菜单
Systematic step-by-step debugging process for bugs, test failures, and unexpected behavior. Use when a test fails, something isn't working as expected, user says "this is broken", "why isn't X working", "help me debug", or when you encounter any error before proposing a fix.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Create production-ready GitHub Actions workflows for automated testing, building, and deploying applications. Use when setting up CI/CD with GitHub Actions, automating development workflows, or creating reusable workflow templates.
Implement comprehensive evaluation strategies for LLM applications using automated metrics, LLM-as-judge, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, comparing prompts/models, or establishing evaluation frameworks. Covers RAGAS for RAG pipelines, evals-as-code CI/CD integration, and modern 2025/2026 practices including structured output evaluation and agentic task success measurement.
Create or expand an Idea.md / IDEA.md file from a rough description, existing repo, conversation history, notes, or other early-stage product inputs. Use when the user asks to "write an Idea.md", "turn this into an idea file", "capture this product idea", "expand this concept", or wants a repo-grounded concept brief before validation, PRD, or implementation work.
Run a rigorous autonomous experiment loop for any optimization target using explicit hypotheses, repeated trials, structured experiment logs, and local HTML reports. Use when asked to "run autoresearch", "optimize X in a loop", "start experiments", or "improve this with benchmark-driven iteration".
Capture reusable knowledge and create new skills automatically during coding sessions, problem solving, and retrospectives. Use when finishing a complex task, running a retrospective, discovering a reusable pattern, or when user says "save this as a skill", "capture this solution", "run a retrospective", or "what did we learn from this".
Build professional native macOS apps in Swift with SwiftUI and AppKit. Full lifecycle - build, debug, test, optimize, ship. CLI-only, no Xcode. Use when asked to: create macOS apps, build Swift apps, develop SwiftUI interfaces, fix macOS app issues, add macOS app features, or when user says 'build a Mac app', 'create a Swift project', 'develop for macOS'.
| name | systematic-debugging |
| description | Systematic step-by-step debugging process for bugs, test failures, and unexpected behavior. Use when a test fails, something isn't working as expected, user says "this is broken", "why isn't X working", "help me debug", or when you encounter any error before proposing a fix. |
Random fixes waste time and create new bugs. Quick patches mask underlying issues.
Core principle: ALWAYS find root cause before attempting fixes. Symptom fixes are failure.
Violating the letter of this process is violating the spirit of debugging.
NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST
If you haven't completed Phase 1, you cannot propose fixes.
Use for ANY technical issue:
Use this ESPECIALLY when:
Don't skip when:
You MUST complete each phase before proceeding to the next.
BEFORE attempting ANY fix:
Read Error Messages Carefully
Reproduce Consistently
Check Recent Changes
Gather Evidence in Multi-Component Systems
WHEN system has multiple components (CI → build → signing, API → service → database):
BEFORE proposing fixes, add diagnostic 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
Example (multi-layer system):
# 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"
This reveals: Which layer fails (secrets → workflow ✓, workflow → build ✗)
Trace Data Flow
WHEN error is deep in call stack:
See root-cause-tracing.md in this directory for the complete backward tracing technique.
Quick version:
Find the pattern before fixing:
Find Working Examples
Compare Against References
Identify Differences
Understand Dependencies
Scientific method:
Form Single Hypothesis
Test Minimally
Verify Before Continuing
When You Don't Know
Fix the root cause, not the symptom:
Create Failing Test Case
superpowers:test-driven-development skill for writing proper failing testsImplement Single Fix
Verify Fix
If Fix Doesn't Work
If 3+ Fixes Failed: Question Architecture
Pattern indicating architectural problem:
STOP and question fundamentals:
Discuss with your human partner before attempting more fixes
This is NOT a failed hypothesis - this is a wrong architecture.
If you catch yourself thinking:
ALL of these mean: STOP. Return to Phase 1.
