From pith
Delivers one-shot structured debug format (Problem/Cause/Fix/Verify) for diagnosing errors, unexpected behavior, crashes, or failures without prose.
How this skill is triggered — by the user, by Claude, or both
Slash command
/pith:pith-debugThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Debug format. Four fields. No prose. No preamble.
Debug format. Four fields. No prose. No preamble.
Problem: [what fails — one sentence, observable behavior not assumed cause] Cause: [exact location — file:line if known. The specific reason it fails.] Fix: [exact change — inline code, not a description of a change] Verify: [runnable command or test that confirms the fix worked]
[unknown — use verify step to investigate] — never speculate as fact.Bad:
The issue seems to be related to how the token validation is being handled in the middleware layer. You might want to look at the expiry check and make sure the units are correct...
Good:
Problem: JWT validation rejects valid tokens after ~1h
Cause: middleware/auth.js:42 — `token.exp < Date.now()` — exp is seconds, now is ms
Fix: `token.exp * 1000 < Date.now()`
Verify: curl -H "Authorization: Bearer $VALID_TOKEN" /api/me → 200
If multiple causes: number them. One Fix + Verify per cause.
Problem: login fails for new users
Cause 1: auth/register.js:18 — password hash missing await
Cause 2: db/users.js:44 — email uniqueness check case-sensitive
Fix 1: add await before bcrypt.hash(...)
Fix 2: change WHERE email = $1 to WHERE LOWER(email) = LOWER($1)
Verify: POST /api/register with new email → 201, then POST /api/login → 200
One-shot. Does not persist.
npx claudepluginhub abhisekjha/pith --plugin pithApplies systematic root-cause analysis to debug errors, test failures, and unexpected behavior across frontend, backend, database, network, and performance.
Debugs errors, test failures, and unexpected behavior via root cause analysis of logs, stack traces, recent changes, hypotheses testing, and strategic logging. Delivers fixes, verification steps, and prevention advice.
Guides systematic debugging for broken features, errors, failed deployments, or tests: reproduce bugs, gather git/logs diagnostics, read errors, diagnose root causes before fixes.