systematic-debugging
This skill implements a four-phase debugging methodology that prioritizes root cause identification over quick fixes. It guides users to first document the exact error and its conditions, then generate multiple hypotheses with supporting evidence, test each hypothesis with minimal changes, and finally implement a fix with verification and test coverage. Use this whenever troubleshooting errors to avoid applying incorrect solutions based on incomplete understanding.
git clone --depth 1 https://github.com/ArchieIndian/openclaw-superpowers /tmp/systematic-debugging && cp -r /tmp/systematic-debugging/skills/core/systematic-debugging ~/.claude/skills/systematic-debuggingSKILL.md
# Systematic Debugging Never guess at fixes. Find the root cause first. ## Phase 1: Understand the Error - Read the full error message - Note the exact file, line, error type - Reproduce the error reliably - Write: 'The error is: [exact error] at [location] when [trigger].' ## Phase 2: Hypothesize Generate at least 2 hypotheses. For each: what evidence supports it? What would disprove it? ## Phase 3: Test Hypotheses Test each hypothesis with the minimum change to confirm or deny it. - Add a log line, not a fix - Test one variable at a time ## Phase 4: Fix and Verify 1. Write the fix 2. Verify the original error is gone 3. Verify no new errors 4. Add a test that would have caught this bug
Syncs agent daily memory and MEMORY.md to an Obsidian vault so notes are human-browsable. Use nightly or on demand.
Structured ideation before any implementation. Use when starting any non-trivial task.
Scaffolds and validates new superpowers skills. Use when creating a new skill for this repository.
Executes plans task-by-task with verification. Use when implementing a plan.
Triggers a secondary verification pass for any agent output containing factual claims, numbers, dates, or named entities before the output is acted on
Crawls a new codebase to infer stack, conventions, and key invariants, then generates a PROJECT.md context file for the agent
Handles PR review feedback by fetching comments, grouping issues, fixing one group at a time, and verifying before replies.
Detects skill name shadowing and description-overlap conflicts that cause OpenClaw to trigger the wrong skill or silently ignore one when two skills compete for the same intent.