Create a Korean patch for a retro game

SkillDev tools

Use for Korean (Hangul) fan translations of retro console or PC games, including ROM or disc analysis, text-engine reverse engineering, Hangul fonts and custom encodings, script extraction and reinsertion, code hooks, reproducible product builds, and emulator verification. Apply it to new investigations and follow-up work in existing Korean-patch projects. 레트로 게임 한글화·한글패치·한글 패치·ROM 번역의 신규 조사와 기존 프로젝트 후속 작업에 사용한다.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Create a Korean patch for a retro game skill

What this skill tells your AI

The instructions your AI receives, as published by mcpads/create-retro-game-kr-patch in skills/create-kr-patch/SKILL.md and read by ahel’s review.

Purpose

Base decisions on evidence from the target game. Keep the evidence and adopted results from the initial survey, fonts and encoding, PoC, extraction, translation, reinsertion, product builds, distributable patches, and runtime verification traceable through completion.

Choose tools, languages, libraries, and fonts based on the target project's existing structure and the current environment. Regardless of those choices, preserve the required capabilities and verification criteria. Look up basic specifications from current primary sources when one straightforward search can recover them.

Treat source-language frequencies and structures from other titles as hypotheses until the target revision confirms them.

Foundational principle

Treat each playthrough as the whole product. Successful paths do not offset a known in-scope defect that can block progress, corrupt text or intended meaning, mislead the player about a choice, break approved terminology or voice, or impair interaction. Fix it, present evidence and feasible options for an explicit human decision to narrow the scope or claim, or withhold the release. See references/strategy/build-and-verify.md §6 and references/strategy/translation-workflow.md §6.

Operating principles

  1. Let product closure define the work. Define the target by what must hold together across its declared scope and claims, not by the current artifact plus the next plausible edit. Credit a result only to the claim it strengthens. Keep the hardest unresolved completion condition—or the one most likely to force redesign—visible, and choose work from it. Among approaches with the same prerequisites and proof scope, prefer the lower total cost of obtaining evidence. See references/conventions/project-records.md §1 and references/strategy/build-and-verify.md §1·§6.
  2. Keep each evidence loop informative. Let unresolved uncertainty determine whether static inspection, runtime observation, or both can produce the next discriminating evidence. Keep the exact applicable artifact fixed while affected routes can still yield interpretable evidence; one defect does not require an immediate rebuild. Change the baseline when its question is answered or observation is blocked, contaminated, or unsafe. Conflicting evidence, repeated equivalent evidence, local passes that do not strengthen the cumulative claim, and accumulating exceptions signal reassessment. Restore the baseline, completion condition, and live and rejected explanations; search references/tips/README.md by observation before adding another local exception. Cases suggest hypotheses, not repairs. See references/conventions/project-records.md §2 and references/strategy/debugging.md §2·§3·§5·§6.
  3. Keep product priorities and decision authority separate from implementation. Current implementation establishes behavior and change cost, not product value. The agent establishes technical facts and feasible options; humans choose product direction, quality, scope, acceptable loss, support, and investment. At a meaningful point of convergence, present the current result and possible gains with their effort, risk, uncertainty, and claim impact. Bind the human choice to that evidence baseline; it is not technical completion or proof that improvement is exhausted. Routine implementation that preserves adopted intent remains the agent's responsibility. See references/conventions/project-records.md §1.1 and references/strategy/translation-workflow.md §4.1·§5.

Task-specific guidance

For an existing repository, reconstruct the current code, documents, artifacts, and verification state before choosing the guidance relevant to the next decision. Start with the initial survey when the game or its structure is not yet understood.

