parallel-investigation
Coordinates parallel investigation threads to simultaneously explore multiple hypotheses or root causes across different system areas. Use when debugging production incidents, slow API performance, multi-system integration failures, or complex bugs where the root cause is unclear and multiple plausible theories exist; when serial troubleshooting is too slow; or when multiple investigators can divide root-cause analysis work. Provides structured phases for problem decomposition, thread assignment, sync points with Continue/Pivot/Converge decisions, and final report synthesis.
Best use case
parallel-investigation is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Coordinates parallel investigation threads to simultaneously explore multiple hypotheses or root causes across different system areas. Use when debugging production incidents, slow API performance, multi-system integration failures, or complex bugs where the root cause is unclear and multiple plausible theories exist; when serial troubleshooting is too slow; or when multiple investigators can divide root-cause analysis work. Provides structured phases for problem decomposition, thread assignment, sync points with Continue/Pivot/Converge decisions, and final report synthesis.
Teams using parallel-investigation 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
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/parallel-investigation/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How parallel-investigation Compares
| Feature / Agent | parallel-investigation | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Coordinates parallel investigation threads to simultaneously explore multiple hypotheses or root causes across different system areas. Use when debugging production incidents, slow API performance, multi-system integration failures, or complex bugs where the root cause is unclear and multiple plausible theories exist; when serial troubleshooting is too slow; or when multiple investigators can divide root-cause analysis work. Provides structured phases for problem decomposition, thread assignment, sync points with Continue/Pivot/Converge decisions, and final report synthesis.
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
# Parallel Investigation
Coordinate parallel investigation threads to explore multiple hypotheses simultaneously. Most effective for production incidents, performance regressions, or integration failures where the root cause is unclear.
## Core Principle
**When uncertain, explore multiple paths in parallel. Converge when evidence points to an answer.**
Parallel investigation reduces time-to-solution by eliminating serial bottlenecks.
## Investigation Structure
### Phase 1: Problem Decomposition
Break the problem into independent investigation threads:
```
Problem: API responses are slow
Investigation Threads:
├── Thread A: Database performance
│ └── Check slow queries, indexes, connection pool
├── Thread B: Application code
│ └── Profile endpoint handlers, check for N+1
├── Thread C: Infrastructure
│ └── Check CPU, memory, network latency
└── Thread D: External services
└── Check third-party API response times
```
Each thread should be independent (no blocking dependencies), focused (clear scope), and time-boxed.
### Phase 2: Thread Assignment
Assign threads with clear ownership:
```markdown
## Thread A: Database Performance
**Investigator:** [Name/Agent A]
**Duration:** 30 minutes
**Scope:**
- Query execution times
- Index utilization
- Connection pool metrics
**Report Format:** Summary + evidence
```
### Phase 3: Parallel Execution
Each thread follows this pattern:
1. Gather evidence specific to thread scope
2. Document findings as you go
3. Identify if thread is a lead or dead end
4. Prepare summary for sync point
**Thread Log Template:**
```markdown
## Thread: [Name]
**Start:** [Time]
### Findings
- [Timestamp] [Finding]
### Evidence
- [Log/Metric/Screenshot]
### Preliminary Conclusion
[What this thread suggests about the problem]
```
### Phase 4: Sync Points
Regular convergence to share findings:
```
Sync Point Agenda:
1. Each thread report (2 min each)
2. Discussion & correlation (5 min)
3. Decision: Continue, Pivot, or Converge (3 min)
```
**Sync Point Decisions:**
- **Continue**: Threads are progressing, maintain parallel execution
- **Pivot**: Redirect threads based on new evidence
- **Converge**: One thread found the answer, others join to validate
### Phase 5: Convergence
When a thread identifies the likely cause:
1. **Validate** — Other threads verify the finding
2. **Deep dive** — Focused investigation on identified cause
3. **Document** — Compile findings from all threads
## Coordination Patterns
**Hub and Spoke**: One coordinator assigns threads, tracks progress, calls sync points, and makes convergence decisions. Best when one person has the most context.
**Peer Network**: Equal investigators post findings to a shared channel and self-organize convergence when a pattern emerges. Best when investigators have similar expertise.
## Communication Protocol
### During Investigation
```
[Thread A] [Status] Starting query analysis
[Thread B] [Finding] No N+1 patterns in user endpoint
[Thread A] [Finding] Slow query: SELECT * FROM orders WHERE...
[Thread C] [Dead End] CPU and memory within normal
[Thread A] [Hot Lead] Missing index on orders.user_id
```
### At Sync Point
```markdown
## Thread A Summary
**Status:** Hot Lead
**Key Finding:** Missing index on orders.user_id
**Evidence:** Query taking 3.2s, explain shows full table scan
**Recommendation:** Likely root cause — suggest converge
```
## Decision Framework
| Thread Status | Action |
|---------------|--------|
| All exploring | Continue parallel |
| One hot lead | Validate lead, others support |
| Multiple leads | Prioritize by evidence strength |
| All dead ends | Reframe problem, new threads |
| Confirmed cause | Converge, begin fix |
## Time Management
A typical two-hour investigation:
```
0:00 Problem decomposition & thread assignment
0:15 Parallel investigation begins
0:45 Sync point #1 → Continue/Pivot/Converge decision
1:30 Sync point #2 (if continuing)
1:35 Final convergence & documentation
```
Adjust sync point cadence based on incident severity — every 20 minutes for critical outages, every 45 minutes for lower-urgency investigations.
