agentleFS
Sign inStart free
dbarkoldbarkol/fibey-agent/.github/skills/agent-dev/SKILL.md

Agent Developer

Skill0 starsChanged 6 months agoMITView on GitHub

Microsoft Agent Framework + Foundry Toolbox MCP integration specialist

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 1

    1. microsoft-foundry/build-2026-demos★ 11100% same

    Edited · 0

    None found.

    Wrote their own version · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository4 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use python-dotenv for environment configuration

    line 54
  2. Very specific:

    All Azure auth via DefaultAzureCredential

    line 55
  3. Very specific:

    Use asyncio and async/await throughout — the agent framework is async-first

    line 57

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Agent Developer Skill

You are a specialist in building and configuring the AI agent backend for this project.

Tech Stack

  • Python 3.11+
  • Microsoft Agent Framework 1.0
  • FastAPI + Uvicorn for the API gateway
  • Azure AI Foundry SDK (azure-ai-projects)
  • Azure Identity (DefaultAzureCredential)

Architecture

This project uses a single agent that connects to the Foundry Toolbox via one MCP endpoint. The Toolbox dispatches to individual tools (FoundryIQ, WorkIQ, custom MCP, FabricIQ) behind the scenes.

API Gateway → Single Agent → Toolbox (MCP endpoint) → Multiple Tools

Agent Modes

  • Local (AGENT_MODE=local): Agent runs in-process, connects to Toolbox MCP directly via MCPStdioTool or MCPStreamableHTTPTool
  • Hosted (AGENT_MODE=hosted): Agent deployed as container in Foundry Agent Service, Toolbox configured via Foundry project

Streaming Protocol

The gateway streams newline-delimited JSON events:

{"type": "message", "content": "chunk of text"}
{"type": "activity", "tool": "FoundryIQ", "status": "running", "detail": "Searching knowledge base..."}
{"type": "activity", "tool": "FoundryIQ", "status": "complete", "detail": "Found 3 results"}
{"type": "citation", "source": "doc-name", "url": "..."}

Activity events must surface individual tool names within the Toolbox, not just "Toolbox called".

File Organization

src/fibey/agent/
├── api_server.py     # FastAPI gateway
├── main.py           # Local-mode entrypoint
├── hosted.py         # Hosted-mode entrypoint
├── agent.py          # Agent definition + Toolbox MCP connection
└── prompts/
    └── system_prompt.md

Conventions

  • System prompts are stored as markdown in prompts/ and loaded at runtime
  • Use python-dotenv for environment configuration
  • All Azure auth via DefaultAzureCredential
  • Type hints on all function signatures
  • Use asyncio and async/await throughout — the agent framework is async-first

Download now (ZIP)

Does 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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free