Markdown Token Optimizer
Microsoft built this to help you slim down markdown files that are eating too many tokens. It counts tokens (using the 4 chars per token estimate), scans for the usual culprits like emoji spam and repetitive blocks, then gives you a table of specific suggestions with estimated savings. Nothing gets changed automatically, you review and decide. The included anti-patterns and optimization technique references are handy if you're trying to keep SKILL.md files under 500 tokens. Honestly most useful when you've written something verbose and need to make it AI-friendly without losing the actual content.
- installs
- 1.1K
- GitHub stars
- 217
- last updated
- Jun 11, 2026
Install
$ npx -y skills add microsoft/github-copilot-for-azure --skill markdown-token-optimizer --agent claude-codeInstalls into .claude/skills of the current project.
Files
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
Sponsors
Details
- Repository
- github.com/microsoft/github-copilot-for-azure
- Categories
- Git & Pull Requests, AI & Agent Building, Cloud & Infrastructure
- First seen
- Apr 16, 2026
