count-dataset-tokens
OfficialCount tokens across datasets with exact tokenizers.
Authorletta-ai
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill guides counting tokens in datasets using specific tokenizers, including loading data, filtering by domain, and aggregating token counts.
Core Features & Use Cases
- Explore dataset structure and field values before counting
- Load and apply tokenizer to text fields
- Robust counting with edge-case handling and documentation of assumptions
Quick Start
Load a dataset, apply the tokenizer named in the task, and compute total tokens across the dataset.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: count-dataset-tokens Download link: https://github.com/letta-ai/skills/archive/main.zip#count-dataset-tokens Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.