Ten Claude Code skills for writing an ML paper, abstract to rebuttal. Recipes, axioms, and mechanical checklists reverse-engineered from pap...
#anthropic
1103 posts
A design system for documents — analytical reports, diagrams, charts, decks, and long-form specs as self-contained HTML. Five Claude Code sk...
Honesty-first full-stack product partner skill for Claude Code: verify against reality, hunt silent failures, audit coverage, build-vs-buy.
Open-source skills for Claude Code CLI and Claude Co-Work — including SVG-to-OmniGraffle conversion and practical AI automation workflows.
Plain-language mode for Claude Code. For non-developers who ship real products by vibe coding.
Five ready-made Claude Skills for students in disciplines that run on close reading, argument, and citation rather than code: law, political...
Claude Code skill that stops prompt-cache thrash: -88% token burn in image-heavy agent sessions, with an audit script that shows exactly whi...
Skills for Claude Code & claude.ai — token-efficiency: measured 30-50% shorter responses at 100% assertion pass rate, with always-on hooks a...
Distilled operating skills for daily-driver Claude models — few dense rules, executable gates over long prose.
Turn complex AI workflows into reusable Claude skills. Capture the lessons to a tagged journal that survives context resets, then crystalliz...
Skills that make your agent behave like a traditional mexican mom
Community binary patches for Claude Code CLI — unlock hard-coded limitations via Agent Skills