$npx skillfedfor your agent

investigate

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.

Investigate provides a five-phase debugging workflow that prioritizes root-cause discovery before attempting any fix.

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

★ 374  29 MITupdated by blueberrycongee

Decision gist · record as of 2026-05-31

Investigate provides a five-phase debugging workflow that prioritizes root-cause discovery before attempting any fix. 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.

manual: git clone https://github.com/blueberrycongee/termcanvas → cp -r termcanvas/skills/skills/investigate ~/.claude/skills/investigate
skills/skills/investigate/SKILL.md · version 7d84702b

Use it when

  • Investigate's root cause analysis follows a disciplined sequence: gather concrete evidence about the failure.
  • Investigate guides you to investigate unexpected behavior by collecting evidence first, then forming ranked hypotheses about what caused it.

Verify before relying

Read SKILL.md below before installing (1 file). Open directory: indexed for reading, not audited.

Same gist for agents: .md · .json

Install

blueberrycongee/termcanvas/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 a bug systematically with Investigate?

Investigate teaches a five-phase debugging process: collect evidence first, form ranked hypotheses from that evidence, verify each hypothesis methodically, apply a minimal fix only after confirming root cause, then verify the fix resolves the issue. This structured approach prevents guess-and-fix cycles by enforcing evidence gathering before hypothesis formation and stopping endless speculation with a three-strike rule that forces re-collection of evidence.

What is the root cause analysis workflow in Investigate?

Investigate's root cause analysis follows a disciplined sequence: gather concrete evidence about the failure, rank multiple hypotheses by likelihood based on that evidence, test each hypothesis systematically rather than guessing, confirm which one is actually the root cause, and only then apply a minimal targeted fix. This methodology ensures you diagnose code issues properly instead of applying premature fixes to symptoms.

How does Investigate help me investigate unexpected behavior?

Investigate guides you to investigate unexpected behavior by collecting evidence first, then forming ranked hypotheses about what caused it. You verify each hypothesis methodically before moving to the next, avoiding the pitfall of skipping phases. The three-strike rule prevents endless speculation—after three failed hypotheses, you must re-collect evidence rather than continue guessing, ensuring you develop debugging discipline.

Can Investigate help me debug without guessing?

Yes. Investigate's structured debugging methodology eliminates guessing by enforcing an evidence-first approach. You collect concrete data about the failure, form ranked hypotheses from that evidence, then verify each one systematically. Only after confirming the actual root cause do you apply a fix. This prevents the common pitfall of skipping phases and teaches debugging discipline that avoids premature fixes and wasted troubleshooting.

What makes Investigate's debugging approach different?

Investigate enforces a five-phase process that separates evidence gathering from hypothesis formation, preventing guess-and-fix cycles. Its three-strike rule stops endless speculation by forcing re-collection of evidence after three failed hypotheses. By requiring verification before applying any fix, Investigate ensures you diagnose root cause properly and apply only minimal, targeted solutions—teaching debugging best practices that avoid common pitfalls.

How does Investigate verify a fix resolves the issue?

Investigate's final phase verifies resolution after you apply the minimal fix. This completes the five-phase workflow: evidence collection, hypothesis ranking, verification of root cause, minimal fix application, and confirmation that the fix actually resolves the original failure. This systematic approach ensures your debugging process is complete and the issue is truly resolved, not just masked.

SKILL.md

Rendered from the published skill. Quoted content, verbatim.

Investigate

Systematic debugging workflow. Do not guess-and-fix — find the root cause first.

Phase 1: Collect

Gather all available evidence before forming any hypothesis.

  1. Read the error message, stack trace, or symptom description exactly as given
  2. Identify the affected code path — read the relevant source files
  3. Check git log --oneline -20 in the affected area for recent changes
  4. If reproducible, reproduce the issue and capture the exact output
  5. List what you know and what you do not know

Deliverable: a structured symptom summary with affected files, error output, and recent changes.

Phase 2: Hypothesize

Form up to 3 ranked hypotheses. For each:

  • State the hypothesis in one sentence
  • Identify the single cheapest check that would confirm or refute it
  • Do NOT start fixing yet

Phase 3: Verify

Test hypotheses in rank order. For each:

  1. Run the cheapest check

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

File tree — 1 file
skills/skills/investigate/SKILL.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 › “Debug a bug or test failure using a structured, root-cause-first methodology”

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 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
qa
by blueberrycongee · blueberrycongee/termcanvas

QA skill uses real browser automation to test websites end-to-end, capturing visual evidence and validating user flows. It audits pages systematically, scores site health across console errors and interactivity, then fixes issues atomically with commit-per-fix discipline.

MITupdated May 2026
★ 374repo stars
code-review
by blueberrycongee · blueberrycongee/termcanvas

Code Review executes a systematic multi-phase examination of pull requests and code diffs, starting with scope and intent identification before conducting a critical pass for logic errors, injection vulnerabilities, and resource leaks. Specialist lenses then apply targeted checks based on change type—tests, data access, auth, or UI—with each finding assigned a confidence level to guide merge decisions.

MITupdated May 2026
★ 374repo stars
gstack-openclaw-investigate
by garrytan · garrytan/gstack

This skill enforces a disciplined debugging workflow: gather symptoms and code context, test hypotheses against known patterns, verify your theory before writing any fix, and document findings in a structured report. It prioritizes root cause discovery over quick patches, flagging when investigation stalls so you know when to escalate rather than guess.

MITupdated Jul 2026
★ 124,836repo stars
hydra
by blueberrycongee · blueberrycongee/termcanvas

Hydra is a Lead-driven orchestration toolkit that lets you coordinate multiple agents through structured workflows. The Lead makes strategic decisions while workers report semantic outcomes (done, needs_rework, replan) via a typed result contract, enabling parallel task execution with explicit decision points and intervention capabilities.

MITupdated May 2026
★ 374repo stars
investigate
by tobihagemann · tobihagemann/turbo

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.

MITfor claude-code, codexupdated Jul 2026
★ 377repo stars

More skills debug (Apache-2.0)

Tags
root-cause-analysishypothesis-driven-debuggingerror-diagnosissystematic-troubleshootingregression-testingevidence-collectioncode-investigationtest-failure-resolutionbug-reproduction