large-doc-masterylisted

Large document and codebase synthesis skill. Activates when the user provides 50k–200k+ tokens of context — codebases, PDFs, legal documents, transcripts, research corpora — and needs synthesis, cross-referencing, or insight extraction with perfect recall across the entire context. Not a summarizer. A precision instrument for finding patterns, contradictions, dependencies, and insights that only emerge when you hold the whole thing at once. Use when user says: analyze this codebase, read this whole document, find all references to X, synthesize across sections, what does this say about Y, find contradictions, extract all decisions, map the dependencies, read the whole thing, cross-reference, audit the entire document, what changed between sections, find every mention of, trace this through the code, what's missing. Do NOT activate for: small documents where a direct answer is more useful, tasks that don't require cross-document reasoning. First response: "Large Document Mode active. Paste or attach your docum
Sandeeprdy1729/claude-design-skill · ★ 2 · Data & Documents · score 69

Install: claude install-skill Sandeeprdy1729/claude-design-skill

# Large Document / Codebase Mastery Summaries lose information. "Analyze this 80k-token codebase" with no structure produces a vague paragraph about architecture that misses the three critical bugs and the two deprecated modules that half the new code still imports. The skill is not consuming large context — Claude does that automatically. The skill is structuring the task so the synthesis is precise: specific questions, specific output formats, explicit cross-reference instructions, and verification passes that confirm the model used the actual document rather than its priors. --- ## SLASH COMMANDS | Command | Action | | --- | --- | | `/map` | Build a structural map of the document (sections, components, entities) | | `/index <topic>` | Find every location in the document that touches a specific topic | | `/extract <type>` | Extract all instances of a type: decisions, risks, assumptions, TODOs, etc. | | `/cross-ref <a> <b>` | Find all connections between two topics, sections, or entities | | `/contradictions` | Surface any internal contradictions or inconsistencies in the document | | `/gaps` | Identify what's absent — what the document should address but doesn't | | `/trace <entity>` | Follow an entity (function, concept, person, requirement) through the full document | | `/timeline` | Extract a chronological sequence of events, changes, or decisions | | `/compare <section-a> <section-b>` | Directly compare two sections or files | | `/synthesize <question>` | Answer a