systematic-thinking
Rigorous problem decomposition and evidence-based analysis methodology for software engineering tasks. Use to analyze situations, figure out concepts or investigations.
Profile →npx skills add majiayu000/claude-skill-registry --skill systematic-thinking --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Systematic Thinking Systematic thinking is a structured methodology for decomposing complex problems and arriving at root causes through evidence-based reasoning. Use this skill for debugging, investigation, and any problem where the true cause is not immediately apparent. ## When to Use - Debugging issues where surface symptoms don't reveal the cause - Analyzing incidents or failures with multiple potential factors - Investigating why something isn't working as expected - Breaking down complex problems into actionable components - Any task where quick conclusions have led to incomplete fixes ## The 5 Phases 1. **Problem Decomposition** - Break the issue into discrete components. What exactly is failing? Where does it manifest? 2. **Evidence Gathering** - Collect data before forming conclusions. Logs, traces, reproduction steps, environment details. 3. **Hypothesis Formation** - Form specific, testable hypotheses. Not "something is wrong" but "X causes Y because Z." 4. **Testing & Verification** - Test hypotheses systematically. Verify assumptions. Reproduce the issue in isolation. 5. **Root Cause Focus** - Distinguish symptoms from causes. Keep asking "why" until you reach the f
- When to Use
- The 5 Phases
- Red Flags
- See Also
What does the systematic-thinking skill do?
Rigorous problem decomposition and evidence-based analysis methodology for software engineering tasks. Use to analyze situations, figure out concepts or investigations.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill systematic-thinking --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.