cosmosdb-agent-kit
AGENTS.md62 starsChanged 4 months agoMITView on GitHub
A collection of skills for AI coding agents working with Azure Cosmos DB. Skills are packaged instructions and scripts that extend agent capabilities. Skills are loaded on-demand — only the skill name and description are loaded at startup. The full SKILL.md loads into context only when the agent decides the skill is relevant. To minimize context usage: The build process compiles individual rule files into AGENTS.md: After creating or updating a skill: Document these installation methods for users: Claude Code:
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository2 other files it gives its agents.
- .github/copilot-instructions.mdCopilot instructions
- cosmosdb-best-practicesSkill
The file
We split this AGENTS.md into the rules it gives an agent
7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 29
SKILL.md: Always uppercase, always this exact filename
- Distinctive: line 30
AGENTS.md: Always uppercase, always this exact filename
- Distinctive: line 84
Ensure all rule files have valid frontmatter (title, impact, tags)
- Distinctive: line 85
Check that rule files use the correct prefix for their section
- Very specific: line 86
Verify metadata.json exists and has valid JSON
- Distinctive: line 90
After creating or updating a skill:
- Distinctive: line 99
Document these installation methods for users:
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
AGENTS.md
This file provides guidance to AI coding agents (Claude Code, Cursor, Copilot, etc.) when working with code in this repository.
Repository Overview
A collection of skills for AI coding agents working with Azure Cosmos DB. Skills are packaged instructions and scripts that extend agent capabilities.
Creating a New Skill
Directory Structure
skills/
{skill-name}/ # kebab-case directory name
SKILL.md # Required: skill definition
AGENTS.md # Required: compiled rules (generated)
metadata.json # Required: version and metadata
README.md # Required: documentation
rules/ # Required for rule-based skills
_sections.md # Section metadata
_template.md # Template for new rules
{prefix}-{name}.md # Individual rule filesNaming Conventions
- Skill directory:
kebab-case(e.g.,cosmosdb-best-practices) - SKILL.md: Always uppercase, always this exact filename
- AGENTS.md: Always uppercase, always this exact filename
- Rule files:
prefix-description.md(e.g.,model-embed-related.md)
SKILL.md Format
---
name: {skill-name}
description: {One sentence describing when to use this skill. Include trigger phrases.}
license: MIT
metadata:
author: cosmosdb-agent-kit
version: "1.0.0"
---
# {Skill Title}
{Brief description of what the skill does.}
## When to Apply
{List of scenarios when this skill should be used}
## Rule Categories by Priority
{Table showing categories and their impact levels}
## Quick Reference
{Organized list of all rules by category}Best Practices for Context Efficiency
Skills are loaded on-demand — only the skill name and description are loaded at startup. The full SKILL.md loads into context only when the agent decides the skill is relevant. To minimize context usage:
- Keep SKILL.md under 500 lines — put detailed reference material in AGENTS.md
- Write specific descriptions — helps the agent know exactly when to activate the skill
- Use progressive disclosure — reference supporting files that get read only when needed
Output
The build process compiles individual rule files into AGENTS.md:
npm run build
# or
node scripts/compile.jsTroubleshooting
Build Issues
- Ensure all rule files have valid frontmatter (title, impact, tags)
- Check that rule files use the correct prefix for their section
- Verify metadata.json exists and has valid JSON
Creating the Zip Package
After creating or updating a skill:
cd skills
zip -r cosmosdb-best-practices.zip cosmosdb-best-practices/End-User Installation
Document these installation methods for users:
Claude Code:
cp -r skills/cosmosdb-best-practices ~/.claude/skills/GitHub Copilot / VS Code:
cp -r skills/cosmosdb-best-practices ~/.copilot/skills/Using add-skill:
npx skills add AzureCosmosDB/cosmosdb-agent-kitDoes it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

