workflowstacks
claude-skill

Phoenix: Real‑time AI Observability for Smarter Startup Ops

Track, evaluate, and refine your LLM pipelines with Phoenix’s Python‑based monitoring suite—ideal for founders building AI‑first products. 12k+ GitHub stars.

From the repo · “AI Observability & Evaluation”

11,942 stars+102★ this week1,231 forksPythonGuide quality 8/10 · reviewed Oct 8Install verified Sep 28Updated 10/22/2026100% free · open source
What it does

Phoenix provides AI observability and evaluation to help startup founders monitor and improve the performance of their machine learning models

When to use it
  • •When you need to troubleshoot issues with your ML model's performance
  • •When you want to compare the performance of different ML models
  • •When you need to audit your ML model's data and performance metrics
Ready-to-paste prompt
phoenix run --model my_model --data my_data.csv --metrics accuracy,f1_score
Heads up: Make sure you have the necessary dependencies installed, including `pytorch` and `tensorflow`, and that you have a valid API key for Arize AI if you plan to use the tool's cloud features
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

⚡ Runs out of the box✓ Install verified 9/28/2026

A prompt/skill package — nothing to install beyond adding it to your AI tool.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/phoenix && curl -fsSL https://workflowstacks.com/api/skills/phoenix/claude-skill -o ~/.claude/skills/phoenix/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How Phoenix: Real‑time AI Observability for Smarter Startup Ops works
Codeflow
Free to inspect

Phoenix: Real‑time AI Observability for Smarter Startup Ops is a very large Python project (~663k lines across 4354 code files, plus 995 test files). Setup is light: installs like a normal app. Reading the code is optional. Last commit this month, Other license, has a test suite.

Size
Very large codebase
~663k lines · 4354 code files · days to read — use, don't read
Setup
One-command install
Installs like a normal app. Reading the code is optional.
Runs on
Python · Docker
No API keys detected
Python 48%TypeScript 41%Jupyter Notebook 10%C 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    pyproject.toml
    Dependencies and the commands it exposes
  4. 4
    src/phoenix/__init__.py
    Inside src/ — the main logic begins here
  5. 5
    examples/README.md
    A worked example — copy this to get going
What's in each folder
src/Core code — the actual logic711 files
prompts/Prompts, skills & agent definitions14 files
packages/Sub-packages / plugins377 files
docs/Documentation791 files
examples/Examples you can copy133 files
tutorials/Examples you can copy116 files
js/Folder3853 files
scripts/Helper scripts321 files
READMEHas testsDocumentedCI checksDocker readyExamples includedOther licenseUpdated this month
Quick Actions
Details
Creator
Arize-ai
Language
Python
Category
claude-skill
Published
11/9/2022

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/phoenix.svg)](https://workflowstacks.com/skills/phoenix?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.

MCP config

GitHub MCP config

Search repos, read code, open issues and PRs from Claude.

MCP config

Context7 (live docs) MCP config

Pull up-to-date library docs into Claude so it codes against the real API.

MCP config

Playwright (browser) MCP config

Drive a real browser for testing and automation from Claude.

Related skills

More claude-skill tools founders pair with this one.

claude-skill★ 256,115
Hermes-Agent: AI Growth
Scale with a versatile AI agent. For startup founders using Python and AI.
claude-skill★ 187,700
AutoGPT: Build Autonomous AI Agents Faster
AutoGPT lets founders launch self‑directing AI agents without deep ML work, so you can concentrate on product and growth. Ideal for Python‑savvy teams. 188k+ GitHub stars
claude-skill★ 148,278
langchain
The agent engineering platform.
claude-skill★ 305
DictateKeyboard: Turn Speech into Accurate Text on Android
Leverage Whisper AI in a Kotlin keyboard to capture flawless transcriptions, perfect for founders needing hands‑free note‑taking on the go.
claude-skill★ 1,978
Agent-Shell: AI in Emacs
Interact with LLM agents in Emacs with Agent-Shell, built for founders, with 1.6k+ GitHub stars.
claude-skill★ 5,215
Claude-BugHunter
A Claude Code skill bundle for bug hunting and external red-team work - 82 skills, 15 slash commands, 681 disclosed-report patterns curated across 24 core vulnerability classes, plus enterprise identity + infrastructure attack matrices.