메뉴
Systematic root-cause debugging with verification. Use for errors, stack traces, broken tests, flaky tests, regressions, or anything not working as expected.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Usage: Build feature {spec-name} phase {phase-number}. Implements a single phase from the spec's task plan, iterating build-test cycles until the phase passes its constitution gate, then records memory, logs decisions, and commits.
Use this skill when the user asks to map, document, or onboard into an existing codebase. Produces structured documentation covering stack, structure, architecture, conventions, integrations, testing, and concerns. Only documents what is verifiable from files or terminal output — never infers or assumes.
Use before any creative work — creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements, and design through collaborative dialogue before implementation.
Browser automation skill. Drives agent-browser through structured navigate→snapshot→interact→re-snapshot flows with authentication support, form automation, visual verification, and explicit human checkpoints for external flows.
Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes.
Structural review of documents for gaps, clarity, completeness, and organization. Use when a brainstorm, plan, spec, ADR, or any doc needs polish before the next workflow step.
| name | debugging |
| description | Systematic root-cause debugging with verification. Use for errors, stack traces, broken tests, flaky tests, regressions, or anything not working as expected. |
Never propose a fix without first identifying the root cause. "Quick fix now, investigate later" is forbidden -- it creates harder bugs. This applies ESPECIALLY under time pressure, when "just one quick fix" seems obvious, or when multiple fixes have already failed. Those are the moments this process matters most.
Trivially obvious bugs are their own root cause -- state the cause and fix directly. A bug is trivially obvious only when the cause is in the error message (e.g., ModuleNotFoundError: no module named foo, a typo in a string literal). If the error shows where something fails but not why (e.g., TypeError: Cannot read 'id' of undefined), it is not trivially obvious -- investigate why the value is undefined.
Root cause identification is the core deliverable of debugging -- not the fix itself.
git bisect to pinpoint the exact commit that introduced the issuefile:line references, log output, and concrete reproduction proof. Root cause = the earliest point where behavior diverged from expectation, stated with evidence at least two levels deep (not just "it failed here" but "it failed here because X was null, and X was null because Y never set it")0. Read the error. Read the full error message, stack trace, and line numbers before doing anything. Error messages frequently contain the exact fix. Don't skim -- read the entire output.
1. Reproduce -- build a feedback loop, then make the bug consistent. The loop is the deliverable of this step, not the analysis. Without a fast, deterministic signal that says "broken / fixed," every later step is guesswork.
Pick the cheapest loop that triggers the bug:
(git bisect and differential analysis are strategies applied during Step 5 and Pattern Comparison, not feedback loops -- they answer "which change broke it?" or "how does broken differ from working?" rather than "is it broken right now?")
If the bug is intermittent, run the loop N times under stress or simulate poor conditions (slow network, low memory) until it triggers reliably.
Cannot build a loop? Stop. State exactly what is missing -- access, credentials, artifacts, repro steps -- and ask the user. Do not proceed to investigate without a signal; you will pattern-match instead of debug.
2. Form initial hypotheses -- before investigating broadly, form 2-3 hypotheses based on the reproduction. What are the most likely causes given the symptoms? This focuses the investigation on plausible paths rather than searching aimlessly.
3. Reduce -- strip the reproduction to the minimal failing case. Remove unrelated code, data, and configuration until removing one more piece makes the bug disappear. That remaining piece is the trigger.
4. Investigate -- trace backward through the call chain from the symptom. Compare working vs broken state using a differential table (environment, version, data, timing -- what changed?).
Multi-component systems (CI -> build -> deploy, API -> service -> DB): before proposing fixes, instrument each component boundary:
Run once to gather evidence showing WHERE it breaks, then investigate that specific component. Log BEFORE the dangerous operation, not after it fails. Include context: working directory, environment variables, stack trace.
Pre-existing failure proof: Before claiming a test failure is "not related to our changes," prove it. Run the test suite on clean state to confirm the failure exists on the base branch. Pre-existing without receipts is a lazy claim.
