Menu
Use when encountering a bug, test failure, or unexpected behavior and you need to find root cause before fixing
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Use when changing cogitation project settings (test/build/lint commands, branching conventions, graphify/codex toggles), or the user says "change config", "update settings", or "set test command"
Use when setting up a project for cogitation for the first time, or the user says "set up cogitation", "init", or "configure this project"
Use at the start of any conversation — establishes the cogitation workflow and requires invoking the right skill before responding, including before clarifying questions
Use for MEDIUM-sized work — new but contained behavior (one component, no architecture/data/API change) that deserves rigor without the design-doc + plan-doc ceremony of brainstorming
Use when the user wants to tailor the cogitation workflow — says "customise", "recustomise", "change the workflow", "make TDD less strict", "turn off finishing-branch", or wants a skill looser or disabled
Use when EC memories need cleanup — deduping, pruning stale entries, hygiene — or the user says "audit memories", "clean up EC", or "review what's stored"
| name | debugging |
| description | Use when encountering a bug, test failure, or unexpected behavior and you need to find root cause before fixing |
Find the root cause before attempting fixes.
Announce: "I'm using the debugging skill to investigate this issue."
NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST
Investigate → Analyze → Hypothesize → Fix
Before any fix attempt:
ec_search:
query: [error message or symptom]
ec_search:
query: [affected component]
type: learning
Check if we've seen this before. Prior solutions save time.
git log --oneline -10
git diff HEAD~5
What changed that could cause this?
Where does the bad value come from?
Look for similar working code:
Search EC for established patterns:
ec_search:
query: [pattern name]
type: pattern
What's different between working and broken?
State clearly: "I think X is the root cause because Y"
Test with the smallest possible change. One variable at a time.
If hypothesis wrong: Form new hypothesis. Don't pile fixes.
Reproduce the bug in a test first (RED).
Address the root cause, not the symptom (GREEN).
Load project config for commands:
ec_search:
query: project config
type: config
Run verification:
If root cause was non-obvious:
ec_add:
type: learning
area: [component]
content: [What was wrong, why it happened, how to recognize it]
rationale: Discovered while debugging [symptom]
Good learnings to store:
Stop and return to Phase 1 if:
Question the architecture:
Search EC for architectural decisions:
ec_search:
query: [component] architecture
type: decision
Discuss before attempting fix #4.