Menú
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Use when an HTML UI beats terminal text — collecting structured answers (decision trees, multi-select, code/SQL fields), showing visual comparisons or mockups, running interactive demos, or presenting decisions for approval. A local browser companion renders markdown+YAML screens and streams the user's answers back. Use when: many questions at once, layout/visual choices, mockup or diagram feedback, config wizard, demo review, approve/revise decisions. Skip: a single quick question (use AskUserQuestion or plain text).
Use when you have a spec or requirements for a multi-step task, before touching code
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Use when you have a written implementation plan to execute in a separate session with review checkpoints
| name | systematic-debugging |
| description | Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes |
亂修耗時，且生新bug。速補掩真疾。
核心原則： 修前必尋根因。治症非修，乃敗。
違其字即違其意。
NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST
未完 Phase 1，不得提修。
用於任何技術問題：
尤當於：
不可跳過即使：
每階段必完方可進次。
修前：
細讀錯誤訊息
穩定復現
察近變更
多組件系統採證
當系統多層（CI → build → signing、API → service → database）：
修前，加診斷 instrumentation：
For EACH component boundary:
- Log what data enters component
- Log what data exits component
- Verify environment/config propagation
- Check state at each layer
Run once to gather evidence showing WHERE it breaks
THEN analyze evidence to identify failing component
THEN investigate that specific component
例（多層）：
# Layer 1: Workflow
echo "=== Secrets available in workflow: ==="
echo "IDENTITY: ${IDENTITY:+SET}${IDENTITY:-UNSET}"
# Layer 2: Build script
echo "=== Env vars in build script: ==="
env | grep IDENTITY || echo "IDENTITY not in environment"
# Layer 3: Signing script
echo "=== Keychain state: ==="
security list-keychains
security find-identity -v
# Layer 4: Actual signing
codesign --sign "$IDENTITY" --verbose=4 "$APP"
此揭： 何層斷（secrets → workflow ✓、workflow → build ✗）
追資料流
當錯深藏 call stack：
詳見 root-cause-tracing.md（本目錄，完整回溯技術）。
簡版：
修前尋式：
尋可用範例
比對參考
辨差異
明依賴
科學法：
成單一假說
最小測試
驗後再進
不知之時
修根因，非症：
立失敗測例
superpowers:test-driven-development skill 寫真失敗測單修實作
驗修
若修不效
三修皆敗：質問架構
示架構問題之兆：
止，質根本：
與 your human partner 論，方可再試
此非假說敗，乃架構誤。
若察己念：
皆意：止。返 Phase 1。
若 3+ 修敗： 質架構（見 Phase 4.5）
察此等改向：
見此：止。返 Phase 1。
| Excuse | Reality |
|---|---|
| 「疾簡，無需流程」 | 簡疾亦有根因。流程於簡 bug 亦速。 |
| 「急，無暇流程」 | 系統化比亂修快。 |
| 「先試此，後察」 | 首修定式。始即正。 |
| 「確修效後再寫測」 | 未測之修不定。測先證之。 |
| 「多修並行省時」 | 無法辨何效。生新 bug。 |
| 「參考過長，吾變其式」 | 半解必生 bug。完讀之。 |
| 「吾見題，修之」 | 見症 ≠ 明根因。 |
| 「再一修」（2+敗後） | 3+ 敗 = 架構問題。質式，勿再修。 |
| Phase | Key Activities | Success Criteria |
|---|---|---|
| 1. Root Cause | 讀錯、復現、察變、採證 | 明何與為何 |
| 2. Pattern | 尋可用例，比對 | 辨差異 |
| 3. Hypothesis | 立說，最小測 | 證或新說 |
| 4. Implementation | 立測、修、驗 | bug 解，測過 |
若系統察揭疾實為環境、時序、外部所致：
然： 95% 之「無根因」實為察不完。
本目錄內技術，皆系統化 debugging 之支：
root-cause-tracing.md — 回溯 bug 穿 call stack 尋原觸發defense-in-depth.md — 尋根因後於多層加 validationcondition-based-waiting.md — 以條件輪詢替任意 timeout相關 skills：
From debugging sessions: