Individual skill

tokenizers

Understand and work with tokenizers — BPE, WordPiece, Unigram, special tokens, and the practical effects of tokenization on cost and quality. Use when token counts, chunking, or model inputs misbehave.

skills/tokenizers/SKILL.md

Read pinned source

Source commit faf37c0859ebf627bfcb5225e8057d088691e0ae

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: No
Repository scan complete: No
Skill scan complete: Yes
Observed behavior: Not checked yet
Last checked: Nov 8, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 56
Repository last updated: Oct 10, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

agent-skills Repository topic
ai-agents Repository topic
ai-agents-automation Repository topic
ai-skills Repository topic
awesome Repository topic
awesome-list Repository topic
chatgpt Repository topic
claude-skills Repository topic
meta-ai Repository topic
muse-ai Repository topic
engineering Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

SKILL.mdcore · 4,133 bytes

Read excerpt


# Tokenizers

Tokenizers turn text into the integer sequences models actually process. They're invisible until 
they cause problems: surprising costs, broken chunking, or corrupted inputs. Understanding them 
turns those mysteries into mechanics.

## Overview

Modern tokenizers learn subword vocabularies from data (BPE merges frequent pairs; WordPiece and 
Unigram have their own strategies), then split text into those pieces. Key consequences: token 
count ≠ word count (varies by language and content — code and non-English text tokenize less 
efficiently), special tokens mark boundaries and roles, and detokenization isn't always the exact 
inverse. Every model has its own tokenizer — using the wrong one corrupts inputs silently.