Lewati ke konten
TakoAPI
Kembali ke skill

wreckit-ralph

oleh christiancattaneo

Web & Frontend Development
413Unduhan dilaporkan oleh clawskills.sh
0Tayangan
0 sukaMasuk untuk menyukai skill ini
—Belum ada penilaian
Penilaian Anda

Ringkasan

Bulletproof AI code verification.

Deskripsi

Apa yang Dilakukan Skill Ini

A multi-gate code verification agent that separates builder, tester, and breaker roles across independent parallel workers. Runs slop scans, type checks, mutation tests, and SAST analysis before aggregating results into a proof bundle with a Ship, Caution, or Blocked verdict. Supports TypeScript, Python, Rust, Go, Swift, Java, and Shell.

Splits verification into independent roles so the same AI context cannot confirm its own work, reducing silent failures from self-agreement.

Kapan Menggunakannya

  • Verifying AI-generated code before merging
  • Auditing a codebase for quality and coverage gaps
  • Fixing a bug and proving no regressions
  • Migrating a project to a new language or framework
  • Checking if a test suite actually catches real bugs

Contoh Alur Kerja

INPUT

User asks: Use wreckit to audit this Python project

AGENT
  1. 1

    Runs detect-stack.sh to identify the language, framework, and test runner

  2. 2

    Runs slop-scan.sh to find placeholder code, empty stubs, and template artifacts

  3. 3

    Runs type checker and coverage stats, then spawns parallel gate workers for mutation testing and SAST

  4. 4

    Runs design-review.sh to analyze dependency graph, coupling, and circular dependencies

  5. 5

    Aggregates all gate results via proof-bundle.sh and writes .wreckit/decision.md with a final verdict

OUTPUT

.wreckit/decision.md with a Ship, Caution, or Blocked verdict plus a full proof bundle at .wreckit/proof.json

Instalasi

clawhub install christiancattaneo/wreckit-ralph

Jalankan perintah CLI-nya, atau tempel prompt ke Claude Code, Cursor, Codex, atau coding agent apa pun yang Anda pakai.

Tautan