flow-debugging

4-phase systematic debugging for flow-fix. NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST.

25 stars

Best use case

flow-debugging is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

4-phase systematic debugging for flow-fix. NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST.

Teams using flow-debugging should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/flow-debugging/SKILL.md --create-dirs "https://raw.githubusercontent.com/ComeOnOliver/skillshub/main/skills/aiskillstore/marketplace/dimon94/flow-debugging/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/flow-debugging/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How flow-debugging Compares

Feature / Agentflow-debuggingStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

4-phase systematic debugging for flow-fix. NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Flow Debugging - Systematic Debugging Method

## The Iron Law

```
NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST
```

Bug fixing is not a guessing game. Systematic debugging = faster fixes + fewer regressions.

## The 4-Phase Process

```
Phase 1: ROOT CAUSE INVESTIGATION (NO FIXES YET)
    ↓
Phase 2: PATTERN ANALYSIS
    ↓
Phase 3: HYPOTHESIS AND TESTING
    ↓
Phase 4: IMPLEMENTATION (TDD)
```

## Phase 1: Root Cause Investigation

**Iron Law**: In this phase, **NO FIX CODE ALLOWED**.

```yaml
Step 1: Read Error Completely
  - Don't skip any details
  - Record: error type, message, stack trace
  - Record: when it happens, frequency, impact

Step 2: Stable Reproduction
  - Find reliable reproduction steps
  - Record: inputs, environment, preconditions
  - If can't reproduce → gather more information

Step 3: Check Recent Changes
  - git log --oneline -20
  - git diff HEAD~5
  - Ask: What changed? When did it start failing?

Step 4: Trace Data Flow Backwards
  - Start from error point
  - Trace upstream
  - Find where data goes wrong
```

**Output**: Root cause hypothesis (evidence-based, not a guess)

## Phase 2: Pattern Analysis

```yaml
Step 1: Find Working Examples
  - Where does similar functionality work?
  - Compare: working vs broken

Step 2: Compare with Reference
  - What does official documentation say?
  - How do other projects do it?
  - What's different?

Step 3: Identify Patterns
  - Is this a known bug pattern?
  - Search: error message + framework name
```

**Output**: Confirmed or refined root cause hypothesis

## Phase 3: Hypothesis and Testing

```yaml
Step 1: Form Single Hypothesis
  - "The problem is because X"
  - Hypothesis must be verifiable

Step 2: Test One Variable at a Time
  - Change only one factor
  - Observe result
  - Record: what changed, what happened

Step 3: 3+ Failed Fixes → STOP
  - If 3+ fix attempts fail
  - Stop and question architecture
  - Problem may be deeper than thought
```

**Red Flag**: If you're "trying this, trying that", you're guessing, not debugging.

## Phase 4: Implementation (TDD)

**Prerequisite**: Phases 1-3 complete, root cause confirmed

```yaml
Step 1: Write Failing Test First
  - Test must reproduce the bug
  - Run test, confirm it fails
  - This is your "red light"

Step 2: Implement Single Fix
  - Fix only the root cause
  - Don't "while I'm here" other things
  - Minimal change

Step 3: Verify
  - Run test, confirm it passes
  - Run related tests, confirm no regression
  - Manual verify original issue resolved
```

## Rationalization Prevention

| Excuse | Reality |
|--------|---------|
| "I know where the problem is" | Prove it. Investigate first. |
| "Quick fix" | Quick fix = quick regression. Systematic debug. |
| "No time for tests" | No tests = don't know if really fixed. |
| "Small change" | Small changes can introduce big bugs. Test it. |
| "Fix first, investigate later" | Fixing without understanding = guessing. |
| "Let me try this" | "Trying" is not debugging. Form hypothesis, verify it. |
| "It's obvious" | Nothing is obvious. Prove with evidence. |
| "I've seen this before" | Every bug is unique. Investigate this one. |

## Red Flags - STOP

If you find yourself:
- Fixing without reproduction
- "Trying this, trying that"
- 3+ failed fix attempts
- Saying "fixed" without tests
- Changing many files for one bug

