Summary
If you're building LLM apps and need to move beyond vibes-based testing, this gives you the Phoenix evaluation framework. It's refreshingly opinionated: error analysis before automation, code evaluators before LLM judges, binary pass/fail over fuzzy scoring. You get pre-built evaluators for common cases like RAG, tools to build custom ones in Python or TypeScript, and crucially, validation workflows to check your LLM judges against human labels (they recommend 80% true positive/negative rates minimum). The workflow guides are practical, from trace sampling through production guardrails. Worth noting it requires running a Phoenix server, so there's infrastructure to manage.
Install to Claude Code
npx -y skills add github/awesome-copilot --skill phoenix-evals --agent claude-codeInstalls into .claude/skills of the current project.
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
Connect Claude to +800M contacts, +150M companies. Find & Enrich leads in chat.
Try For Free →Files
SKILL.md
Select a file.
Featured
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →Connect Claude to +800M contacts, +150M companies. Find & Enrich leads in chat.
Try For Free →
