AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Ag 2 Corrigir

skill-andregusman-raiz-a-gusman-claude-ag-2-corrigir · by andregusman-raiz

Maquina autonoma de correcao. Bugs, erros TypeScript, tech debt — auto-detecta modo, diagnostica, corrige, verifica em loop convergente. Produz PR com fix verificado.

No reviews yet
0 installs
21 views
0.0% view→install

Install

$ agentstack add skill-andregusman-raiz-a-gusman-claude-ag-2-corrigir

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-andregusman-raiz-a-gusman-claude-ag-2-corrigir)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
1mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Ag 2 Corrigir? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

CORRIGIR — Maquina Autonoma de Correcao

Invocacao

/corrigir login nao funciona apos Clerk update       # Bug unico
/corrigir tipos                                       # Sweep TypeScript
/corrigir lista: [bug1, bug2, bug3]                  # Batch
/corrigir debt modulo financeiro                      # Tech debt
/corrigir --triage-only erros reportados pelo QA      # So diagnosticar
/corrigir --resume                                    # Retomar

O que faz

Correcao completa AUTONOMA em 4 fases:

ASSESS → DIAGNOSE → FIX → VERIFY → (loop ate green) → SHIP
                     ↑       │
                     └───────┘  (convergencia: max 3 cycles — Definition of Done CLAUDE.md)

Emissao de Phase Tags (observabilidade)

Emitir linha de status a cada transicao de fase:

[ASSESS ✓] modo=bug ciclos_max=3
[DIAGNOSE ✓] causa_raiz="null ref em adapter" confianca=alta hipoteses=3
[FIX →] aplicando fix em 2 arquivos...
[VERIFY ✓] typecheck=0 lint=0 tests=8/8 ciclo=1/3
[SHIP ✓] branch=fix/X PR=#43

Se VERIFY falha: [VERIFY ✗] ciclo=2/3 erros=3 → voltando para FIX

  1. ASSESS: Auto-detecta modo (bug/tipos/batch/debt/triage), estima volume
  2. DIAGNOSE: Causa raiz, categoriza, prioriza (ag-depurar-erro se obscuro). Listar 3+ hipoteses concorrentes (Deep Reasoning Directive).
  3. FIX: Corrige (ag-corrigir-bugs/B-53 conforme modo). Loop convergente.
  4. VERIFY: Typecheck + lint + testes. Se red → volta para FIX.
  5. SHIP: PR com diagnostico e evidencia.

ReasoningBank — Fix Strategy Persistence

Ao encerrar fix bem-sucedido (VERIFY verde), extrair e persistir o pattern:

# Append em meridian-kb/fix-strategies.json (criar se nao existe)
FIX_ENTRY=$(python3 -c "
import json, sys, datetime
entry = {
  'ts': '$(date -u +%Y-%m-%dT%H:%M:%SZ)',
  'sintoma': 'SINTOMA_AQUI',
  'causa_raiz': 'CAUSA_AQUI',
  'fix_aplicado': 'FIX_AQUI',
  'arquivos': [],
  'modo': 'MODO_AQUI',
  'ciclos': 1
}
print(json.dumps(entry))
")
mkdir -p meridian-kb
STRATEGIES_FILE="meridian-kb/fix-strategies.json"
if [ -f "\$STRATEGIES_FILE" ]; then
  python3 -c "
import json
with open('\$STRATEGIES_FILE') as f:
  data = json.load(f)
data['strategies'].append(\$FIX_ENTRY)
with open('\$STRATEGIES_FILE', 'w') as f:
  json.dump(data, f, indent=2)
"
else
  echo '{ \"strategies\": [\$FIX_ENTRY] }' > "\$STRATEGIES_FILE"
fi

ANTES de diagnosticar: Buscar fix similar em meridian-kb/fix-strategies.json por sintoma/causa. Se match encontrado, usar como hipotese inicial (confianca elevada).

Modos (auto-detectados)

| Modo | Sinais | Agents internos | |------|--------|-----------------| | bug | 1 bug claro/obscuro | ag-depurar-erro (debug) + ag-corrigir-bugs --fix | | tipos | "typecheck", "TS errors" | ag-corrigir-tipos (--fix ou --sweep) | | batch | lista de bugs, "corrigir todos" | ag-corrigir-bugs --batch ou --parallel | | debt | "tech debt", "cleanup" | fix direto em batches de 5 | | triage | "diagnosticar", desconhecido | ag-corrigir-bugs --triage (read-only) |

Propriedades MERIDIAN

  • Autonomo: diagnostica e corrige sem perguntar
  • Convergente: FIX ↔ VERIFY loop ate green (max 3 cycles). VERIFY OBRIGATORIO roda typecheck + lint + test (Definition of Done CLAUDE.md). Apos 3 ciclos red, parar e reportar.
  • State persistente: corrigir-state.json — resume de onde parou
  • Self-healing: regressao → revert + alternativa
  • Artifacts: PR com diagnostico, errors-log.md atualizado

Output

CORRIGIR COMPLETO
  Modo: [bug/tipos/batch/debt]
  Branch: [fix/...]
  PR: [url]
  Corrigidos: [X/Y]
  Ciclos: [N]
  Testes: [status]

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.