Havuz

AtlasAgent - an auditable AI agent control plane: evidence-backed memory, governed tool runtime, checkpoint DAG recovery, and a 55-chapter e

A collection of Agent Skills by Cali Castle.

Codex-native, spec-driven AI Agent workflow with Claude Code compatibility, independent review, QA, fixes, and refactors.

Open-World Self-Evolution for LLM Agents — agents that build both their skills and their own verification signals from scratch, with no targ

The security-first skill manager for AI agents — every install runs a security scan. Manage skills & MCP servers across 90 agents. Zero-depe

Official Findings of EMNLP 2026 implementation of Corpus2Skill: compile a document corpus into a navigable skill hierarchy that LLM agents e

Typed React command-center components, live examples, and a portable coding-agent skill.

An open-source Agent Skill for problem framing and assumption testing across coding, debugging, architecture, scientific research, and produ

Self-evolving browser automation for Codex, Claude Code, and Cursor—learn reusable site knowledge and safely replay verified routines with a

TypeScript toolkit for Windows x64 native systems programming, memory manipulation, and process instrumentation.

为 DeepSeek Harness 提供电脑控制插件：新鲜 Accessibility 观测、过期状态拒绝、作用域权限与安全输入（目前支持macos）｜Accessibility-first macOS Computer Use bundle for DSH with fres

Offline cyber security agent for your apps and AI coding tools. Open R&D: measured in public, improved every release.

由 AI 自动完成 AutoDL 实例开关机的 Claude Code skill，含空闲自动关机、预算核对与用量记账

🖼️ AI agent skill for Claude Code & Codex — turns raw app screenshots into store-ready App Store & Google Play marketing images: device fram

The Wasp Nest: a plugin marketplace of AI coding agents, skills, and workflows for Claude Code, Codex, Cursor, ZCode, and Cowork, with PRDs,

Mini Program Engineering Skill Suite is an Agent Skill suite for evidence‑first mini‑program development. It helps agents bring WeChat or ot

让 Codex 少烧 Token、少造复杂度，同时不降智的代码约束 Skill

AI agent skill that generates beautifully typeset travel guidebook PDFs — from research to print, powered by parallel agents and Amap MCP.

Multi-workspace profile router, MCP server isolation auditor, and CLAUDE.md <-> AGENTS.md instruction bridge for Claude Code and OpenAI Code

humanizer, but for code — an agent skill that removes AI-generated code slop: duplicated helpers, try-import fallbacks, broad excepts, specu

Practical Agent Skills. Install with npx skills add.

Agents can work. They cannot declare success. A governed coordination protocol for multi-agent AI work: eight contracts (task, resource, own

Multi-harness control protocol that turns requests into approved design contracts, orchestrating isolated worker sessions for sequential imp

Durable single-Agent Harness for TypeScript: recoverable Threads, context continuity, explicit side effects, and a native TUI.

Production-ready AI agent profiles for Claude Code, Cursor, Codex, OpenClaw, and Hermes. Search, install, and contribute ForgeCat packages.

[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.

A product-validation system for AI agents: idea → logo → product → brand → launch video in two hours. Desktop app + skills for Claude Code a

中国法条与法律法规检索 Agent Skill｜Chinese legal research Agent Skill for retrieving and verifying Chinese laws from official sources｜支持具体法条检索、现行有效核验、1

交接 Skill（Jiaojie）：跨窗口、跨模型、跨设备、跨语言的 AI 上下文交接工具。换窗口，不失忆；换模型，不重来。Open-source AI context handoff.

Composable Agent Skills (Claude + OpenAI Codex) for taking an idea from fuzzy → validated → sequenced build → shipped — a manual tier (ideat

An agent skill to evolve the quality of LLM-Wiki (Graphify) at test time.

58 个跨境电商 · DTC 品牌出海 AI 技能库:Amazon 运营、SEO/GEO、广告归因、财务、联盟、红人、线下零售、VOC、众筹。事实均标来源与日期,内置证据闸——数据不足时说「数据不足」,而不是编一个数字。| 58 skills for cross-border e

Feature flags and A/B tests as Markdown files in your repo. dif build compiles them to a typed TypeScript client for Next.js, React, and Sve

SkillForge — AI Agent Skills Generator. A structured 4-step prompt system that forges production-grade Agent Skills from scratch.

Nuphus — 本地优先的 AI Agent：真实桌面执行力 + 手机第二块屏幕。Local-first AI agent with real desktop execution and dual-device real-time sync.

An agent skill that plays ARC-AGI-3. One rule: say what an action will do before you spend it. Claude Code on Opus 5 finished all 25 public

Know what to fix next — local .pm governance skill pack for AI coding agents (Spec Kit–inspired).

agent-marketplace is a command-line tool that installs shared AI agent resources into the AI coding tools you use

教 Claude Code/Codex 真正用好 gpt-image-2 的 skill 包 · Drop-in skill teaching agents to actually use GPT Image 2 — intent-first prompting, surgica

SoftSync for the agentic era

Open source list of roblox skills for AI agents

Método jurídico aberto e executável por agentes de IA: base curada de STF/STJ, legislação, súmulas, temas e teses; 10 protocolos e motores l

Don't make LLMs honest. Make every factual claim auditable. — An LLM Claim Auditing Layer with T1-T7 truth gradients. 98.1% business effecti

O Specsfy ajuda você a transformar uma ideia em software testado sem espalhar requisitos, planos e tarefas por vários arquivos.

The automated approach leverages the cross-combination of high-quality papers from top conferences to uncover feasible research and innovati

Claude Code skill: faceless 9:16 explainer reels in a cut-paper style. Voice-timed scenes, word-by-word captions. Free, local, no API keys.

mentor — a session-insights skill for AI coding agents. This skill reads your local Claude Code and OpenAI Codex history and writes an /insi

Design skills for coding agents.

241 evaluated academic Claude/agent skills across 18 research domains — bioinformatics, cheminformatics, data science, databases, clinical,