skills.rest
raindrop-airaindrop-aiOfficial·4 Agent Skills Included

cli

Debug AI agents locally with live traces and replays

Streams every token, tool call, and decision from your AI agent into a local debugging UI in real time. Eliminates blind guessing when agents fail by letting Claude Code read traces, write evals, and fix broken code automatically. Replays production traces against your real agent code locally, so you can reproduce and fix issues without touching live systems.
1,068|63
↗
npx skills add raindrop-ai/cli --all -g -y
Available:

Tells the AI agent to install Workshop via the one-line installer for normal use, and only build from source when developing Workshop itself, with verification steps before submitting changes.

All Skills in This Repository (4)

Pure Emerald Level Indicators
📦 In Repo
raindrop-airaindrop-ai

raindrop-debug-traces

Analyze Raindrop Workshop traces to explain agent behavior and pinpoint issues.

Official
Intermediate
📦 In Repo
raindrop-airaindrop-ai

raindrop-instrument-agent

Wires Agent code to MonkeyLearn's API for automated text analysis and data extraction.

Official
Intermediate
📦 In Repo
raindrop-airaindrop-ai

raindrop-add-readonly-replay

Adds per-run readonly mode to replay production traces safely via HTTP /replay endpoint.

Official
Advanced
📦 In Repo
raindrop-airaindrop-ai

instrument-agent

Instrument AI agents with Raindrop SDK tracing and verify runs in Workshop.

Official
Advanced

Frequently Asked Questions

FAQPage Schema
How to install Raindrop Workshop?▼

Run `npx skills add raindrop-ai/cli --all -g -y` in your terminal to install all skills in this suite globally.

How to debug AI agents locally?▼

Workshop streams every token, tool call, and decision from your agent into a local UI as it happens, so you can see exactly where things go wrong.

Can Claude Code fix my agent automatically?▼

Yes. Claude Code reads your traces, writes evals against your codebase, fixes the failure, and re-runs until every assertion passes.

Which frameworks does Raindrop support?▼

It works with TypeScript, Python, Go, and Rust, plus SDKs like Vercel AI SDK, LangChain, OpenAI Agents, Claude Agent SDK, and coding agents like Claude Code, Cursor, and Codex.

Can I replay production traces locally?▼

Yes. The setup-agent-replay skill scaffolds a local replay server that re-runs a captured production trace against your real agent code without side effects.

Related Repositories in Software Engineering

View All in Software Engineering→
openclawopenclaw
388.4k

openclaw

Run a personal AI assistant across your devices and chat apps

Official📦 120 Skills
obraobra
280.0k

superpowers

Gives coding agents a disciplined workflow from idea to merged code

Community📦 15 Skills
facebookfacebook
248.4k

react

AI agent skills for building, testing, and porting React core

Official📦 14 Skills