investigate
Investigate guides you through structured debugging in five phases, from evidence collection to verified fix. It enforces the Iron Law principle—never fix without a confirmed root cause—using pattern analysis, hypothesis testing with a 3-strike escalation rule, and regression coverage. Output includes a machine-readable debug report with the full evidence chain.
Investigate enforces systematic debugging by collecting evidence and confirming root cause before applying any fix.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-06-18
Investigate enforces systematic debugging by collecting evidence and confirming root cause before applying any fix. Investigate guides you through structured debugging in five phases, from evidence collection to verified fix. It enforces the Iron Law principle—never fix without a confirmed root cause—using pattern analysis, hypothesis testing with a 3-strike escalation rule, and regression coverage. Output includes a machine-readable debug report with the full evidence chain.
Use it when
- Investigate uses hypothesis testing with a 3-strike escalation rule to isolate bugs.
- Investigate systematically extracts signals from logs and stack traces to map error scope and isolate the problem.
Verify before relying
Read SKILL.md below before installing (8 files). Open directory: indexed for reading, not audited.
Install
catlog22/Claude-Code-Workflow/investigate · repository language: TypeScript
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How do I debug my code systematically with Investigate?
Investigate guides you through five structured phases: evidence collection, pattern analysis, hypothesis testing, root cause confirmation, and verified fix implementation. The skill enforces the Iron Law—never fix without a confirmed root cause—by requiring you to gather logs, stack traces, and error patterns before proposing solutions. Each phase builds an evidence chain that feeds into a machine-readable debug report.
What is the root cause analysis process in Investigate?
Investigate uses hypothesis testing with a 3-strike escalation rule to isolate bugs. You collect error patterns across your codebase, trace them to their origin, and test minimal probes to validate each hypothesis. The skill prevents guessing by requiring structured validation at each step, ensuring you confirm the actual cause before implementing any fix.
How does Investigate help trace bug from logs and stack traces?
Investigate systematically extracts signals from logs and stack traces to map error scope and isolate the problem. It analyzes patterns across your codebase to assess how widespread the issue is, then guides you to the root cause through disciplined tracing. The output includes the full evidence chain so you can see exactly how the bug was located.
What does Investigate's debug report include?
Investigate generates a structured debug report with the complete evidence chain, confirmed root cause, and regression test coverage. The report is machine-readable, making it easy to share findings, track the investigation, and ensure your fix is validated before deployment. This enforces accountability and prevents fixes without proper justification.
Can Investigate help me debug production errors?
Yes. Investigate is designed for production error investigation by collecting evidence from live systems, tracing error patterns to assess scope, and confirming root cause before you deploy a fix. The structured methodology and regression test coverage reduce the risk of introducing new bugs while fixing the original issue.
Why does Investigate enforce the Iron Law principle?
Investigate enforces the Iron Law—never fix without a confirmed root cause—to prevent wasted effort and cascading failures. By requiring evidence collection, pattern analysis, and hypothesis validation before any fix, the skill ensures you address the actual problem, not symptoms. This disciplined approach saves time and improves code quality.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Investigate
Systematic debugging skill that enforces the Iron Law: never fix without a confirmed root cause. Produces a structured debug report with full evidence chain, minimal fix, and regression test.
Iron Law Principle
No fix without confirmed root cause. Every investigation follows a strict evidence chain: 1. Reproduce the bug with concrete evidence 2. Analyze patterns to assess scope 3. Form and test hypotheses (max 3 strikes) 4. Implement minimal fix ONLY after root cause is confirmed 5. Verify fix and generate structured report
Violation of the Iron Law (skipping to Phase 4 without Phase 3 confirmation) is prohibited.
Key Design Principles
- Evidence-First: Collect before theorizing. Logs, stack traces, and reproduction steps are mandatory inputs.
- Minimal Fix: Change only what is necessary. Refactoring is not debugging.
- 3-Strike Escalation: If 3 consecutive hypothesis tests fail, STOP and
(truncated - see the full file via the links below)
File tree — 8 files
.claude/skills/investigate/SKILL.md
.claude/skills/investigate/phases/01-root-cause-investigation.md
.claude/skills/investigate/phases/02-pattern-analysis.md
.claude/skills/investigate/phases/03-hypothesis-testing.md
.claude/skills/investigate/phases/04-implementation.md
.claude/skills/investigate/phases/05-verification-report.md
.claude/skills/investigate/specs/debug-report-format.md
.claude/skills/investigate/specs/iron-law.md
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Systematically investigate a bug by collecting evidence and confirming root cause before implementing a fix”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
team-frontend-debug orchestrates a multi-role team for frontend quality assurance, routing feature lists to a testing pipeline or bug reports to a debugging pipeline. Both flows leverage Chrome DevTools MCP for browser inspection, DOM analysis, console monitoring, and performance tracing. The coordinator role parses your input, spawns specialized workers (tester, reproducer, analyzer, fixer, verifier), and manages progress across phases.
Debugging Protocol teaches a disciplined four-phase investigation process that enforces root cause analysis before any code change. It prevents the common trap of jumping to fixes without understanding why problems exist, using the Iron Law (investigate first) and Three Strikes Rule (escalate after three failed attempts) to guide systematic problem-solving.
Investigate guides you through a disciplined five-phase debugging process: collect evidence, form ranked hypotheses, verify each one methodically, apply a minimal fix only after confirming root cause, then verify resolution. The workflow prevents guess-and-fix cycles by enforcing evidence gathering before hypothesis formation and a three-strike rule that forces re-collection rather than endless speculation.
CCW Chain orchestrates multi-step workflows by analyzing user intent, routing to the appropriate chain, and executing skill pipelines through progressive step loading. It supports auto mode for hands-off execution, delegation between chains, and variable propagation across the entire workflow.
Issue Management provides a menu-driven interface for tracking and organizing issues through the `ccw issue` CLI. Create, view, edit, delete, and bulk-update issues while filtering by status, priority, or other criteria—with automatic archiving of completed items.
CCW-Help is a command discovery and guidance system for Claude Code Workflow. It offers command search by name or category, smart next-step recommendations, contextual documentation, beginner onboarding, and browsing of workflow skills and team collaboration tools. The skill also handles issue reporting and auto-selects appropriate workflow levels based on task intent.
More skills investigate (MIT) · bug-hunt-swarm (MIT) · gstack-openclaw-investigate (MIT) · skill-generator (MIT) · Investigate (NOASSERTION) · Systematic Debugging (unlicensed)