qaRun technical and visual QA after image translation: validate no-API built-in imagegen multi-candidate provenance, source protection, original Korean visual feel, source-text removal, canvas, alpha, anchors, atlases, preserved pixels, hashes, and injection readiness. Use after gt-image-translate.
gt-image-reviewPrepare an image-review handoff after technical QA with complete before/after and multi-candidate comparisons, built-in imagegen provenance, source-text removal, original Korean visual feel, layout, alpha, atlas, and style evidence. Use after gt-image-qa and honor an explicit user-gate when configur
gt-image-translateTranslate text-bearing game textures, atlases, and raster labels through no-API built-in imagegen edits, multi-candidate selection, fail-closed provenance, source protection, and original typography, atmosphere, layout, alpha, material, and lighting preservation. Use after gt-image-analyze when game
gt-nsw-buildCreate or validate the one canonical NSW LayeredFS patch ZIP when the user asks for 빌드 생성, 패치 생성, an NSW build, or a Title-ID/romfs archive; reject alternate candidate, delta-applier, game-name, or update-Title-ID packages.
gt-project-cleanupArchive exact cleanup candidates for one game title project, fully re-review and report them, then move separately approved files only to the recoverable operating-system Trash. Use when cleaning a title's _work project after QA/release or when stale session and duplicate artifacts are consuming sto
gt-qaIntegrated game-translation QA after text and conditional image review-ready handoffs: verify font coverage, structure, build, session ownership, emulator/runtime behavior, and logs/screenshots with fail-closed bench-versus-runtime evidence. Use for final patch QA, emulator testing, emucap evidence,
gt-releaseRelease a QA-verified Korean game patch using the platform adapter's exact contract, deterministic hashes, runtime evidence, notes, and cleanup evidence; for NSW build or patch packaging, consume the canonical ZIP produced by gt-nsw-build.
gt-text-analyzeText branch analysis for game localization: inventory every text source, stable key, encoding, control token, language slot, and round-trip constraint before translation. Use when starting or resuming text analysis.
gt-text-qaText branch technical QA after Korean translation: validate manifest structure and round-trip safety, prove full Korean font glyph coverage and atlas coordinates/metrics, build an emulator-ready text candidate, and route to text review without waiting for user approval. Use after gt-text-translate o
gt-text-reviewText branch review handoff after technical QA: inspect the complete translated text sheet and emulator-ready candidate, record unresolved issues and optional user review materials, and continue automatically by default. Use after gt-text-qa when text review preparation, font/layout evidence, or an e
gt-text-translateText branch translation after text analysis: batch-translate extracted game text (JA/EN/ZH to Korean) with glossary accumulation, tone consistency, structure validation, explicit batch-policy checks, and fail-closed warnings. Use when translating game text, dialogue, or UI.
gt-workspace-cleanupArchive exact cleanup candidates from a game-translation workspace, fully re-review and report them, then move separately approved files only to the recoverable operating-system Trash. Use when reconciling title folders, unscoped root artifacts, stale sessions, or workspace storage growth.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Package any website or local web build into a lightweight desktop app with Pake CLI.
1 skill
Use Alibaba Open Code Review from local Codex.
2 skills
Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development
9 skills · 1 command · 8 agents
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.