**STOP. Go back to Phase 1. Investigate root cause.**

## Debug Output Template

```markdown
# Bug Analysis - ${BUG_ID}

## Phase 1: Root Cause Investigation

### Error Details
- Type: [error type]
- Message: [error message]
- Stack: [key stack frames]

### Reproduction
- Steps: [1, 2, 3...]
- Frequency: [always/sometimes/rare]
- Environment: [conditions]

### Recent Changes
- [relevant commits]

### Data Flow Analysis
- [where data goes wrong]

### Root Cause Hypothesis
[Evidence-based hypothesis]

## Phase 2: Pattern Analysis

### Working Example
[Where similar code works]

### Comparison
[Difference between working and broken]

### Confirmed Root Cause
[Refined hypothesis]

## Phase 3: Hypothesis Testing

### Hypothesis
[Single testable hypothesis]

### Test Results
| Change | Result |
|--------|--------|
| [change 1] | [result] |

## Phase 4: Implementation

### Failing Test
[Test code that reproduces bug]

### Fix
[Minimal fix code]

### Verification
- [ ] Test passes
- [ ] No regression
- [ ] Manual verification
```

## Integration with flow-fix

This skill is the core methodology for `/flow-fix` command:

```yaml
/flow-fix phases:
  阶段 1: Root Cause Investigation → This skill Phase 1
  阶段 2: Pattern Analysis & Planning → This skill Phase 2
  阶段 3: 修复执行 (TDD) → This skill Phase 3-4
  阶段 4: 验证与发布 → verification-before-completion
```

## Cross-Reference

- [flow-fix.md](../../commands/flow-fix.md) - Bug fix command
- [flow-tdd/SKILL.md](../flow-tdd/SKILL.md) - TDD enforcement
- [verification-before-completion](../verification-before-completion/SKILL.md) - Verification skill

---

**[PROTOCOL]**: 变更时更新此头部,然后检查 CLAUDE.md

Related Skills

tensorflow-serving-setup

25
from ComeOnOliver/skillshub

Tensorflow Serving Setup - Auto-activating skill for ML Deployment. Triggers on: tensorflow serving setup, tensorflow serving setup Part of the ML Deployment skill category.

tensorflow-savedmodel-creator

25
from ComeOnOliver/skillshub

Tensorflow Savedmodel Creator - Auto-activating skill for ML Deployment. Triggers on: tensorflow savedmodel creator, tensorflow savedmodel creator Part of the ML Deployment skill category.

tensorflow-model-trainer

25
from ComeOnOliver/skillshub

Tensorflow Model Trainer - Auto-activating skill for ML Training. Triggers on: tensorflow model trainer, tensorflow model trainer Part of the ML Training skill category.

step-functions-workflow

25
from ComeOnOliver/skillshub

Step Functions Workflow - Auto-activating skill for AWS Skills. Triggers on: step functions workflow, step functions workflow Part of the AWS Skills skill category.

sprint-workflow

25
from ComeOnOliver/skillshub

Execute this skill should be used when the user asks about "how sprints work", "sprint phases", "iteration workflow", "convergent development", "sprint lifecycle", "when to use sprints", or wants to understand the sprint execution model and its convergent diffusion approach. Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

process-flow-generator

25
from ComeOnOliver/skillshub

Process Flow Generator - Auto-activating skill for Visual Content. Triggers on: process flow generator, process flow generator Part of the Visual Content skill category.

prefect-flow-builder

25
from ComeOnOliver/skillshub

Prefect Flow Builder - Auto-activating skill for Data Pipelines. Triggers on: prefect flow builder, prefect flow builder Part of the Data Pipelines skill category.

oauth2-flow-helper

25
from ComeOnOliver/skillshub

Oauth2 Flow Helper - Auto-activating skill for Security Fundamentals. Triggers on: oauth2 flow helper, oauth2 flow helper Part of the Security Fundamentals skill category.

n8n-workflow-generator

25
from ComeOnOliver/skillshub

N8N Workflow Generator - Auto-activating skill for Business Automation. Triggers on: n8n workflow generator, n8n workflow generator Part of the Business Automation skill category.

mlflow-tracking-setup

25
from ComeOnOliver/skillshub

Mlflow Tracking Setup - Auto-activating skill for ML Training. Triggers on: mlflow tracking setup, mlflow tracking setup Part of the ML Training skill category.

mermaid-flowchart-generator

25
from ComeOnOliver/skillshub

Mermaid Flowchart Generator - Auto-activating skill for Visual Content. Triggers on: mermaid flowchart generator, mermaid flowchart generator Part of the Visual Content skill category.

jira-workflow-creator

25
from ComeOnOliver/skillshub

Jira Workflow Creator - Auto-activating skill for Enterprise Workflows. Triggers on: jira workflow creator, jira workflow creator Part of the Enterprise Workflows skill category.