πŸ•΅οΈ
QualityShell

Diagnose Root

by danielvm-git

Diagnose Root is a Quality skill for Claude Code, published by danielvm-git in bigpowers.

173 stars14 forkson danielvm-git/bigpowersAdded 2026/09/07+8% in starsRepository updated 2026/09/06
ai-agentsautomationbmadclaude-codeclean-codecursor-rulesdevopsdocumentation-as-codegemini-cliproductivitysoftware-engineeringsolo-developerspec-driven-developmenttdd
Install in seconds
Install Diagnose Root
Copy Diagnose Root into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/danielvm-git/bigpowers/tree/main/skills/diagnose-root ~/.claude/skills/diagnose-root

Requires Node.js. Downloads this skill only β€” not the rest of the repository β€” into your Claude Code skills folder.

Without Node.js

git clone https://github.com/danielvm-git/bigpowers.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
skills/diagnose-root/SKILL.md in danielvm-git/bigpowers
Installs to
~/.claude/skills/diagnose-root
Collection
One of 23 skills cataloged from this repository
Category
Quality β€” 1817 skills

What Diagnose Root does

Diagnose Root runs a four-phase root cause analysis for confirmed bugs: reproduce, isolate, hypothesize, and verify. Use it when the cause is unclear and you need evidence before proposing a fix.

Diagnose Root is cataloged under Quality on DirSkills. Diagnose Root comes from a repository tagged ai-agents, automation, bmad, claude-code and clean-code.

Documentation

README

Diagnose Root

Boundary: Canonical, reusable 4-phase RCA engine. Invoked by investigate-bug (as step 2 of the end-to-end flow) and by fix-bug (when no bug file exists). Does not write the bug file β€” that is investigate-bug's responsibility.

Four phases β€” do not skip. Update the active specs/bugs/BUG-*.md file at each phase.

Phases

  1. Reproduce β€” minimal steps; record environment; capture logs.
  2. Isolate β€” narrow to module/function; binary-search commits or config.
  3. Hypothesize β€” list ranked hypotheses with falsification test each.
  4. Verify β€” run falsification; confirm single root cause; link to fix plan.

HARD GATE β€” Do not propose a fix until phase 4 confirms one root cause with evidence.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Diagnose Root

  • What else does danielvm-git publish alongside Diagnose Root?

    Diagnose Root is one of 23 skills that DirSkills catalogs from danielvm-git/bigpowers, the repository it ships in. Its siblings there include Align Grid, Assess Impact and Audit Code. Each one is a separate skill with its own page in this directory, installs the same way Diagnose Root does, and is maintained by danielvm-git in that same repository. The rest of the collection is listed on the danielvm-git/bigpowers page.

  • How does Diagnose Root compare to other Quality skills?

    Diagnose Root ranks #1730 by stars among the 1817 Quality skills in this catalog. The most-starred ones next to it are Benchmark, Benchmark Optimization Loop and API Design Patterns. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Diagnose Root against them. Open each page to compare what they document and how they install.

More from danielvm-git/bigpowers

Diagnose Root is one of 23 skills cataloged on DirSkills from danielvm-git/bigpowers.

See all 23 skills β†’
πŸ“
2h ago

Align Grid

Align Grid builds MΓΌller-Brockmann modular grid webpages with CSS-variable-driven columns, baseline rhythm, and optical alignment. Use it when you need a visible, load-bearing grid that can be toggled and verified with a Puppeteer harness.
Frontend
17314
πŸ”
2h ago

Assess Impact

Assess Impact analyzes the blast radius of a proposed change before code is written. It maps dependents, affected stories, and test coverage, then writes specs/IMPACT_LATEST.md.
Quality
17314
βœ…
2h ago

Audit Code

Audit Code runs a self-review checklist before requesting review or committing. It checks security, tests, types, conventions, and code quality, then produces pass/fail results.
Quality
17314
🧭
2h ago

Audit Plan

Audit Plan evaluates an incoming project plan against bigpowers principles and conventions, then records gaps and a READY or NOT READY verdict before build work starts. Use it when a new project arrives or before seeding conventions in an unfamiliar codebase.
AI Engineering
17314
πŸ—οΈ
2h ago

Build Epic

Build Epic orchestrates a nine-step build cycle for one epic, from threat modeling and planning through TDD, verification, audit, commit, and release. Use it to resume or run release work with state tracked in YAML files.
DevOps
17314
πŸ—‚οΈ
2h ago

Change Request

Change Request adds or reorders release requirements against specs/release-plan.yaml and epic capsules. Use it when a new requirement arrives mid-release or the plan needs reprioritization.
DevOps
17314