freemcplab / Directorio / Playground / SkillForge

● Comunidad tripleyak ⚡ Instantáneo

SkillForge

Name: SkillForge (Claude Skill)
Author: tripleyak

Phase-based skill router + creator — triages each request, analyzes via 11 thinking lenses, generates XML specs, and runs multi-agent approval before shipping.

SkillForge is a meta-skill for Claude Code and Codex that decides whether to USE an existing skill, IMPROVE one, CREATE new, or COMPOSE from multiple. It runs 4 phases: triage → deep 11-lens analysis → XML spec → generation with multi-agent synthesis. v5.0 streamlined the SKILL.md to 313 lines with lazy-loaded references so the context stays lean.

▶ Ver demo 📦 Instalar 💡 Casos de uso

Por qué usarlo

Características clave

Phase 0 triage: USE_EXISTING / IMPROVE_EXISTING / CREATE_NEW / COMPOSE
Phase 1 deep analysis via 11 thinking lenses before any generation
Phase 2-3 XML-spec-driven generation with iteration
Phase 4 multi-agent synthesis panel must unanimously approve
Lean SKILL.md (313 lines) with lazy-loaded references

Demo en vivo

Cómo se ve en la práctica

skillforge-skill.replay ▶ listo

0/0

Instalación

Repositorio del autor · Documentación oficial de Skills de Claude

Casos de uso

Usos del mundo real: SkillForge

Find the right existing skill instead of reinventing one

👤 Anyone with a big skill library and no memory of what's installed ⏱ ~5 min beginner

Cuándo usarlo: You have a task and aren't sure if something already covers it.

Flujo

Describe the task

Use skillforge. I need to turn our docs site into a searchable knowledge base.✓ Copiado

→ Triage returns USE_EXISTING with a recommendation (e.g. skill-seekers)
Confirm and hand off

Good — run that skill.✓ Copiado

→ Routes to the recommended skill

Resultado: You use what's already there rather than writing a new skill.

Errores comunes

Triage is over-eager to create new — Explicitly ask 'prefer USE_EXISTING unless match score < 70%'

Combinar con: skill-seekers-skill

Create a new skill with engineered rigor

👤 Skill authors who want quality, not vibes ⏱ ~30 min intermediate

Cuándo usarlo: Triage returned CREATE_NEW and you want the full 4-phase generation.

Flujo

Approve triage

skillforge — CREATE_NEW for a skill that drafts ADRs from design discussions.✓ Copiado

→ Phase 1 analysis begins with 11 lenses
Review the spec

Show me the XML spec before generation.✓ Copiado

→ Structured spec you can critique
Run synthesis

Generate, then run the multi-agent panel.✓ Copiado

→ Panel verdict with unanimous approval or concrete objections

Resultado: A production-quality SKILL.md ready to install.

Errores comunes

Panel stuck in endless loop — Cap iterations — SkillForge supports an iteration limit flag

Combinar con: skill-seekers-skill

Combinaciones

Combínalo con otros MCPs para multiplicar por 10

skillforge-skill + skill-seekers-skill

Use SkillForge to decide, then Skill Seekers to actually ingest sources for CREATE_NEW

skillforge triage, then if CREATE_NEW, use skill-seekers to pull in the docs.✓ Copiado

skillforge-skill + filesystem

Skill output goes straight into ~/.claude/skills/

Write the generated SKILL.md and references to ~/.claude/skills/<name>/.✓ Copiado

Herramientas

Lo que expone este MCP

Herramienta	Entradas	Cuándo llamar
Phase 0 triage	task description + skill library	Start of every request
Phase 1 deep analysis (11 lenses)	task	After triage, before generation
Phase 2-3 XML spec + generation	analysis	CREATE_NEW or IMPROVE_EXISTING
Phase 4 multi-agent synthesis	draft	Final quality gate

Coste y límites

Lo que cuesta ejecutarlo

Cuota de API: None
Tokens por llamada: Full 4-phase generation is token-heavy (10-30k)
Monetario: Free — skill is local
Consejo: Use triage-only for simple routing; invoke full pipeline only for real skill authoring.

Seguridad

Permisos, secretos, alcance

Almacenamiento de credenciales: No credentials — skill is prompts

Salida de datos: None from the skill itself

Resolución de problemas

Errores comunes y soluciones

Triage picks wrong verdict

Provide the current skill library list so triage can match properly.

Multi-agent panel keeps rejecting

Check the objections — often a missing section in the spec. Fix once, re-run.

Generated skill feels generic

Give more source material in Phase 1; skill quality follows source quality.

Alternativas

SkillForge vs otros

Alternativa	Cuándo usarla	Contrapartida
skill-seekers-skill	You want document-ingest-first rather than analysis-first	Seekers is heavier on source processing; SkillForge is heavier on engineering rigor
Manual SKILL.md authoring	The skill is small and you have a clear spec	Fastest for trivial skills

Más

Recursos

📖 Lee el README oficial en GitHub

🐙 Ver issues abiertas

🔍 Ver todos los 400+ servidores MCP y Skills