All authors
Claude Skills by massimodeluisa
github.com/massimodeluisa3 skills0 installs4 views
- Recursive DecompositionBased on the Recursive Language Models (RLM) research by Zhang, Kraska, and Khattab (2025), this skill provides strategies for handling tasks that exceed comfortable context limits through programmatic decomposition and recursive self-invocation. Triggers on phrases like "analyze all files", "process this large document", "aggregate information from", "search across the codebase", or tasks involving 10+ files or 50k+ tokens.Votes: 0GitHub stars: 47
- Recursive DecompositionDecompose dense codebase-wide, multi-document, PDF, and aggregation work even when the input fits the context window, following Recursive Language Models (Zhang, Kraska, Khattab, 2025). Use when the user asks to analyse all files, a whole repo, all docs, large PDFs, or to aggregate or multi-hop across scattered sources. Skip one file, one function, a single needle, or a one-page PDF conversion. Triggers: long context, context rot, large codebase, many files, all files, big document, multi-doc...Votes: 0GitHub stars: 47
- Nerd FontsUse Nerd Fonts (nerdfonts) glyphs for icons in CLI output, TUIs, shell prompts, statuslines, editor and terminal configs, docs, and web pages. Pick a named glyph from the 10,995 on nerdfonts.com/cheat-sheet (nf-md-, nf-fa-, nf-dev-, nf-oct-, nf-cod-, nf-seti-, nf-pl-), verify the codepoint, and install a patched font from nerdfonts.com/font-downloads. Use when adding or fixing terminal or editor icons, tofu or empty boxes instead of icons, starship, powerlevel10k, oh-my-posh, tmux, lualine, n...Votes: 0GitHub stars: 2