113 boosters for "lib" — open source, verified from GitHub, ready to install
Structured approach to improving performance through focused effort, feedback, and continuous refinement. Based on psychologist K. Anders Ericsson's research on expertise acquisition.
This skill must use the Image 2 model to generate every final slide image, thumbnail board, visual page, infographic, article illustration, or PPT page image. HTML output is strictly forbidden for image generation. Do not create HTML/CSS pages, browser screenshots, SVG/HTML mockups, canvas renders,
vcspull is a VCS project synchronization tool using yaml/json manifests built on libvcs, designed for developers managing multiple repositories. It helps teams maintain consistent project configurations across different version control systems.
Frontmatter fields above are primarily for Claude Code / OpenClaw. author: Agents365-ai category: Content Creation
Empirica is a system prompt that adds epistemic measurement, RAG grounding, and calibration gates to AI agents to reduce hallucinations and improve reliability in code generation workflows. It's designed for developers building AI-native applications who need measurable confidence in agent outputs.
Before making changes in this repository, read and obey the rule files it routes you to.
Bilibili Mcp Js is an MCP server that enables AI models to search and retrieve Bilibili videos, anime, and trending content directly through Claude. Developers building AI applications can use this to integrate Chinese video platform functionality without manual API calls.
检测和改写中文 AI 生成文本的完整工具链。可独立运行（统一 CLI 或独立脚本），也可作为 LLM prompt 指南使用。 所有脚本在 目录下，纯 Python，无依赖。 v3.0 所有阈值都基于 HC3-Chinese 300+300 人类/AI 样本的 Cohen's d 校准：
This is github.com/unpoller/unifi/v5: a Go library that connects to a Ubiquiti UniFi controller and pulls data (clients, devices, sites, alarms, events, etc.). It does not update or change controller settings by design. Run and before committing. When adding features:
Please read and follow the instructions in AGENTS.md. All code MUST compile with Java 8. See AGENTS.md for forbidden features, build commands, code patterns, skills, and the task-solving workflow.
An MCP Server that integrates Alibaba Cloud DevOps API capabilities into AI assistants, enabling automated participation in development workflows and team collaboration optimization. Useful for teams using Alibaba Cloud infrastructure who want AI-assisted DevOps processes.
"name": "xiaohongshu-skills", "email": "xiaoluopupu@gmail.com" "description": "Complete Xiaohongshu (Little Red Book) operations skills library - 144 skills covering content creation, account management, community engagement, data analytics, e-commerce conversion, platform rules, tools ecosystem, ma
Bip is a CLI tool for managing academic references locally and searching papers via external APIs, designed for researchers and developers working with the bipartite reference library. It helps users efficiently organize and discover academic papers while prioritizing local search over external API calls.
专业的AI脚本和分镜生成系统，用于在Seedance 2.0平台上创建专业的AI视频系列。 以下是经过实测沉淀的通用规范，适用于所有 Seedance 2.0 / GPT-image-2 prompt 的生成。生成任何分镜 prompt 前必须逐条核对。 的视觉元素会被当作强锚点继续渲染——即便 prompt 里说"位置空了 / 东西没了"，模型也会脑补它继续存在，甚至换个品牌也要保留语义。要让某元素在续接段中真正消失，必须三重加固：
Heuristic scoring (no AI key configured).
Guides developers on calling Erlang code from Gleam, leveraging the BEAM ecosystem while maintaining type safety. Essential for Gleam developers integrating with Erlang libraries or NIFs.
Librarian is a local-first documentation CLI that indexes and retrieves docs using vector embeddings and SQLite, enabling developers to search and manage documentation offline with AI assistance.
An MCP server that integrates Open Library's vast book database into Claude, enabling AI assistants to search for books, retrieve author information, and access literary metadata. Useful for developers building book-focused AI applications, researchers, and anyone needing programmatic access to library data.
Litmus spawns multiple OpenClaw subagents that experiment on your GPU overnight. Each runs on its own git branch in a shared lab repository — every experiment is a commit, agents can read each other's code, cherry-pick breakthroughs, and build on the global best at any time.
If anything is unclear or you want this tailored to specific agent roles (refactoring, feature, doc-only), tell me which role and I'll iterate.
"description": "Mission Planner, Agent Creator, Skill Creator, and Librarian — the complete Forge suite for science-backed AI team assembly", "name": "jdforsythe", "url": "https://github.com/jdforsythe"
Production-grade geospatial workflows with an open-first stack and pragmatic hosted/SaaS choices when global scale, latency, SLA, or data quality makes local processing a poor fit. Cloud-native by default: STAC for discovery, GeoParquet + COG + PMTiles for storage, DuckDB and PostGIS for compute, Ma
During you interaction with the user, if you find anything reusable in this project (e.g. version of a library, model name), especially about a fix to a mistake you made or a correction you received, you should take note in the section in the file so you will not make the same mistake again. You s
This repository contains , a shared library used by the Microsoft Authentication Library (MSAL) for iOS and macOS. It contains internal classes and is not intended for public API consumption. To build and validate changes, use the provided Python build script. This script handles building the projec
