Claude
Cursor
Skill
parallel-debugging
Debug complex issues using competing hypotheses with parallel investigation, evidence collection, and root cause arbitration. Use this skill when debugging bugs with multiple potential causes, performing root cause analysis, or organizing parallel investigation workflows.
Virus-scanned
Reviewed automatically before listing.
Download
wshobson-agents-plugins_agent-teams_skills_parallel-debugging-554237f.zip · 3 KB
Install
skills CLI
npx skills add https://github.com/wshobson/agents/tree/main/plugins/agent-teams/skills/parallel-debugging
Claude Code
claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install wshobson-agents@llmmart
Git
git clone https://github.com/wshobson/agents.git
The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole wshobson/agents collection as a plugin from our marketplace. Git is the plain clone.
Skill manifest
Parallel Debugging
Framework for debugging complex issues using the Analysis of Competing Hypotheses (ACH) methodology with parallel agent investigation.
When to Use This Skill
- Bug has multiple plausible root causes
- Initial debugging attempts haven't identified the issue
- Issue spans multiple modules or components
- Need systematic root cause analysis with evidence
- Want to avoid confirmation bias in debugging
Hypothesis Generation Framework
Generate hypotheses across 6 failure mode categories:
1. Logic Error
- Incorrect conditional logic (wrong operator, missing case)
- Off-by-one errors in loops or array access
- Missing edge case handling
- Incorrect algorithm implementation
2. Data Issue
- Invalid or unexpected input data
- Type mismatch or coercion error
- Null/undefined/None where value expected
- Encoding or serialization problem
- Data truncation or overflow
3. State Problem
- Race condition between concurrent operations
- Stale cache returning outdated data
- Incorrect initialization or default values
- Unintended mutation of shared state
- State machine transition error
4. Integration Failure
- API contract violation (request/response mismatch)
- Version incompatibility between components
- Configuration mismatch between environments
- Missing or incorrect environment variables
- Network timeout or connection failure
5. Resource Issue
- Memory leak causing gradual degradation
- Connection pool exhaustion
- File descriptor or handle leak
- Disk space or quota exceeded
- CPU saturation from inefficient processing
6. Environment
- Missing runtime dependency
- Wrong library or framework version
- Platform-specific behavior difference
- Permission or access control issue
- Timezone or locale-related behavior
Evidence Collection Standards
What Constitutes Evidence
| Evidence Type | Strength | Example |
|---|---|---|
| Direct | Strong | Code at file.ts:42 shows if (x > 0) should be if (x >= 0) |
| Correlational | Medium | Error rate increased after commit abc123 |
| Testimonial | Weak | "It works on my machine" |
| Absence | Variable | No null check found in the code path |
Citation Format
Always cite evidence with file:line references:
**Evidence**: The validation function at `src/validators/user.ts:87`
does not check for empty strings, only null/undefined. This allows
empty email addresses to pass validation.
Confidence Levels
| Level | Criteria |
|---|---|
| High (>80%) | Multiple direct evidence pieces, clear causal chain, no contradicting evidence |
| Medium (50-80%) | Some direct evidence, plausible causal chain, minor ambiguities |
| Low (<50%) | Mostly correlational evidence, incomplete causal chain, some contradicting evidence |
Result Arbitration Protocol
After all investigators report:
Step 1: Categorize Results
- Confirmed: High confidence, strong evidence, clear causal chain
- Plausible: Medium confidence, some evidence, reasonable causal chain
- Falsified: Evidence contradicts the hypothesis
- Inconclusive: Insufficient evidence to confirm or falsify
Step 2: Compare Confirmed Hypotheses
If multiple hypotheses are confirmed, rank by:
- Confidence level
- Number of supporting evidence pieces
- Strength of causal chain
- Absence of contradicting evidence
Step 3: Determine Root Cause
- If one hypothesis clearly dominates: declare as root cause
- If multiple hypotheses are equally likely: may be compound issue (multiple contributing causes)
- If no hypotheses confirmed: generate new hypotheses based on evidence gathered
Step 4: Validate Fix
Before declaring the bug fixed:
- Fix addresses the identified root cause
- Fix doesn't introduce new issues
- Original reproduction case no longer fails
- Related edge cases are covered
- Relevant tests are added or updated
Files (agents)
-
references
-
hypothesis-testing.md 3.2 KB
# Hypothesis Testing Reference Task templates, evidence formats, and arbitration decision trees for parallel debugging. ## Hypothesis Task Template ```markdown ## Hypothesis Investigation: {Hypothesis Title} ### Hypothesis Statement {Clear, falsifiable statement about the root cause} ### Failure Mode Category {Logic Error | Data Issue | State Problem | Integration Failure | Resource Issue | Environment} ### Investigation Scope - Files to examine: {file list or directory} - Related tests: {test files} - Git history: {relevant date range or commits} ### Evidence Criteria **Confirming evidence** (if I find these, hypothesis is supported): 1. {Observable condition 1} 2. {Observable condition 2} **Falsifying evidence** (if I find these, hypothesis is wrong): 1. {Observable condition 1} 2. {Observable condition 2} ### Report Format - Confidence: High/Medium/Low - Evidence: list with file:line citations - Causal chain: step-by-step from cause to symptom - Recommended fix: if confirmed ``` ## Evidence Report Template ```markdown ## Investigation Report: {Hypothesis Title} ### Verdict: {Confirmed | Falsified | Inconclusive} ### Confidence: {High (>80%) | Medium (50-80%) | Low (<50%)} ### Confirming Evidence 1. `src/api/users.ts:47` — {description of what was found} 2. `src/middleware/auth.ts:23` — {description} ### Contradicting Evidence 1. `tests/api/users.test.ts:112` — {description of what