# Skill Improve > Mejora un skill con un ciclo de prueba-corrección-reprueba: ejecuta chequeos estáticos, propone fixes, reescribe el skill, vuelve a probarlo y conserva o revierte según el cambio de puntuación. Fuente: https://skillsagentes.com/skills/donchitos/claude-code-game-studios/skill-improve Markdown: https://skillsagentes.com/skills/donchitos/claude-code-game-studios/skill-improve.md Repositorio: https://github.com/Donchitos/Claude-Code-Game-Studios Autor: Donchitos Licencia: MIT Actualizado: hace 3 meses Coste de contexto: 41 tok instalada, 1.2k tok al activarse, 1.2k tok con todos los archivos del bundle Bundle: 1 archivo, 5 KB Permisos que pide: read, glob, grep, write, bash ## Instalación Un skill son archivos markdown: los mismos archivos valen para cualquier agente y lo único que cambia es el directorio de destino, es decir la bandera `--agent`. Añade `-g` para instalarlo en todos los proyectos de la máquina. ```bash # Claude Code npx -y skills add Donchitos/Claude-Code-Game-Studios --skill skill-improve --agent claude-code # Cursor npx -y skills add Donchitos/Claude-Code-Game-Studios --skill skill-improve --agent cursor # Codex npx -y skills add Donchitos/Claude-Code-Game-Studios --skill skill-improve --agent codex # Gemini CLI npx -y skills add Donchitos/Claude-Code-Game-Studios --skill skill-improve --agent gemini # Windsurf npx -y skills add Donchitos/Claude-Code-Game-Studios --skill skill-improve --agent windsurf # Cline npx -y skills add Donchitos/Claude-Code-Game-Studios --skill skill-improve --agent cline ``` ## Qué hace - Ejecuta /skill-test static y category como línea base para un skill dado - Diagnostica cada fallo o warning identificando la brecha exacta en el texto del skill - Propone un fix redactado con bloques antes/después y pide permiso para escribir - Reescribe SKILL.md, vuelve a testear y compara puntuaciones antes/después - Mantiene el cambio si mejora, o revierte con git checkout si no mejora o empeora ## Cuándo usarla - Quieres mejorar un skill específico que ya falla checks estáticos o de categoría - Necesitas un ciclo test-fix-retest controlado antes de aceptar cambios en un skill ## Cuándo no - El skill ya pasa todos los checks estáticos y de categoría con 0 fallos y 0 warnings ## Qué la activa - "/skill-improve tech-debt" - "Mejora el skill skill-improve usando el ciclo test-fix-retest" - "Corrige los fallos del Check 4 y Check 5 en este skill" ## Antes de instalar - Requiere que exista .claude/skills/[name]/SKILL.md y acceso a /skill-test y CCGS Skill Testing Framework/catalog.yaml. - runs shell commands - writes to your files ## Archivos - SKILL.md — 5 KB ## SKILL.md Reproducido tal cual desde Donchitos/Claude-Code-Game-Studios bajo MIT. Esta sección es el documento original y está en inglés. # Skill Improve Runs an improvement loop on a single skill: test → fix → retest → keep or revert. --- ## Phase 1: Parse Argument Read the skill name from the first argument. If missing, output usage and stop: ``` Usage: /skill-improve [skill-name] Example: /skill-improve tech-debt ``` Verify `.claude/skills/[name]/SKILL.md` exists. If not, stop with: "Skill '[name]' not found." --- ## Phase 2: Baseline Test Run `/skill-test static [name]` and record the baseline score: - Count of FAILs - Count of WARNs - Which specific checks failed (Check 1–7) Display to the user: ``` Static baseline: [N] failures, [M] warnings Failing: Check 4 (no ask-before-write), Check 5 (no handoff) ``` If baseline is 0 FAILs and 0 WARNs, note it and proceed to Phase 2b. ### Phase 2b: Category Baseline Look up the skill's `category:` field in `CCGS Skill Testing Framework/catalog.yaml`. If no `category:` field is found, display: "Category: not yet assigned — skipping category checks." and skip to Phase 3. If category is found, run `/skill-test category [name]` and record the category baseline: - Count of FAILs - Count of WARNs - Which specific category rubric metrics failed Display to the user: ``` Category baseline: [N] failures, [M] warnings ([category] rubric) ``` If BOTH static and category baselines are 0 FAILs and 0 WARNs, stop: "This skill already passes all static and category checks. No improvements needed." --- ## Phase 3: Diagnose Read the full skill file at `.claude/skills/[name]/SKILL.md`. For each failing or warning **static** check, identify the exact gap: - **Check 1 fail** → which frontmatter field is missing - **Check 2 fail** → how many phases found vs. minimum required - **Check 3 fail** → no verdict keywords anywhere in the skill body - **Check 4 fail** → Write or Edit in allowed-tools but no ask-before-write language - **Check 5 warn** → no follow-up or next-step section at the end - **Check 6 warn** → `context: fork` set but fewer than 5 phases found - **Check 7 warn** → argument-hint is empty or doesn't match documented modes For each failing or warning **category** check (if category was assigned in Phase 2b), identify the exact gap in the skill's text. For example: - If G2 fails (gate mode, full directors not spawned): skill body never references all 4 PHASE-GATE director prompts - If A2 fails (authoring, no per-section May-I-write): skill asks once at the end, not before each section write - If T3 fails (team, BLOCKED not surfaced): skill doesn't halt dependent work on blocked agent Show the full combined diagnosis to the user before proposing any changes. --- ## Phase 4: Propose Fix Write a targeted fix for each failure and warning. Show the proposed changes as clearly marked before/after blocks. Only change what is failing — do not rewrite sections that are passing. Ask: "May I write this improved version to `.claude/skills/[name]/SKILL.md`?" If the user says no, stop here. --- ## Phase 5: Write and Retest Record the current content of the skill file (for revert if needed). Write the improved skill to `.claude/skills/[name]/SKILL.md`. Re-run `/skill-test static [name]` and record the new static score. If a category was assigned, also re-run `/skill-test category [name]` and record the new category score. Display the comparison: ``` Static: Before [N] failures, [M] warnings → After [N'] failures, [M'] warnings Category: Before [N] failures, [M] warnings → After [N'] failures, [M'] warnings (if applicable) Combined change: improved / no change / worse ``` --- ## Phase 6: Verdict Count the combined failure total: static FAILs + category FAILs + static WARNs + category WARNs. **If combined score improved (combined failure count is lower than baseline):** Report: "Score improved. Changes kept." Show a summary of what was fixed in each dimension. **If combined score is the same or worse:** Report: "Combined score did not improve." Show what changed and why it may not have helped. Ask: "May I revert `.claude/skills/[name]/SKILL.md` using git checkout?" If yes: run `git checkout -- .claude/skills/[name]/SKILL.md` --- ## Phase 7: Next Steps - Run `/skill-test static all` to find the next skill with failures. - Run `/skill-improve [next-name]` to continue the loop on another skill. - Run `/skill-test audit` to see overall coverage progress. ## Dónde encaja - Categoría: [Herramientas para desarrolladores](https://skillsagentes.com/categorias/herramientas-desarrollo.md) — Skills que cambian cómo tu agente escribe, revisa y despliega código. - Creador: [Donchitos](https://skillsagentes.com/creators/donchitos.md) — 73 skills en el directorio - [Todas las skills](https://skillsagentes.com/skills.md) - [Ranking de instalaciones](https://skillsagentes.com/ranking.md) ## Otras skills del mismo repositorio - [Team Qa](https://skillsagentes.com/skills/donchitos/claude-code-game-studios/team-qa.md): Orquesta al equipo de QA (qa-lead y qa-tester) para producir un paquete completo de QA: plan de pruebas, smoke check, casos de prueba, ejecución manual y reporte de sign-off. - [Consistency Check](https://skillsagentes.com/skills/donchitos/claude-code-game-studios/consistency-check.md): Compara todos los GDDs contra el registro de entidades para detectar inconsistencias entre documentos: mismo stat, ítem o fórmula con valores distintos, usando un enfoque grep-first. - [Create Architecture](https://skillsagentes.com/skills/donchitos/claude-code-game-studios/create-architecture.md): Redacción guiada, sección por sección, del documento de arquitectura maestro del juego, consciente de la versión del motor y de sus posibles brechas de conocimiento. - [Day One Patch](https://skillsagentes.com/skills/donchitos/claude-code-game-studios/day-one-patch.md): Prepara un patch day-one para el lanzamiento de un juego: define alcance, prioriza, implementa y valida con un QA gate ligero, como un mini-sprint con plan de rollback. - [Hotfix](https://skillsagentes.com/skills/donchitos/claude-code-game-studios/hotfix.md): Flujo de arreglo urgente que se salta el proceso normal de sprint pero deja rastro de auditoría completo: crea rama hotfix, registra aprobaciones y asegura el backport correcto. --- Skills Agentes · [Índice de páginas en markdown](https://skillsagentes.com/sitemap.md) · [Inicio](https://skillsagentes.com/index.md)