SuperAPI AI Directory
Partner中文AI newsFavorites
Skillsdebug

debug

Testing & quality

View repository

Updated 10-16 05:04

About this skill

Debug Skill

Trigger

  • Keywords: debug, debugging, troubleshoot, diagnose, investigate issues, find bugs, why isn't it working, why doesn't it work, something wrong, not working

When NOT to Use

Scenario Alternative
GitHub Issue / PR thread analysis /issue-analyze
Known root cause, direct fix /bug-fix
Understand how the code works /code-explore
Need dual-perspective confirmation of logic /code-investigate
Post-deployment read-only functionality verification /feature-verify

Prohibited Actions

❌ git add | git commit | git push — per @rules/git-workflow.md

This skill debugs and may fix code but does not commit. /precommit is a quality gate only. To commit, offer the menu per rules/git-workflow.md § Proactive Offer — a commit option on any real branch, a push option only where review-state.js offer allows one — and invoke /smart-commit --execute on selection; never print the command for the user to copy.

Workflow

Phase 0    Phase 1     Phase 2          Phase 3           Phase 4        Phase 5
Intake  →  Classify →  Probe Loop   →   Root Cause    →   Fix +       →  Report
+ Repro    (Taxonomy)  (max 6)          Confirmation      Verify
  │          │           │                 │                │              │
  ▼          ▼           ▼                 ▼                ▼              ▼
Execute    refs/       Bash            /seek-verdict    Edit+test     --export
reproduce  failure-    /codex-         /code-investigate /bug-fix      (optional)
           taxonomy    brainstorm      (optional)

Phase 0: Intake + Reproduce

Step Action Output
0a Parse the problem description (symptoms, scope, environment) Structured problem description
0b Attempt to reproduce (run commands/scripts) Expected vs actual results
0c Reproduction successful? Yes → Phase 1 / No → ⚠️ Need Human

Repro Contract: Root cause claims must be based on reproducible observations, not on static speculation.

Phase 1: Classify

Based on the observed failure mode, use the Failure Taxonomy to classify and select a first-probe strategy.

See references/failure-taxonomy.md for:

  • 6 problem types + detection signals + first-probe commands
  • Classification decision tree
  • Escalation paths

Phase 2: Probe Loop

Hypothesis-driven interactive probing loop. See references/probe-protocol.md for full rules.

Each probe is a hypothesis test:

1. 定義假設 H
2. 設計探測命令 C
3. 預測「若 H 成立 → 期望 O」
4. 執行 C → 觀察實際結果
5. 更新假設集合
6. 選下一個最具鑑別力的探測

Termination

Condition Action
Root cause located + ≥1 execution result as supporting evidence Stop → Phase 3
≥2 competing hypotheses cannot be distinguished Brainstorm → /codex-brainstorm adversarial debate
2 consecutive rounds with no new information Escalate → ⚠️ Need Human
Max rounds (6) reached Escalate → ⚠️ Need Human

/codex-brainstorm Integration

When ≥2 equally credible hypotheses exist:

  1. Pause probe loop
  2. Invoke /codex-brainstorm via Skill tool — topic = hypothesis comparison
  3. Use Nash equilibrium result as new primary hypothesis
  4. Resume probe loop to verify

Phase 3: Root Cause Confirmation

Step Action Required
3a Summarize the root cause (What + Why + Impact + Evidence) ✅
3b /seek-verdict --intent confirm — Codex independent verification ✅ Mandatory
3c /code-investigate dual-perspective in-depth verification Optional
3d /git-investigate trace the introduction point (if regression) Conditional

/seek-verdict Integration (Step 3b — Mandatory)

Invoke /seek-verdict --intent confirm for independent root cause verification.

Anti-anchoring contract (per @skills/seek-verdict/SKILL.md):

  • Fresh thread: a new § Start dispatch, never a § Resume onto an existing thread
  • No Claude conclusions: prompt must not contain Claude's probe findings or root cause judgment
  • Finding packet only: provide symptoms, files, observed behavior — let Codex judge independently

Result routing:

Result Action
ACTIONABLE (confirm) → Phase 4
NON_ACTIONABLE (high confidence) Re-enter Phase 2 or ⚠️ Need Human
UNCERTAIN → Phase 4 (conservative), note low confidence

Phase 4: Fix + Verify

Condition Path
Simple fix (≤3 lines) Edit + regression test + verify
Complex fix (multi-file) Delegate to /bug-fix
Architecture-level change ⛔ Need Human — report root cause + recommendation

All fix paths require regression test per @rules/testing.md evidence model. Bug type → test level mapping per @skills/bug-fix/SKILL.md.

