🐛
QualityTypeScript

Debugging Difficult Bugs

by crbnos

Debugging Difficult Bugs is a Quality skill for Claude Code, published by crbnos in carbon.

2.3K stars318 forkson crbnos/carbonAdded 2026/07/14+1% in starsRepository updated 2026/07/20
agentic-platformassemblylinebusinesserpleanmanagementmanufacturingmcp-servermespostgresqlqmsreact-routersupabasetypescript
Install in seconds
Install Debugging Difficult Bugs
Copy Debugging Difficult 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/crbnos/carbon/tree/main/.ai/skills/debugging-difficult-bugs ~/.claude/skills/debugging-difficult-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/crbnos/carbon.git

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

In this catalog

Source file
.ai/skills/debugging-difficult-bugs/SKILL.md in crbnos/carbon
Installs to
~/.claude/skills/debugging-difficult-bugs
Collection
One of 47 skills cataloged from this repository
Category
Quality1897 skills

What Debugging Difficult Bugs does

A systematic debugging approach: add temporary JSONL logging to the real code path, reproduce the bug, and analyze runtime events to find the exact point of divergence before fixing. Use when static analysis gives low confidence or the bug involves runtime state, ordering, concurrency, or manual reproduction.

Debugging Difficult Bugs is cataloged under Quality on DirSkills. Debugging Difficult Bugs comes from a repository tagged agentic-platform, assemblyline, business, erp and lean.

Documentation

README

debugging-difficult-bugs — instrument, reproduce, read, then fix

Core idea: when you can't see the failure by reading code, make the runtime tell you. Add temporary append-only JSONL logging along the real code path, reproduce the real issue once, read the log chronologically, and only then fix. Never make a second speculative fix without new runtime evidence.

Announce at start: "Using the debugging-difficult-bugs skill — instrumenting the runtime path to observe the failure."

Step 1: State the uncertainty

Write down: what you believe, what you can't verify statically, and the exact runtime path that must be observed (route → service → query, edge function, job).

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

Commands Debugging Difficult Bugs provides

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

  • /auth
  • /test
  • /fix

Frequently asked about Debugging Difficult Bugs

  • What else does crbnos publish alongside Debugging Difficult Bugs?

    Debugging Difficult Bugs is one of 47 skills that DirSkills catalogs from crbnos/carbon, the repository it ships in. Its siblings there include Agent Browser, Agent Browser and Browser Error Snapshot. Each one is a separate skill with its own page in this directory, installs the same way Debugging Difficult Bugs does, and is maintained by crbnos in that same repository. The rest of the collection is listed on the crbnos/carbon page.

  • How does Debugging Difficult Bugs compare to other Quality skills?

    Debugging Difficult Bugs ranks #522 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 Debugging Difficult Bugs against them. Open each page to compare what they document and how they install.

More from crbnos/carbon

Debugging Difficult Bugs is one of 47 skills cataloged on DirSkills from crbnos/carbon.

See all 47 skills
🌐
2026/07/20

Agent Browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task.
Automation
2.3K318
🌐
2026/07/21

Agent Browser

A browser automation CLI for AI agents to navigate websites, fill forms, click buttons, take screenshots, extract data, and automate browser tasks.
Automation
2.3K327
📸
2026/07/20

Browser Error Snapshot

Captures screenshot and element snapshot on browser errors during e2e testing, saving to gitignored .ai/scratch/e2e/. Invoke when 'Something went wrong', auth errors, blank pages, or unexpected redirects appear. A building block that captures and returns, leaving further action to the caller.
Quality
2.3K318
🧪
2026/08/12

Browser Feature Testing

Browser Feature Testing drives the running Carbon app through a specific user flow in a real browser to verify a feature or fix works end to end. It builds a plan from the diff or an issue, tests with agent-browser, and caches successful playbooks for reuse.
Quality
2.3K335
🐛
2026/07/20

Bug Fix Pipeline

Orchestrates the bug-fix lifecycle from root cause analysis to implementing and proving the fix with a mandatory red→green regression test. Use when fixing a bug, test failure, or unexpected behavior.
Quality
2.3K318
🔑
2026/07/20

Carbon Auth

Authenticate against a local Carbon ERP dev server using the DEV_BYPASS_EMAIL bypass with agent-browser. Used as a prerequisite for automated tests that require an authenticated session.
Automation
2.3K318