mcpbeat

Markdown Token Optimizer

microsoft/markdown-token-optimizer

Analyzes markdown files for token efficiency. TRIGGERS: optimize markdown, reduce tokens, token count, token bloat, too many tokens, make concise, shrink file, file too large, optimize for AI, token efficiency, verbose markdown, reduce file size

2k tokens
context cost
the whole folder, loaded on every use
3
files
instructions only
0
copies elsewhere
how many repositories repackaged it
242
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository 
npx skills add https://github.com/microsoft/GitHub-Copilot-for-Azure --skill markdown-token-optimizer

What comes with it

6 381 bytes besides the instruction
references/ANTI-PATTERNS.md
references/OPTIMIZATION-PATTERNS.md

The instruction itself

5 sections, as written by the author

Markdown Token Optimizer

This skill analyzes markdown files and suggests optimizations to reduce token consumption while maintaining clarity.

When to Use

  • Optimize markdown files for token efficiency
  • Reduce SKILL.md file size or check for bloat
  • Make documentation more concise for AI consumption

Workflow

  • Count - Calculate tokens (~4 chars = 1 token), report totals
  • Scan - Find patterns: emojis, verbosity, duplication, large blocks
  • Suggest - Table with location, issue, fix, savings estimate
  • Summary - Current/potential/savings with top recommendations

See ANTI-PATTERNS.md for detection patterns and OPTIMIZATION-PATTERNS.md for techniques.

Rules

  • Suggest only (no auto-modification)
  • Preserve clarity in all optimizations
  • SKILL.md target: <500 tokens, references: <1000 tokens

References

  • OPTIMIZATION-PATTERNS.md - Optimization techniques
  • ANTI-PATTERNS.md - Token-wasting patterns

How to use it

Copy the folder

Take microsoft/markdown-token-optimizer from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.