skills.rest
ElliotJLT
ElliotJLTCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

dont-be-greedy

Estimate token costs for CSV, JSON, and TXT files before loading.

60|2|Updated Jan 21, 2026
Search Tags:#summarization#preview#chunking#CSV#data-loading#token-cost#estimate
One-click install
npx skills add https://github.com/ElliotJLT/Claude-Skill-Potions --skill dont-be-greedy
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: dont-be-greedy
Source: https://github.com/ElliotJLT/Claude-Skill-Potions/tree/main/skills/dont-be-greedy
Command: npx skills add https://github.com/ElliotJLT/Claude-Skill-Potions --skill dont-be-greedy

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This skill mitigates context overflow by measuring files before loading, chunking oversized data, and returning safe previews and summaries to keep downstream processes running smoothly.

Core Features & Use Cases

  • Size-aware loading: measure file size and tokens before loading.
  • Automatic chunking and per-chunk summarization for large files.
  • Quick inspection and safe previews to aid quick decisions.
  • Use Case: A data analyst receives a CSV or JSON dataset larger than the token limit and wants a compact summary plus representative snippets without overwhelming the model.

Quick Start

  1. Estimate token cost for a file: python scripts/estimate_size.py "<file_path>"
  2. Choose the action based on estimated tokens:
    • If < 10,000: perform quick inspection and load directly
    • If 10,000–30,000: perform quick inspection and consider filtering
    • If > 30,000: chunk the file and summarize each chunk
  3. Run the appropriate workflow:
    • For small files: python scripts/quick_inspect.py "<file_path>"
    • For large files: python scripts/chunker.py "<file_path>" && python scripts/summarize.py "<chunk_file>"
  4. Return a structured output including overall summary, safe preview, and next steps.

Frequently Asked Questions about dont-be-greedy

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I estimate token cost before loading a large CSV or JSON file?▼

Token cost estimation measures file size before loading to prevent context overflow. Run the size estimation script on your file path to get token count, then decide whether to load directly, filter, or chunk based on the result.

What's the best way to handle CSV files that are too large for my context window?▼

Chunking splits oversized data into manageable sections with per-chunk summarization. After estimating tokens, use the chunker script on files exceeding 30,000 tokens, then summarize each chunk to create a compact overview.

Can I get a quick preview of a large data file without loading the entire thing?▼

Quick inspection provides safe previews and representative snippets for fast decision-making. Run the quick inspect script on files under 10,000 tokens to view content samples without overwhelming your context.

How does automatic chunking and summarization work for data loading?▼

Automatic chunking divides large files into sections, summarizes each chunk independently, and returns structured output including an overall summary, safe preview, and next-step recommendations for downstream processes.

Does this work with formats other than CSV and JSON?▼

The skill handles CSV, JSON, TXT, and other large data files using the same size estimation and chunking workflow. Token cost estimation and conditional chunking apply uniformly across supported formats.

Related Skills

Explore More Data & Analytics Skills→
omicverseomicverse
32

gsea-enrichment-analysis

Run gene set enrichment analysis with dictionary-based gene sets from .txt, .gmt, or .json files.

Official
Advanced
Wesley1600Wesley1600

data-analysis

Analyze CSV, JSON, and Parquet datasets with exploratory analysis and visualizations.

Community
Advanced
ericwang915ericwang915
38

csv_analyzer

Analyze CSV and Excel files with pandas and openpyxl for statistics and structure.

Community
Intermediate
patricio0312revpatricio0312rev
5

embedding-pipeline-builder

Automate document embedding pipelines for semantic search.

Community
Advanced