$npx skillfedfor your agent

investigate

Investigate walks you through a structured methodology to pinpoint what's causing bugs, test failures, build errors, and unexpected behavior. It cycles through characterization, isolation, hypothesis generation, and targeted testing—with escalation to deeper analysis when needed—to diagnose the root cause without applying fixes.

Investigate helps you find the root cause of bugs and test failures using a systematic four-step methodology.

AI-generated summary based on this skill's SKILL.md

★ 377  29 MITupdated by tobihagemann

Decision gist · record as of 2026-07-27

Investigate helps you find the root cause of bugs and test failures using a systematic four-step methodology. Investigate walks you through a structured methodology to pinpoint what's causing bugs, test failures, build errors, and unexpected behavior. It cycles through characterization, isolation, hypothesis generation, and targeted testing—with escalation to deeper analysis when needed—to diagnose the root cause without applying fixes.

manual: git clone https://github.com/tobihagemann/turbo → cp -r turbo/claude/skills/investigate ~/.claude/skills/investigate
claude/skills/investigate/SKILL.md · version 4abda837

Use it when

  • Investigate helps you find the answer by systematically debugging and diagnosing unexpected behavior.
  • Investigate uses a cyclic methodology: first characterize what's broken and how it fails.

Verify before relying

Read SKILL.md below before installing (2 files). Open directory: indexed for reading, not audited.

Same gist for agents: .md · .json

Install

tobihagemann/turbo/investigate · repository language: Shell

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

What does Investigate help me do?

Investigate walks you through a structured methodology to pinpoint what's causing bugs, test failures, build errors, and unexpected behavior. It cycles through characterization, isolation, hypothesis generation, and targeted testing—with escalation to deeper analysis when needed—to diagnose the root cause without applying fixes.

Why is my test failing?

Investigate helps you find the answer by systematically debugging and diagnosing unexpected behavior. The skill guides you through isolating the failure, characterizing its symptoms, generating hypotheses about the cause, and running targeted tests to confirm which one is correct—all before you attempt any fix.

How does Investigate help find the root cause of an error?

Investigate uses a cyclic methodology: first characterize what's broken and how it fails, then isolate which component or code path is responsible, form hypotheses about why it's happening, and test each hypothesis systematically. When standard approaches don't work, Investigate escalates to deeper analysis techniques.

Can Investigate troubleshoot intermittent or hard-to-reproduce failures?

Yes. Investigate is designed to handle intermittent and hard-to-reproduce failures by helping you systematically narrow down conditions, timing, and dependencies. It guides you through isolation and hypothesis testing to characterize the failure pattern and identify what triggers it.

Does Investigate investigate performance issues?

Investigate can help diagnose performance issues and slow responses by applying the same structured methodology: characterizing the slowness, isolating which component is the bottleneck, forming hypotheses about the cause, and testing them to confirm the root cause.

What is Investigate's license?

Investigate is licensed under the MIT license, which permits free use, modification, and distribution with minimal restrictions.

SKILL.md

Rendered from the published skill. Quoted content, verbatim.

Investigate

Systematic methodology for finding the root cause of bugs, failures, and unexpected behavior. Cycle through characterize-isolate-hypothesize-test steps, with oracle escalation for hard problems. Diagnose the root cause — do not apply fixes.

Optional: $ARGUMENTS contains the problem description or error message.

Step 1: Characterize

Gather the symptom and establish what is actually happening:

  1. Collect evidence — error message, stack trace, test output, log entries, or user description of unexpected behavior
  2. Classify the problem type:
Signal Type
Stack trace / exception Runtime error
Test assertion

(truncated - see the full file via the links below)

File tree — 2 files
claude/skills/investigate/SKILL.md
claude/skills/investigate/references/problem-type-playbooks.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 › “Find the root cause of a bug or test failure”

Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →

Related skills

Investigate
by dcouple · dcouple/Pane

Investigate walks you through structured bug diagnosis, starting with hypothesis generation and moving through code inspection, data flow tracing, and controlled experiments to isolate the root cause. It focuses on finding and explaining problems rather than fixing them, and escalates to diagnostic logging only when code inspection alone cannot pinpoint the issue.

no license declared → metadata onlyfor claude-code, codexupdated Jul 2026
★ 332repo stars
debug-investigator
by Mathews-Tom · Mathews-Tom/armory

Debug Investigator replaces ad-hoc troubleshooting with structured investigation: capture symptoms, build a reproducible feedback loop, analyze evidence from stacktraces and logs, generate ranked hypotheses, and design bisection strategies. Use it for non-obvious bugs—intermittent failures, performance regressions, or issues requiring systematic root cause analysis—where native debugging falls short.

MITupdated Jul 2026
★ 274repo stars
parallel-debugging
by wshobson · wshobson/agents

Parallel Debugging applies the Analysis of Competing Hypotheses methodology to organize multi-agent investigation of complex issues. It structures hypothesis generation across six failure mode categories, establishes evidence collection standards with citation requirements, and provides arbitration protocols to identify root causes while avoiding confirmation bias.

MITupdated Jul 2026
★ 38,308repo stars
investigate
by blueberrycongee · blueberrycongee/termcanvas

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.

MITupdated May 2026
★ 374repo stars
investigate
by catlog22 · catlog22/Claude-Code-Workflow

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.

MITfor claude-codeupdated Jun 2026
★ 2,142repo stars
Debugging Protocol
by jwilger · jwilger/agent-skills

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.

CC0-1.0updated Jul 2026
★ 1repo stars

More skills bug-hunt-swarm (MIT) · systematic-debugging (MIT)

Tags
root-cause-analysissystematic-debuggingfailure-diagnosishypothesis-drivenproblem-isolationerror-characterizationtroubleshooting-workflowevidence-gatheringdefect-investigation