Debug

Skill mattjaikaran/meridian/skills/debug

Skill that gives AI coding agents persistent memory and quality enforcement

Install

npx -y skills add mattjaikaran/meridian --skill debug

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.3 KB, as published. Nobody here has run it

/meridian:debug — Systematic Debugging

4-phase systematic debugging with decision logging. Uses the protocol from references/discipline-protocols.md.

Arguments

<description> — Bug description or error message
--plan <id> — Associate with a specific plan
--phase <id> — Associate with a specific phase

Procedure

Phase 1: Investigation

Read the full error message and stack trace
Identify the exact file, line, and function
Check recent changes: git log --oneline -10 and git diff
Reproduce the error by running the failing test/command
Record findings

Phase 2: Pattern Recognition

Categorize the error type:
- Import/module error
- Type error / null reference
- Logic error / wrong behavior
- Race condition / timing
- Configuration / environment
- Data integrity
Search codebase for similar patterns
Check if this is a known issue pattern

Phase 3: Hypothesis

Form a specific hypothesis: "The error occurs because X"
Identify evidence that would confirm/refute
Test with minimal change
Record hypothesis and result as a decision:

PYTHONPATH=$MERIDIAN_HOME uv run --project $MERIDIAN_HOME -- python -c "
from scripts.db import connect, get_db_path
from scripts.state import create_decision
conn = connect(get_db_path('.'))
create_decision(conn, '<hypothesis and result>', category='approach',
    rationale='<evidence>', phase_id=<phase_id_or_None>)
conn.close()
"

Phase 4: Implementation

Fix at the source, not the symptom
Run the failing test — must pass now
Run full test suite — no regressions
Commit the fix with descriptive message

Escalation Rule

After 3 failed fix attempts:

STOP fixing
Record a deviation decision
Re-examine assumptions
Consider if the problem is architectural
May need to re-plan the current phase

PYTHONPATH=$MERIDIAN_HOME uv run --project $MERIDIAN_HOME -- python -c "
from scripts.db import connect, get_db_path
from scripts.state import create_decision
conn = connect(get_db_path('.'))
create_decision(conn, 'Escalation: 3+ failed fixes on <issue>. Likely architectural.',
    category='deviation', rationale='<what was tried>')
conn.close()
"

Output

Report:

Root cause identified
Fix applied (file:line)
Tests passing
Decision logged