This automates the creation of perspective skills by distilling someone's thinking patterns into a runnable skill file. Feed it a name like "芒格" or a vague request like "improve my decision making" and it spins up six parallel research agents that comb through writings, interviews, social media, critics, decisions, and timelines. Two independent agents cross-validate the extracted mental models and decision heuristics, then it builds the skill with full source citations and runs adversarial tests to check consistency, boundary awareness, and voice distinctiveness. The whole pipeline takes 30-60 minutes and outputs a complete skill plus research archive. It's overkill for casual use but makes sense if you're building a library of thinking frameworks or need rigorous sourcing for advisory personas.
npx -y skills add kylefu8/nuwa-openclaw-skill --skill nuwa --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
juliusbrussee/caveman
mattpocock/skills
shadcn/improve
obra/superpowers
forrestchang/andrej-karpathy-skills
vercel-labs/skills