Decision areaDocumentUse it to determine
Initial surveyreferences/strategy/initial-survey.mdCompletion-critical conditions, actual dependencies, initial volume, unresolved populations, and revision-specific facts
Fonts and encodingreferences/strategy/font-strategy.mdCode-to-glyph mapping, total repertoire, active working set, representation, and runtime reachability
Name entry and user stringsreferences/strategy/name-entry.mdInput repertoire, editing state, committed records, glyph supply, redisplay consumers, and persistence
Text extractionreferences/strategy/text-extraction.mdPopulation and volume, consumer-defined boundaries and tokens, reversible artifacts, and round trips
PoCreferences/strategy/poc.mdWhether a PoC is needed and what a visibility, representative end-to-end, or conditional PoC must establish
Reinsertion and hooksreferences/strategy/reinsertion.mdBoundary policies, reference completeness, hooks, space, and consumer invariants
Translationreferences/strategy/translation-workflow.mdTranslation work and agent assignment, context, approved terminology and voice, protected information and consumer constraints, and high-impact semantic decisions
Build and verificationreferences/strategy/build-and-verify.mdReproducible artifacts, checks enforced by the product build, distribution boundaries, integrity and runtime verification, text and interaction QA, and release readiness
Debugging and issue handlingreferences/strategy/debugging.mdGameplay routes, target-state access, what state intervention can establish, causes, fixes, and regression evidence
Graphics textreferences/strategy/graphics-text.mdPixel-text population, protected visual assets, and consumer-path verification
Compressionreferences/strategy/compression.mdVerified transformation boundaries, consumer compatibility, and repacking verification
Runtime asset reachabilityreferences/strategy/runtime-assets.mdStorage, lookup, load or transform, residency, and consumption as one connected claim

Apply the relevant conventions when designing or validating artifacts, exchange data, or records. Keep an existing repository structure when it already preserves the same responsibilities and constraints.

ScopeDocumentUse it for
Project-wide implementationreferences/conventions/project-conventions.mdRepository vocabulary and ownership; tooling build, analysis, product build, test, artifact verification, and runtime verification boundaries; machine-code verification; round-trip equivalence and denominator; final-write verification; external-component reproducibility; and source assets
Translation artifactsreferences/conventions/translation-artifacts.mdSource preservation, control tokens, review states, and eligibility as product build inputs
Project recordsreferences/conventions/project-records.mdHuman strategic decisions, survey and PoC decisions, graphics-text catalog, HITL observations, QA evidence, and issue states
Analysis and product build datareferences/conventions/data-formats.mdCharacter maps, controls, pointers, translation links, reinsertion policies, and font-rendering profiles

Read a platform document only when a constraint involving hardware, the medium, address space, or rendering can change the current decision.

PlatformDocument
SNESreferences/platforms/snes.md
Mega Drivereferences/platforms/megadrive.md
Sega Saturnreferences/platforms/saturn.md
PlayStationreferences/platforms/ps1.md
Dreamcastreferences/platforms/dreamcast.md
PC Engine and CD-ROM²references/platforms/pce.md
PC-98references/platforms/pc98.md
Game Gearreferences/platforms/gg.md
Game Boy and Game Boy Colorreferences/platforms/gb.md
NES and Famicomreferences/platforms/nes.md
Nintendo DSreferences/platforms/nds.md

For an unlisted platform, establish only the constraints that can change the current decision.

Artifact requirements

Violating one of these requirements invalidates the affected release claim. A mechanically invalid input or artifact must also stop the product build unless the declared development/PoC input policy permits it. Record every exception and the resulting limit on the claim.

  • Never commit source ROM or disc images, or unauthorized third-party assets. Follow references/conventions/project-conventions.md §6.
  • Plan every final change from an immutable source and fail on overlapping writers, protected-range writes, or unexplained final differences. Follow references/conventions/project-conventions.md §5.2.
  • Never silently skip or substitute a character whose glyph or encoding is missing. An unmapped character fails the product build. A product build under the development/PoC input policy may proceed only under references/conventions/translation-artifacts.md §5 and cannot produce a release candidate.
  • A rule-based batch transformation that changes translated prose requires prior human approval of the rule, pre-transformation text, scope, and expected impact. Follow references/strategy/translation-workflow.md §5.2.

Signals

GitHub stars
81
Forks
21
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
create-kr-patch
Source
github.com/mcpads/create-retro-game-kr-patch