Diagnosing Bugs

by tt-a1i

Diagnosing Bugs is a Quality skill for Claude Code, published by tt-a1i in matt-skills-with-to-goal.

14 stars3 forkson tt-a1i/matt-skills-with-to-goalAdded 2026/07/16+17% in starsRepository updated 2026/07/16

View source on GitHub Download repo ZIP

agent-skillsai-agentsclaude-codecodexcoding-agentsdeveloper-toolsworkflow

Install in seconds

Install Diagnosing Bugs

Copy Diagnosing Bugs 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/tt-a1i/matt-skills-with-to-goal/tree/main/skills/diagnosing-bugs ~/.claude/skills/diagnosing-bugs

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

Without Node.js

git clone https://github.com/tt-a1i/matt-skills-with-to-goal.git

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

In this catalog

Source file: skills/diagnosing-bugs/SKILL.md in tt-a1i/matt-skills-with-to-goal
Installs to: ~/.claude/skills/diagnosing-bugs
Collection: One of 40 skills cataloged from this repository
Category: Quality — 1897 skills

What Diagnosing Bugs does

Guides systematic debugging of hard bugs and performance regressions through building a tight feedback loop, reproducing, minimizing, hypothesizing, and instrumenting. Use when encountering difficult or flaky bugs.

Diagnosing Bugs is cataloged under Quality on DirSkills. Diagnosing Bugs comes from a repository tagged agent-skills, ai-agents, claude-code, codex and coding-agents.

Documentation

README

Excerpt

Diagnosing Bugs

A discipline for hard bugs. Skip phases only when explicitly justified.

When exploring the codebase, read CONTEXT.md (if it exists) to get a clear mental model of the relevant modules, and check ADRs in the area you're touching.

Phase 1 — Build a feedback loop

This is the skill. Everything else is mechanical. If you have a tight pass/fail signal for the bug — one that goes red on this bug — you will find the cause; bisection, hypothesis-testing, and instrumentation all just consume it. If you don't have one, no amount of staring at code will save you.

Spend disproportionate effort here. Be aggressive. Be creative. Refuse to give up.

Ways to construct one — try them in roughly this order

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

Commands Diagnosing Bugs provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

/improve-codebase-architecture

Frequently asked about Diagnosing Bugs

What else does tt-a1i publish alongside Diagnosing Bugs?
Diagnosing Bugs is one of 40 skills that DirSkills catalogs from tt-a1i/matt-skills-with-to-goal, the repository it ships in. Its siblings there include Agent Handoff, Ask Matt and Ask Matt. Each one is a separate skill with its own page in this directory, installs the same way Diagnosing Bugs does, and is maintained by tt-a1i in that same repository. The rest of the collection is listed on the tt-a1i/matt-skills-with-to-goal page.
How does Diagnosing Bugs compare to other Quality skills?
Diagnosing Bugs ranks #1885 by stars among the 1897 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 Diagnosing Bugs against them. Open each page to compare what they document and how they install.