Ce Debug

A systematic debugging framework that won't let you skip to the fix before you understand the root cause. It enforces a discipline: reproduce, trace the code path, form predictions for uncertain links, test one hypothesis at a time. The causal chain gate is the heart of it: you can't propose a fix until you can explain the full chain from trigger to symptom with no gaps. Includes integrations for fetching GitHub issues, a fast path for trivial bugs, and specific guidance on when to ask questions versus investigate first. Built for the times when you're stuck after multiple failed attempts and need to stop guessing.

skills.sh installs: 3.6K
GitHub stars: 26K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add everyinc/compound-engineering-plugin --skill ce-debug --agent claude-code

Installs into .claude/skills of the current project.

Files

Debug and Fix

Find the root cause of a failure, then — when the user chooses to — fix it with test-first discipline.

Done when: the causal chain from trigger to symptom is stated with no gaps and file:line evidence, and either a verified fix has been handed off (PR, commit, or the user's chosen stop) or a diagnosis-only summary has been delivered. Escalate rather than persist: 2-3 hypotheses exhausted without confirmation, or 3 failed fix attempts, means diagnose why instead of trying again — that is the smart escalation references/investigate.md describes. One hypothesis, one change at a time; changing several to see what helps is shotgun debugging.

<bug_description> is whatever this skill was invoked with — a failure description, a mode: token, or an issue reference (#123, org/repo#123, an issue URL) — from the user or from a calling skill (ce-babysit-pr / lfg in mode:pipeline pass the failing jobs and log tails; lfg's defect route passes mode:return-to-caller and the user's own reference). Blank if nothing was provided.