A structured thinking framework that walks Claude through ten stages of deliberate cognition, from external observation and metacognition through first-principles analysis, lateral connections, intuition, intellectual humility, and iterative growth. You'd invoke this when facing non-trivial decisions like architecture choices, post-mortems, or release-blocking audits where skipping uncomfortable steps like bias logging or verdict calibration leads to brittle output. The discipline scales with irreversibility: overkill for typo fixes, essential for ambiguous multi-stakeholder tradeoffs. Honest take: the anti-sycophancy guardrails in stages 8 and 10 are the real value here, forcing you to tier findings accurately and document what to improve next cycle instead of just claiming victory and moving on.
npx -y skills add agricidaniel/claude-obsidian --skill think --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
github/awesome-copilot
microsoft/win-dev-skills
github/awesome-copilot
github/awesome-copilot