contradicts} ### Causal Chain (if confirmed) 1. {First cause} → 2. {Intermediate effect} → 3. {Observable symptom} ### Recommended Fix {Specific code change with location} ### Additional Notes {Anything discovered that may be relevant to other hypotheses} ``` ## Arbitration Decision Tree ``` All investigators reported? ├── NO → Wait for remaining reports └── YES → Count confirmed hypotheses ├── 0 confirmed │ ├── Any medium confidence? → Investigate further │ └── All low/falsified? → Generate new hypotheses ├── 1 confirmed │ └── High confidence? │ ├── YES → Declare root cause, propose fix │ └── NO → Flag as likely cause, recommend verification └── 2+ confirmed └── Are they related? ├── YES → Compound issue (multiple contributing causes) └── NO → Rank by confidence, declare highest as primary ``` ## Common Hypothesis Patterns by Error Type ### "500 Internal Server Error" 1. Unhandled exception in request handler (Logic Error) 2. Database connection failure (Resource Issue) 3. Missing environment variable (Environment) ### "Race condition / intermittent failure" 1. Shared state mutation without locking (State Problem) 2. Async operation ordering assumption (Logic Error) 3. Cache staleness window (State Problem) ### "Works locally, fails in production" 1. Environment variable mismatch (Environment) 2. Different dependency version (Environment) 3. Resource limits (memory, connections) (Resource Issue) ### "Regression after deploy" 1. New code introduced bug (Logic Error) 2. Configuration change (Integration Failure) 3. Database migration issue (Data Issue)
-
-
SKILL.md 4.6 KB
--- name: parallel-debugging description: Debug complex issues using competing hypotheses with parallel investigation, evidence collection, and root cause arbitration. Use this skill when debugging bugs with multiple potential causes, performing root cause analysis, or organizing parallel investigation workflows. version: 1.0.2 --- # Parallel Debugging Framework for debugging complex issues using the Analysis of Competing Hypotheses (ACH) methodology with parallel agent investigation. ## When to Use This Skill - Bug has multiple plausible root causes - Initial debugging attempts haven't identified the issue - Issue spans multiple modules or components - Need systematic root cause analysis with evidence - Want to avoid confirmation bias in debugging ## Hypothesis Generation Framework Generate hypotheses across 6 failure mode categories: ### 1. Logic Error - Incorrect conditional logic (wrong operator, missing case) - Off-by-one errors in loops or array access - Missing edge case handling - Incorrect algorithm implementation ### 2. Data Issue - Invalid or unexpected input data - Type mismatch or coercion error - Null/undefined/None where value expected - Encoding or serialization problem - Data truncation or overflow ### 3. State Problem - Race condition between concurrent operations - Stale cache returning outdated data - Incorrect initialization or default values - Unintended mutation of shared state - State machine transition error ### 4. Integration Failure - API contract violation (request/response mismatch) - Version incompatibility between components - Configuration mismatch between environments - Missing or incorrect environment variables - Network timeout or connection failure ### 5. Resource Issue - Memory leak causing gradual degradation - Connection pool exhaustion - File descriptor or handle leak - Disk space or quota exceeded - CPU saturation from inefficient processing ### 6. Environment - Missing runtime dependency - Wrong library or framework version - Platform-specific behavior difference - Permission or access control issue - Timezone or locale-related behavior ## Evidence Collection Standards ### What Constitutes Evidence | Evidence Type | Strength | Example | | ----------------- | -------- | --------------------------------------------------------------- | | **Direct** | Strong | Code at `file.ts:42` shows `if (x > 0)` should be `if (x >= 0)` | | **Correlational** | Medium | Error rate increased after commit `abc123` | | **Testimonial** | Weak | "It works on my machine" | | **Absence** | Variable | No null check found in the code path | ### Citation Format Always cite evidence with file:line references: ``` **Evidence**: The validation function at `src/validators/user.ts:87` does not check for empty strings, only null/undefined. This allows empty email addresses to pass validation. ``` ### Confidence Levels | Level | Criteria | | ------------------- | ----------------------------------------------------------------------------------- | | **High (>80%)** | Multiple direct evidence pieces, clear causal chain, no contradicting evidence | | **Medium (50-80%)** | Some direct evidence, plausible causal chain, minor ambiguities | | **Low (<50%)** | Mostly correlational evidence, incomplete causal chain, some contradicting evidence | ## Result Arbitration Protocol After all investigators report: ### Step 1: Categorize Results - **Confirmed**: High confidence, strong evidence, clear causal chain - **Plausible**: Medium confidence, some evidence, reasonable causal chain - **Falsified**: Evidence contradicts the hypothesis - **Inconclusive**: Insufficient evidence to confirm or falsify ### Step 2: Compare Confirmed Hypotheses If multiple hypotheses are confirmed, rank by: 1. Confidence level 2. Number of supporting evidence pieces 3. Strength of causal chain 4. Absence of contradicting evidence ### Step 3: Determine Root Cause - If one hypothesis clearly dominates: declare as root cause - If multiple hypotheses are equally likely: may be compound issue (multiple contributing causes) - If no hypotheses confirmed: generate new hypotheses based on evidence gathered ### Step 4: Validate Fix Before declaring the bug fixed: - [ ] Fix addresses the identified root cause - [ ] Fix doesn't introduce new issues - [ ] Original reproduction case no longer fails - [ ] Related edge cases are covered - [ ] Relevant tests are added or updated
Comments (0)
Sign in to join the conversation.
Reviews (0)
No reviews yet.
No comments yet.