## Documentation
### Final Report Structure
```markdown
# Investigation: [Problem]
## Summary
[Brief description and resolution]
## Threads Explored
### Thread A: [Area]
- Investigator: [Name]
- Findings: [Summary]
- Outcome: [Lead / Dead End / Root Cause]
## Root Cause
[Detailed explanation of what was found]
## Evidence
- [Evidence 1]
- [Evidence 2]
## Resolution
[What was done to fix]
## Lessons Learned
- [Learning 1]
```
## Integration with Other Skills
- **debugging/root-cause-analysis**: Each thread follows RCA principles
- **debugging/hypothesis-testing**: Threads test specific hypotheses
- **handoff-protocols**: When passing a thread to another personRelated Skills
find-skills
Discovers, searches, and installs skills from multiple AI agent skill marketplaces (400K+ skills) using the SkillKit CLI. Supports browsing official partner collections (Anthropic, Vercel, Supabase, Stripe, and more) and community repositories, searching by domain or technology, and installing specific skills from GitHub. Use when the user wants to find, browse, or install new agent skills, plugins, extensions, or add-ons; asks 'is there a skill for X' or 'find a skill for X'; wants to explore a skill store or marketplace; needs to extend agent capabilities in areas like React, testing, DevOps, security, or APIs; or says 'browse skills', 'search skill marketplace', 'install a skill', or 'what skills are available'.
test-patterns
Applies proven testing patterns — Arrange-Act-Assert (AAA), Given-When-Then, Test Data Builders, Object Mother, parameterized tests, fixtures, spies, and test doubles — to help write maintainable, reliable, and readable test suites. Use when the user asks about writing unit tests, integration tests, or end-to-end tests; structuring test cases or test suites; applying TDD or BDD practices; working with mocks, stubs, spies, or fakes; improving test coverage or reducing flakiness; or needs guidance on test organization, naming conventions, or assertions in frameworks like Jest, Vitest, pytest, or similar.
red-green-refactor
Guides the red-green-refactor TDD workflow: write a failing test first, implement the minimum code to make it pass, then refactor while keeping tests green. Use when a user asks to practice TDD, write tests first, follow red-green-refactor, do test-driven development, write failing tests before code, or phrases like 'make the test pass', 'test coverage', or 'unit tests before implementation'.
testing-anti-patterns
Reviews test code to identify and fix common testing anti-patterns including flaky tests, over-mocking, brittle assertions, test interdependency, and hidden test logic. Flags bad patterns, explains the specific defect, and provides corrected implementations. Use when reviewing test code, debugging intermittent or unreliable test failures, or when the user mentions flaky tests, test smells, brittle tests, test isolation issues, mock overuse, slow tests, or test maintenance problems.
verification-gates
Creates explicit validation checkpoints (verification gates) between project phases to catch errors early and ensure quality before proceeding. Use when the user asks about quality gates, milestone checks, phase transitions, approval steps, go/no-go decision points, or preventing cascading errors across a multi-step workflow. Produces acceptance criteria checklists, automated CI gate configurations, manual sign-off requirements, and conditional review rules for scenarios such as security changes, API changes, or database migrations.
task-decomposition
Breaks down complex software, writing, or research tasks into small, atomic, independently completable units with dependency graphs and milestone breakdowns. Use when the user asks to plan a project, decompose a feature, create subtasks, split up work, or needs help organizing a large piece of work into a step-by-step plan. Triggered by phrases like "break down", "decompose", "where do I start", "too big", "split into tasks", "work breakdown", or "task list".
design-first
Guides the creation of technical design documents before writing code, producing architecture diagrams, data models, API interface definitions, implementation plans, and multi-option trade-off analyses. Use when the user asks to plan a feature, architect a system, design an API, explore implementation approaches, or requests a technical design or spec before coding — especially for complex features involving multiple components, ambiguous requirements, or significant architectural changes.
skill-authoring
Creates and structures SKILL.md files for AI coding agents, including YAML frontmatter, trigger phrases, directive instructions, decision trees, code examples, and verification checklists. Use when the user asks to write a new skill, create a skill file, author agent capabilities, generate skill documentation, or define a skill template for Claude Code agents.
trace-and-isolate
Applies systematic tracing and isolation techniques to pinpoint exactly where a bug originates in code. Use when a bug is hard to locate, code is not working as expected, an error or crash appears with unclear cause, a regression was introduced between recent commits, or you need to narrow down which component, function, or line is faulty. Covers binary search debugging, git bisect for regressions, strategic logging with [TRACE] patterns, data and control flow tracing, component isolation, minimal reproduction cases, conditional breakpoints, and watch expressions across TypeScript, SQL, and bash.
root-cause-analysis
Performs systematic root cause analysis to identify the true source of bugs, errors, and unexpected behavior through structured investigation phases — not just treating symptoms. Use when a user reports a bug, crash, error, or broken behavior and needs to debug, troubleshoot, or investigate why something is not working; especially for complex or intermittent issues across multiple components. Applies the Five Whys method, hypothesis-driven testing, stack trace analysis, git blame/log evidence gathering, and causal chain documentation to isolate and confirm root causes before applying any fix.
hypothesis-testing
Applies the scientific method to debugging by helping users form specific, testable hypotheses, design targeted experiments, and systematically confirm or reject theories to find root causes. Use when a user says their code isn't working, they're getting an error, something broke, they want to troubleshoot a bug, or they're trying to figure out what's causing an issue. Concrete actions include isolating failing components, forming and testing hypotheses, analyzing error messages, tracing execution paths, and interpreting test results to narrow down root causes.
structured-code-review
Performs a structured five-stage code review covering requirements compliance, correctness, code quality, testing, and security/performance. Each stage uses targeted checklists and categorized feedback (Blocker/Major/Minor/Nit) with actionable suggestions and rationale. Use when the user asks for code review, PR feedback, pull request review, or wants their code checked for bugs, style issues, or vulnerabilities — triggered by phrases like "review my code", "check this PR", "review my changes", "pull request review", or "code feedback".