faical-yannick-congo/fluently
Score, compare, and share human-AI collaboration patterns using the 4D framework community knowledge base, CLI, and MCP server
Platform-specific configuration:
{
"mcpServers": {
"fluently": {
"command": "npx",
"args": [
"-y",
"fluently"
]
}
}
}Add the config above to .claude/settings.json under the mcpServers key.
[](https://www.npmjs.com/package/fluently-cli) [](https://github.com/faical-yannick-congo/fluently/actions) [](LICENSE) [](https://github.com/faical-yannick-congo/fluently/stargazers)
---
AI is powerful—but not magic. Teams shipping with AI today face a hard truth: output quality depends entirely on clarity. You need to know *what to delegate*, *how to describe it*, *how to verify it works*, and *who's accountable*. That's the 4D Framework: Delegation, Description, Discernment, Diligence.
Fluently operationalizes the 4D Framework. It gives you a CLI, MCP server, and a growing knowledge base of best practices—built on Anthropic's AI Fluency research by Dakan & Feller. Score your team's AI workflows. Learn from the community's Fluently 4D cycles. Ship with confidence.
---
Real-world example: Compare your code review process against community best practices:
$ fluent compare --task "Automated code review with human sign-off"
┌─────────────────────────────────────────────────────────┐
│ TOP 3 SIMILAR FLUENTLY 4D CYCLES FROM KNOWLEDGE BASE │
├─────────────────────────────────────────────────────────┤
│ 1. Code Review: Review Depth vs. Speed Tradeoffs │
│ Delegation: 75 Description: 82 Discernment: 78 │
│ Diligence: 71 OVERALL: 76/100 │
│ │
│ 2. Bug Fix Prioritization Loading reviews...