Before external searches (web, docs, forums): strip hostnames, IPs, file paths, SQL fragments, and customer data from the query. Raw stack traces leak privacy and return noise.
5. Hypothesize and test -- one change at a time. If a hypothesis is wrong, fully revert before testing the next. Use git bisect to find regressions efficiently. Scope lock: after forming a hypothesis, identify the narrowest affected directory or file set. Do not edit code outside that scope during the debug session. If the fix requires changes elsewhere, update the hypothesis first.
6. Fix and verify -- create a failing test FIRST, then fix. Run the test. Confirm the original reproduction case passes. No completion claims without fresh verification evidence.
Emit after every resolved bug. For non-trivial production bugs, also write a full Postmortem (see below).
After resolving, output a structured report:
SYMPTOM: [What was observed]
ROOT CAUSE: [Why it happened -- file:line with evidence]
FIX: [What changed]
EVIDENCE: [Verification output proving the fix]
REGRESSION: [Test added to prevent recurrence]
RELATED: [Prior bugs in same area, known issues, architectural notes]
STATUS: DONE | DONE_WITH_CONCERNS | BLOCKED | NEEDS_CONTEXT
After 3 failed fix attempts, STOP. An attempt = one complete hypothesis-test cycle (form hypothesis, make minimal change, verify). The problem is likely architectural, not a surface bug. Escalate to the user before attempting further fixes. Step back and question assumptions about how the system works. Read the actual code path end-to-end instead of spot-checking.
Architectural problem indicators -- signals the bug is structural, not a surface fix:
No root cause found: If investigation is exhausted without a clear root cause, say so explicitly. Document what was checked, what was ruled out, and what instrumentation to add for next occurrence. An honest "unknown" with good diagnostics beats a fabricated cause.
When the cause is unclear across multiple components, use Analysis of Competing Hypotheses (ACH). Generate hypotheses across failure categories, collect evidence FOR and AGAINST each, rank by confidence, and investigate the strongest first.
Six failure categories to consider: code logic, data/state, environment/config, concurrency/timing, external dependency, infrastructure.
Evidence strength scale: direct reproduction (strongest), log correlation, code path analysis, circumstantial (weakest).
For race conditions, deadlocks, resource exhaustion, and timing-dependent bugs:
After fixing, validate at every layer -- not just where the bug appeared. Apply the four-layer pattern:
When multiple bugs exist, prioritize by:
await, unhandled promise rejection, callback firing before setup completes. The temporal gap between setup and callback is where bugs hide.git log shows 3+ prior fixes in the same file, the file needs redesign, not another patch. Escalate as architectural smell.When the cause isn't obvious, find working similar code in the codebase and compare it structurally with the broken path. Read the working reference implementation completely -- don't skim. List every difference between working and broken, however small. Don't assume any difference can't matter. The bug is in one of them.
When you catch yourself doing or thinking these things, stop and return to Step 1 (Reproduce):
| What You're Doing / Thinking | What It Really Means |
|---|---|
| Shotgun debugging / "I see the problem, let me fix it" / "It's probably X" | Reasoning is not evidence. Form a hypothesis, make one change, test, revert if wrong. Trace the actual execution path. |
| Ignoring intermittent failures ("works on my machine") | Instrument and reproduce under load. Isolation success doesn't explain integration failure. |
| "I'll clean up the debugging later" | Remove diagnostic code now or it ships to production. |
| "This failure is pre-existing, not related to our changes" | Prove it: run the test suite on the base branch. No receipts = no claim. |
| "The test is wrong, not the code" | Verify before dismissing. Read the test's intent. If the test is genuinely wrong, fix it with a clear rationale, not a silent update. |
| "Reference too long, I'll adapt the pattern" | Partial understanding guarantees bugs. Read the working example completely and apply it exactly. |
file:line evidence (not just "it failed here")git diff shows no leftover logging)For non-trivial production bugs, write a lightweight postmortem covering: timeline, root cause, impact, fix, and prevention measures.
Generated by autoharness | Template: community/skills/debugging/SKILL.md.tmpl