Miguelecf/elgordo-ia

Un agente piensa, otro construye y otro intenta romper lo construido. Así, la IA no reemplaza el proceso de ingeniería: lo estructura, lo acelera y lo vuelve más verificable.

Qu'est-ce que elgordo-ia ?

elgordo-ia is a Claude Code agent skill that un agente piensa, otro construye y otro intenta romper lo construido. Así, la IA no reemplaza el proceso de ingeniería: lo estructura, lo acelera y lo vuelve más verificable.

Compatible avecClaude Code~Codex CLI~Cursor
npx skills add Miguelecf/elgordo-ia

Installed? Explore more Recherche et analyse de données skills: obra/superpowers, affaan-m/quarkus-verification, affaan-m/uspto-database · View all 6 →

Demander à votre IA préférée

Ouvre une nouvelle conversation avec cette compétence d'agent déjà préchargée.

Documentation

ElGordo Handoff

Conductor → Role Agent

Every delegation includes:

  1. phase — current value from the private runtime status check.
  2. change — slug and title.
  3. artifacts — exact paths: intent.md, the active plans/NNNN.md, execution.md or qa.md as relevant, and openspec/changes/<slug>/ when present.
  4. skills — exact SKILL.md paths selected from .atl/skill-registry.md.
  5. scope — the single task or work unit in scope.
  6. constraints — human decisions, constitution rules, and explicit non-goals.

Role Agent → Conductor

Every return includes:

  1. status: done | blocked | needs_human.
  2. artifacts_written — exact paths.
  3. evidence — commands run and results, or answers recorded.
  4. open_questions — unresolved decisions.
  5. recommended_next — next step and which role owns it.

Hard Rules

  • needs_human halts autopilot; the conductor relays it to the questioner.
  • Paths are exact and verified to exist; no descriptions in place of paths.
  • Nothing outside the declared scope is produced.

Skills associés