eastreamsOfficial·34 Agent Skills Included

loong

Rust foundation for building secure, high-performance AI agents

Provides a Rust framework for building vertical AI agents with security, performance, and long-term maintainability built in. Authorizes sensitive agent actions before execution through a policy-based permission model instead of scattered runtime checks. Includes an actor runtime, tool hosting, context storage, and OpenAI provider integration so developers avoid wiring infrastructure from scratch.

641|104

↗

npx skills add eastreams/loong --all -g -y

All Skills in This Repository (34)

Pure Emerald Level Indicators

📦 In Repo

eastreams

agent-browser

Automate web page navigation, interaction, and data extraction via Chrome DevTools Protocol.

systematic-debugging

Identifies root causes of software bugs via a four-phase investigation.

plan

Generate a structured markdown execution plan in the .hermes/plans/ directory.

find-skills

Search the skills.sh ecosystem using the Skills CLI to find and install relevant skills.

design-md

Generate a semantic DESIGN.md file from Stitch project design assets.

skill-creator

Create, modify, and evaluate AI skills with Claude tools.

mcporter

Invoke MCP servers and tools from the command line with JSON output.

native-mcp

Connect to external MCP servers and expose their tools as native Hermes Agent capabilities.

github-issues

Create, triage, and manage GitHub issues via the gh CLI or REST API.

xlsx

Generate, edit, and validate Excel workbooks with formula error repair.

pdf

Extract text and structured data from PDF files using Python libraries.

pptx

Extract, edit, and repack .pptx slide decks with XML validation.

Official

Advanced

Frequently Asked Questions

FAQPage Schema

How to install Loong?▼

Run `npx skills add eastreams/loong --all -g -y` in your terminal to install all skills in this suite globally.

What is Loong used for?▼

Loong is a Rust foundation for building vertical AI agents that need strong security, predictable performance, and clean long-term architecture.

How does Loong keep AI agents safe?▼

It models outbound actions as typed capabilities and requires policy authorization before any sensitive operation executes, so unsafe actions are blocked by design.

Is Loong ready for production use?▼

Not yet. The repository is an early-stage architecture and contract skeleton, not a finished agent product you can deploy today.

Does Loong support OpenAI models?▼

Yes. It includes a dedicated OpenAI provider crate with streaming support, plus failover handling across providers.