Havuz

Build production-ready AI agents in Claude Code from natural language. Analyzes your problem, researches best practices, and generates subag

开源 · 本地优先的 AI 智能体：编程与实干兼备。 自带模型密钥，内置 MCP、技能、插件、工作流、知识库以及数据库。

One command to cut token usage by up to 50%+

Agent skill for repository-aware social preview images, visual directions, and GitHub-ready exports.

Atomic SAP ADT CLI and scenario-driven AI skills for ABAP code and business logic analysis, source read/write, Unit/Dump diagnostics, experi

这是一个社会化能力训练Skill，同时是一本精简版的社会化指南。以《乌合之众》《关键对话》《人情世故大全》三本经典为理论根基，便于大家能够更好的进行社会化能力的训练提升。

Agent-ready toolkit for isometric games: ComfyUI art pipelines, seamless terrain, sprites, grid math, Canvas2D rendering, pathfinding, and a

A automatic dev agent from idea → spec → design → plan → build → test → review → ship and included many roly and responsibility. Add many fe

Meet PixelLab Pip: a tiny pup who fetches the right PixelLab workflow. He follows human commands to create, edit, and animate pixel assets,

Очеловечить текст нейросети: убирает длинное тире, канцелярит и штампы ChatGPT, не трогая факты. Правила для любой нейросети + скилл для Cla

AI job-search coach for Berlin and the rest of Germany: find jobs, check German/visa/salary requirements, write a Lebenslauf or CV, practise

Build, debug, profile, test, refactor, and release Swift apps across iOS, macOS, Xcode, SwiftUI, SwiftPM, Tuist, and App Store Connect.

Static reproducibility checks, experiment replay, and verification for ML pipelines.

Design engineering for AI agents: a skill graph, 13 agents that loop (with a cross-model design council and a grader), example taste forks,

Create production-ready skills and agents for OpenClaw. 4-level memory, auto-improvement, 22 battle-tested pitfalls.

Personal AI agent skills for Claude Code, Copilot, Codex, Gemini & Cursor — turn a PR or idea into marketing content, technical Slidev prese

Open-source self-hosted web tool for evaluating Agent Skills with rubric scores, Deep Review, and improvement suggestions.

The animated diagram editor AI agents can draw on. Animated technical diagrams (architecture, sequence, BPMN, cloud icons) built by you and

One character image → a full pack of animated chat stickers (WeChat / Telegram / LINE / Discord). Claude Code & Codex skill · 给 AI 一张图，做一整套会

Skills that stop AI agents from writing backend code that passes the demo and breaks in production. Critical mistakes: 25/150 runs without,

Installable Codex skills for goal-setting and marketing operator work.

The definitive open-source agent skills library for AI-powered Google Ads management. 73+ skills across 10 categories. Built for googleadsag

Find repeated manual work in activity records. Get automation proposals with source evidence, work counts, and owner review. An n8n labs exp

An agent skill for finding papers worth reading—trace research lineages, map evidence networks, and weigh supporting and conflicting finding

Perhaps the only agent skill you need: if memory loss is the root, let every AI agent rebirth follow the First-Time Principle. That's all.

One engineering workflow for Claude Code, Codex, Droid, Pi and OpenCode, with a validator that refuses a record without its evidence. Alpha,

23 practical agent skills: TeamWorkflow, multi-model review, media ingestion, and writing. Original Claude Code packages plus a Codex deskto

YouTube transcript Agent Skill for Claude Code, Cursor, Codex and OpenClaw: fetch YouTube video transcripts, search videos, browse channels

Paid APIs and supported tokenized shares for agents, funded with prepaid balance. Instinct Checkout guidance: https://vaaya.ai/llms.txt

Your own design studio inside the coding agent you already use.

Open benchmark for Claude Code SEO skills — real headless execution against fixture sites with planted-defect answer keys. Deterministic sco

Toolbox panel for DeepSeek Harness Web: MCP manager (tools & JSON Schema, market, import, workspace copy) and skills manager (scopes & shado

Google Ads Agent Skills for Claude — campaign analysis, account auditing, safe write ops, PPC math, and MCP server integration

Write, validate, and review Agent SKILL.md's directly in Visual Studio Code. SKILL.md Inspector provides live diagnostics for every file na

A framework for discovering, compiling, and validating reusable skills for scientific agents.

Claude Design access and UI workflows for coding agents, part of QualityLayer. Create and review designs in QualityLayer without a Claude su

Measured Agent Skills for geospatial AI — 18 skills that stop when the data cannot support the claim. Routing benchmark, held-out split, and

中文变现决策 Skill：在你继续开发、发内容或追加投入之前，先判断这件事是否接近收入。Chinese monetization decision skill for Claude Code — finds the one revenue point closest to rea

Let Claude Code, Codex, OpenCode, Pi and other agents run DeepSeek Harness (dsh) sessions in parallel: research batches, material gathering,

oo is OOMOL's CLI toolkit. Everything can be done in the CLI.

The lazygit for AI coding agents: skills, sessions, usage, providers and hooks for Claude Code, Codex, Gemini CLI, OpenCode, Pi, Crush and H

Official Sent plugin to send SMS, WhatsApp, RCS. Create and manage Sender Profiles, SMS compliance, contacts, analytics. Build and configure

十三希诺 Agent 工作流 · 中文源库：把工程纪律做成可机检门禁的元工作流 Skill 家族——三级跑道／判级／GATE 12 字段可复跑证据／405 条细则库／五包交付（核心+流程+角色+产品工程+单文件蒸馏），五平台注入适配。docs/ 为开发工作区，实验数据已归档。En

Skill librarian MCP server — every installed skill costs tokens; the librarian keeps your whole collection out of agent context. Agents ask,

Control the hinge angle of iPhone Duo Simulator from the CLI or AI agents

并发调用本机 Grok 4.5、Kimi K3 与 Claude Code，带实时心跳和独立日志 | Concurrent local model CLI orchestration with live progress and isolated logs.

端到端 QA 验收编排器 · Agent Skill：上下文 → 风险 → 用例 → 脚本 → 执行 → 审查 → 报告，全程自动衔接，只在用例确认时停下等你审核。支持 Claude Code / Codex / Cursor

Production-grade AI agent skills for React 19, Next.js 16, TypeScript 7, testing, data, UI, and frontend architecture—ready for Codex, Claud

一条命令跑完国内求职：猎聘 BOSS 智联前程一起搜，学历、户口、外包这些硬性条件先筛掉陪跑岗，打招呼话术和中文简历都备好，你只管点发送。数据不出本机，Claude Code、Codex、Qoder、Antigravity、Qwen、MiMo 都照样跑。

Evidence-backed retrospectives for AI coding-agent histories. Offline indexing, scoped workflow improvements, and bilingual documentation.