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 verif
[Description truncada. Veja o README completo no GitHub.]