Simple fix path:

  1. Edit fix
  2. Write regression test
  3. Re-execute Phase 0 repro command (verify fix)
  4. If code file changed → enter review loop (auto-loop)

Phase 5: Debug Report

Output format: see references/report-template.md.

Default: conversation-only output. With --export [path], write to file (with redaction per Probe Safety Rules).

Probe Safety Rules

Rule Description
Read-first default Probes are read-only by default:cat, curl -s, grep, ls, git log
Write-probe gate Probes that may modify state are marked [WRITE_PROBE], and in non-sandbox environments require user confirmation
Timeout Each probe command has a timeout ≤ 30 seconds
Output budget Single probe output ≤ 500 lines (truncate if exceeded)
Redaction Recording API keys, tokens, passwords is prohibited (per @rules/security.md), replace with [REDACTED] replaced with
Deny list Prohibited:rm, drop, delete, truncate, any destructive operation

Config

Key Default Description
debug.max_probe_rounds 6 Maximum probe loop iterations

Review Loop

MUST re-review after fix until PASS (per @rules/auto-loop.md)

Fix → Review → Issues found → Fix again → ... → ✅ Pass → Next step

Doc Sync

Doc Sync is governed by @rules/auto-loop.md (behavior-layer rule). After precommit pass, triggers conditionally when changes map to docs/features/.

Output

## Debug Report: <title>
- **Type**: <classification>
- **Root Cause**: <what + why>
- **Fix**: <change description>
- **Verdict**: <seek-verdict result>
- **Probe Rounds**: <N>

Verification

  • Phase 0 reproduced the issue
  • Problem classified using failure taxonomy
  • Probe journal recorded for each round
  • /seek-verdict --intent confirm executed (Phase 3)
  • Root cause has ≥1 execution evidence
  • Regression test written (if fix applied)
  • Review loop completed (if code changed)
  • No git add/commit/push executed

References

File Purpose When to Read
references/failure-taxonomy.md Problem classification + first-probe routing Phase 1
references/probe-protocol.md Probe Loop rules + termination criteria Phase 2
references/report-template.md Debug Report template + export format Phase 5

Examples

Script Bug

Input: /debug bash scripts/deploy.sh 回傳 exit code 1
Phase 0: 執行 bash scripts/deploy.sh → 確認失敗
Phase 1: Script Bug
Phase 2: R1: bash -x trace → 發現 line 42 curl 失敗
         R2: 直接 curl endpoint → 404
         R3: 檢查 URL → 路徑缺少 /api prefix → Stop
Phase 3: /seek-verdict confirm → ACTIONABLE
Phase 4: Edit line 42 + regression test
Phase 5: Debug Report

API Error

Input: /debug API 回傳空陣列但資料庫有資料
Phase 0: curl API endpoint → 確認回傳 []
Phase 1: Silent Failure（表面正常但結果錯誤）
Phase 2: R1: 檢查 query filter → 發現 status 欄位名稱不符
         R2: 直接 DB query → 有資料 → Stop
Phase 3: /seek-verdict confirm → ACTIONABLE
Phase 4: 修正 field name + unit test
Phase 5: Debug Report

Silent Failure

Input: /debug ks-status.sh 回傳 ready:false 但 deployment 已就緒
Phase 0: 執行 bash ks-status.sh → ready:false, 缺少 replicas 欄位
Phase 1: Silent Failure（404 被 fallback 吞掉）
Phase 2: R1: 直接 curl API → invalid JSON → R2: 原始回應 → 404
         R3: 改用 apps/v1 路徑 → 200 + 完整資料 → Stop
Phase 3: /seek-verdict confirm → ACTIONABLE
Phase 4: api/v1 → apps/v1（1 word fix）+ test
Phase 5: Debug Report