agentpluginsdirectory
RDCrystalLab avatar

debug-hypothesis

v1.0.0

by RDCrystalLab · author: LichAmnesia

debug-hypothesis 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.

假設驅動除錯法 — 強制 agent 走 Observe → Hypothesize → Experiment → Conclude 四階段科學方法迴圈，所有推理寫進 DEBUG.md，沒有證據前不准寫 fix。專治 AI 一路撞牆寫 150 行錯誤修復的 bulldozer 失敗模式。中文觸發詞：『這個 bug 怎麼修』、『一直修不好』、『科學方法除錯』、『debug 卡住了』。

Skills
1
MCP servers
0
Stars
0
License
MIT

Links

Skills · 1

  • debug-hypothesis

Keywords

debugging · hypothesis · scientific-method · root-cause · anti-bulldozer · debug-md

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).