RDCrystalLab avatar

patch-based-engineering

v1.0.0

by RDCrystalLab · author: Ricky

patch-based-engineering is an Agent Plugin published by RDCrystalLab that packages 1 skill and no MCP servers for ChatGPT, Codex, Cursor, GitHub Copilot, VS Code, and Kiro. Verified against the official Agent Plugins 1.0.0 schema on 2026-08-07; MIT licensed.

Patch-Based Engineering workflow — 將 patch / commit range 轉成可重建 spec,支援 spec-first reapply 與 clean-baseline validation。觸發詞:把這個 patch 變成 spec、重建這個客製化、從 commit range 抽出需求、驗證 patches.md 能不能獨立重做;extract patch intent, reapply from spec, validate patch spec.

Skills
1
MCP servers
0
Stars
0
License
MIT

Links

Skills · 1

  • patch-based-engineering

Keywords

patch · spec · reapply · downstream · upstream · worktree · reconstruction

Related plugins

  • agency-agentsRDCrystalLab

    數位行銷代理商專用 Agent 集合,涵蓋工程、設計、行銷、銷售、測試等 14 個專業類別,共超過 140 個專業 Agent。

  • anvilRDCrystalLab

    Evidence-first coding agent. Verifies before presenting. Attacks its own output with adversarial multi-model review, IDE diagnostics, and SQL-tracked verification to ensure code quality.

  • autoresearchRDCrystalLab

    Autonomous improvement engine for Claude Code. Runs an unbounded modify-verify-keep/discard loop against any mechanical metric. Includes planning wizard, security audit, shipping workflow, autonomous debugger, and autonomous fixer.

  • cavemanRDCrystalLab

    Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.

  • cli-creatorRDCrystalLab

    從 API 文件、OpenAPI spec、curl 範例或現有腳本建立可組合的 CLI 工具。支援 Python (uv single-file)、Rust、TypeScript,含 companion skill 自動生成。

  • damage-controlRDCrystalLab

    損害控制 (Damage Control) 安全系統 - 透過 PreToolUse 鉤子封鎖危險指令並保護敏感檔案

Verified : manifest fetched from GitHub and checked against the official Agent Plugins 1.0.0 schema (agent-plugins.org).