If 3+ fixes failed: Question the architecture (see Phase 4.5)
Watch for these redirections:
When you see these: STOP. Return to Phase 1.
| Excuse | Reality |
|---|---|
| "Issue is simple, don't need process" | Simple issues have root causes too. Process is fast for simple bugs. |
| "Emergency, no time for process" | Systematic debugging is FASTER than guess-and-check thrashing. |
| "Just try this first, then investigate" | First fix sets the pattern. Do it right from the start. |
| "I'll write test after confirming fix works" | Untested fixes don't stick. Test first proves it. |
| "Multiple fixes at once saves time" | Can't isolate what worked. Causes new bugs. |
| "Reference too long, I'll adapt the pattern" | Partial understanding guarantees bugs. Read it completely. |
| "I see the problem, let me fix it" | Seeing symptoms ≠ understanding root cause. |
| "One more fix attempt" (after 2+ failures) | 3+ failures = architectural problem. Question pattern, don't fix again. |
These are anti-patterns observed in debugging practice. Recognize them and correct course immediately. See also: Red Flags and Common Rationalizations for related guidance.
Anti-pattern:
Error log shows "timeout" → assume network issue → add retry logic
(But you never actually reproduced the timeout)
Problem:
How to avoid:
npm test with X set to Y" → bug happensRecovery:
Anti-pattern:
Change 3 things:
- Update dependency version
- Refactor retry logic
- Add fallback handler
Run tests → passes
Problem:
How to avoid:
Recovery:
Anti-pattern:
Feature shipped 3 days ago → bug happened today → bug must be in that feature
(But you didn't verify the feature code against current data/environment)
Problem:
How to avoid:
Recovery:
Anti-pattern:
"Fixed the bug" (but didn't write down how to trigger it)
Weeks later: "Wait, does this still happen? I don't remember how to trigger it"
Problem:
How to avoid:
Recovery:
Anti-pattern:
Error happens in production
You: "Probably a race condition?"
You don't have logs showing what was happening at that moment
You guess at fixes for 3 hours
Problem:
How to avoid:
Specific strategies:
# Reproduce with logging
DEBUG=* npm test # Enable all logs
strace node app.js # System call tracing
tcpdump -i any -w dump # Network tracing
Recovery:
Anti-pattern:
Implement fix
Run manual test: "Looks good"
Commit and push
(No automated test proving bug existed)
Problem:
How to avoid:
Recovery:
Anti-pattern:
Database slow? Maybe it's the query. Maybe it's the network. Maybe it's CPU.
Let me add caching, fix indexes, reduce batch size, and upgrade servers.
Problem:
How to avoid:
Example:
# API slow. Which part?
time curl /api/endpoint # Total time
# Add logging to API entry point
# Add logging before DB query
# Add logging after DB returns
# Add logging before response
# Now you know: API fast (10ms), DB query slow (2s) → focus on DB
Recovery:
Anti-pattern:
Test case passes for happy path
Deploy without testing error cases
(Bug appears 2 weeks later under edge condition you didn't think to test)
Problem:
How to avoid:
Recovery:
These pitfalls are patterns, not one-off mistakes. When you catch yourself in one, stop and realign to the process.
| Phase | Key Activities | Success Criteria |
|---|---|---|
| 1. Root Cause | Read errors, reproduce, check changes, gather evidence | Understand WHAT and WHY |
| 2. Pattern | Find working examples, compare | Identify differences |
| 3. Hypothesis | Form theory, test minimally | Confirmed or new hypothesis |
| 4. Implementation | Create test, fix, verify | Bug resolved, tests pass |
If systematic investigation reveals issue is truly environmental, timing-dependent, or external:
But: 95% of "no root cause" cases are incomplete investigation.
These techniques are part of systematic debugging and available in this directory:
root-cause-tracing.md - Trace bugs backward through call stack to find original triggerdefense-in-depth.md - Add validation at multiple layers after finding root causecondition-based-waiting.md - Replace arbitrary timeouts with condition pollingRelated skills:
From debugging sessions: