llm011 avatar

llm011

Official

@llm011

0Followers
|
5Public Repos
|
45Published Skills

A comprehensive suite of browser-based interaction, document management, and knowledge retrieval capabilities for enterprise productivity and research environments.

Skills Distribution
DomainDeveloper To...Browser Interactio.. (40%)Enterprise Documen.. (30%)System Integration.. (30%)

Agent Skills by llm011

Showing 45 vetted skills indexed across 1 GitHub repositories.

llm011llm011
9

agent-browser

Automates browser interactions for command-line web workflows.

Official
Advanced
llm011llm011
9

wechat-reading

Manage WeChat Reading books, shelves, notes, highlights, and statistics via API.

Official
Intermediate
llm011llm011
9

deepwiki

Retrieve structured documentation and wiki content from public GitHub repositories.

Official
Intermediate
llm011llm011
9

blogwatcher

Monitor RSS and Atom feeds to organize new articles.

Official
Intermediate
llm011llm011
9

eigenflux

Connect AI agents to the EigenFlux network for privacy-screened signal exchange.

Official
Advanced
llm011llm011
9

ui-card

Convert structured information into visually organized A2UI v0.9.1 UI cards.

Official
Intermediate
llm011llm011
9

travel-query

Queries official 12306 Chinese train and high-speed rail schedules, fares, and ticket availability by route, date, and station code.

Official
Intermediate
llm011llm011
9

didi-ride

Book rides from origin to destination via Feishu interactive cards.

Official
Advanced
llm011llm011
9

url-process

Route links to platform-specific extraction workflows for Markdown or summaries.

Official
Advanced
llm011llm011
9

flomo

Capture, search, organize, and delete flomo notes via browser automation.

Official
Advanced
llm011llm011
9

companion-listen

Provide empathetic listening and present-focused support during emotional conversations.

Official
Intermediate
llm011llm011
9

image-split

Split oversized images into readable segments using whitespace-aware boundaries.

Official
Basic
llm011llm011
9

jd-shopping

Search, extract, compare, and organize product and order data from JD web pages.

Official
Advanced
llm011llm011
9

gws-gmail

Manage Gmail messages and mailbox workflows through the gws command-line interface.

Official
Advanced
llm011llm011
9

task-strategy

Classify tool failures and route to safe fallbacks or user escalation.

Official
Advanced
llm011llm011
9

rss-briefing

Aggregate RSS articles into structured Chinese news briefings for Feishu.

Official
Advanced
llm011llm011
9

use-browser

Automate real Chrome tabs for authenticated web tasks and content extraction.

Official
Advanced
llm011llm011
9

nearby-search

Determines user location and searches Amap for nearby points of interest.

Official
Advanced
llm011llm011
9

code-review

Review code diffs and post prioritized inline comments on pull requests.

Official
Advanced
llm011llm011
9

feishu-writer

Create and format long-form Feishu documents with Mermaid diagrams.

Official
Advanced
llm011llm011
9

得到大脑(Get笔记)

Manage personal notes and knowledge retrieval through the Get笔记 API.

Official
Advanced
llm011llm011
9

excalidraw

Convert natural-language workflows and architectures into editable Excalidraw diagrams.

Official
Advanced
llm011llm011
9

lark-doc

Manage Feishu cloud documents by fetching, editing, and exporting Docx and Wiki content.

Official
Advanced
llm011llm011
9

paper-analysis

Analyze academic papers and transform PDF content into structured deep explanations.

Official
Advanced

Frequently Asked Questions About llm011

FAQPage Schema
What specific tasks can be performed using these browser-based capabilities?

These capabilities enable authenticated web navigation, content extraction from dynamic pages, and interaction with enterprise platforms like Feishu, JD, and Xiaohongshu. You can perform batch scraping, manage cloud documents, and execute complex web-based transactions through simulated browser sessions.

Which personas benefit most from these technical capabilities?

Software engineers, research analysts, and knowledge managers benefit most. These capabilities are designed for users requiring structured data retrieval from academic repositories, synchronization of personal note-taking systems, and management of enterprise messaging and task platforms.

What are the primary dependencies for running these browser and system-level functions?

Execution requires a local environment configured with Playwright for browser control and specific authentication credentials for target platforms like Feishu or S3-compatible storage. Users must ensure appropriate environment variables are set for secure resource access.