skills.rest
sharad07072007
sharad07072007COMMUNITY
Explore all skills by this author →
GitHub

eve

Build and debug durable backend AI agents with the eve framework.

Updated Sep 10, 2026
Search Tags:#ai agents#vercel#agent debugging#eve#agent runs#backend agents#filesystem framework
One-click install
npx skills add https://github.com/sharad07072007/paras --skill eve-sharad07072007
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: eve
Source: https://github.com/sharad07072007/paras/tree/main/.agents/plugins/vercel/skills/eve/upstream
Command: npx skills add https://github.com/sharad07072007/paras --skill eve-sharad07072007

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires eve, vercel.

What problem does it solve? Building backend AI agents that persist state and run reliably requires coordinating instructions, tools, connections, channels, subagents, and schedules. This Skill guides you through creating, editing, and debugging eve agents using its filesystem-first framework and Vercel Agent Runs observability. ## Core Features & Use Cases - Filesystem-First Agent Development: Define agents as directories on disk containing instructions, skills, tools, connections, channels, subagents, and schedules that eve compiles and runs. - Runtime Observability: Inspect deployed agents through Vercel Agent Runs via the Vercel MCP server or CLI, accessing run metadata, lifecycle events, traces, tool calls, and token usage. - Version-Matched Documentation: Read bundled docs at node_modules/eve/docs/ that exactly match your installed eve version. - Use Case: You deployed an eve agent on Vercel and it behaves unexpectedly. Use this Skill to query Agent Runs for full traces showing turns, messages, reasoning, and tool input/output to diagnose the issue. ## Quick Start Ask the assistant to scaffold a new eve agent with npx eve init and then read the bundled documentation to add tools and a schedule.

Frequently Asked Questions about eve

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create a new eve agent project?▼

Run npx eve init <agent-name> to scaffold a new agent directory, or install eve with npm install eve in an existing project. Then read node_modules/eve/docs/README.md for the full documentation index and recommended reading order before writing code.

How do I debug a deployed eve agent on Vercel?▼

Use Vercel Agent Runs observability through the Vercel MCP server or the vercel agent-runs CLI command. These expose run metadata, lifecycle events, full traces with turns, messages, reasoning, tool calls, and token usage for your deployed agent.

What can an eve agent directory contain?▼

An eve agent is a directory on disk containing instructions, skills, tools, connections, channels, sandboxes, subagents, schedules, and evals, all defined as files. The eve framework compiles this directory and runs the agent.

Why is vercel agent-runs command not found?▼

The vercel agent-runs subcommand requires a recent Vercel CLI version. Check your version with vercel --version, then upgrade with npm i -g vercel@latest and verify availability with vercel agent-runs --help.

Where is the official eve framework documentation?▼

The complete documentation ships inside the eve npm package at node_modules/eve/docs/, matching your installed version exactly. Start with node_modules/eve/docs/README.md, which contains the full index and recommended reading order.

Related Skills

Explore More Software Engineering Skills→
openaiopenai
5.3k

eve

Build and debug durable AI agents with the eve filesystem-first framework.

Official
Intermediate
exerias21exerias21

eval-harness

Run pytest tests and pipeline simulations to verify feature behavior.

Community
Intermediate
liminal-ailiminal-ai
1

convex-performance-audit

Diagnose Convex app performance issues by identifying the strongest signal.

Official
Intermediate
Community-AccessCommunity-Access
387

scanner-bridge

Integrate GitHub Accessibility Scanner CI data with agent issue tracking and audit reporting.

Official
Advanced