token-efficiency
Token optimization strategies for cost-effective Claude Code usage across all projects.
- Use Opus for learning and deep codebase understanding, Sonnet (default) for development, debugging, and implementation tasks; typical pattern saves ~50% tokens
- Prefer bash commands over reading files for modifications: use
sed,cp,catinstead of Read/Edit/Write cycles, saving 90-95% on file operations - Filter before reading with
grep,head,tail, and check file metadata first; never read entire log files without filtering - Use quiet/minimal output modes by default; override only when user explicitly requests verbose output or full file contents
- Skills use progressive disclosure (~155 tokens for descriptions only); full content loads only when activated, so symlinking multiple skills is safe
Token Efficiency Expert
This skill provides token optimization strategies for cost-effective Claude Code usage across all projects. These guidelines help minimize token consumption while maintaining high-quality assistance.
Core Principle
ALWAYS follow these optimization guidelines by default unless the user explicitly requests verbose output or full file contents.
Default assumption: Users prefer efficient, cost-effective assistance.
Model Selection Strategy
Use the right model for the task to optimize cost and performance:
Opus - For Learning and Deep Understanding
More from delphine-l/claude_global
bioinformatics-fundamentals
Core bioinformatics concepts including SAM/BAM format, AGP genome assembly format, sequencing technologies (Hi-C, HiFi, Illumina), quality metrics, and common data processing patterns. Essential for debugging alignment, filtering, pairing issues, and AGP coordinate validation.
216folder-organization
Best practices for organizing project folders, file naming conventions, and directory structure standards for research and development projects
116obsidian
Integration with Obsidian vault for managing notes, tasks, and knowledge when working with Claude. Supports adding notes, creating tasks, and organizing project documentation. Updated with 2025-2026 best practices including MOCs, properties, practical organization patterns, and Obsidian CLI (1.12+).
71jupyter-notebook-analysis
Best practices for creating comprehensive Jupyter notebook data analyses with statistical rigor, outlier handling, and publication-quality visualizations. Includes Claude API image size helpers.
62managing-environments
Best practices for managing development environments including Python venv and conda. Always check environment status before installations and confirm with user before proceeding.
54claude-collaboration
Best practices for using Claude Code in team environments. Covers skill management, knowledge capture, version control, and collaborative workflows.
48