Havuz

Does the model pick the right tool? Tool-routing tests for your MCP server: run them on Claude and OpenAI models, see where each request lan

AI agents worth falling in love with. Built by the community, loved by everyone.❤️

中文网文写作工具包 · Chinese web-novel writing toolkit (23 skills) — a Claude Code plugin, also works in ChatGPT / DeepSeek / Gemini

Route-first FPV AI video prompting skill for Seedance, Kling, Runway, Veo, GPT Image asset packs, numbered stops, and red-line path control.

Your coding agent starts every session knowing nothing about your project. One line, and it writes its own memory from your real code, then

中文 AI 图片提示词库，覆盖女装、童装、电商主图、产品摄影、小红书封面和广告海报。

Plain-markdown system that turns Claude or ChatGPT into a project coach.

Make Claude Opus, Sonnet, GPT, or Gemini produce work close to what Claude Fable 5 would ship. 21 craft standards written and audited by the

人格蒸馏引擎 · 蒸馏自己看清自己，蒸馏亲友留住余温与回声 · Claude Code Skill

A lightweight pre-coding check for Codex, Claude, Cursor, Antigravity, Gemini, and Grok: look up what you can, and ask only when an unresolv

Agent Skills for working UX designers. Challenge ideas, find blind spots, use the real design system, preserve evidence and decisions, and c

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

A terminal-native prompt composer for power users running multiple coding agents.

A native macOS companion for Draw Things: always-visible image and Moodboard inputs, a canvas you can draw on from an iPad (Sidecar), a loca

Agent Skill: rewrite a task into a deeper version, not a bigger one. Based on Felix Rieseberg's depth prompt. Claude Code, Codex, Copilot, C

Battle-tested model-dispatch doctrine for Claude Code — portable ops rules that let Sonnet/Haiku reliably run projects. Iterated in real dep

千笔一文 Novel — 人 AI 共写的长篇网文创作台：条目化世界书 · 正则 must 契约（确定性复检，违规拦住锁定）· 三层审校（引证验真 + 投票）· 同人文外部导入可整批撤销 · 升级不动书稿 · BYOK 全本地 · MIT。A long-form fiction

ComfyUI custom nodes: anime character styling console (clothing / pose / expression / scene slots) with a cross-plugin tag arbiter. Zero thi

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

PROS 05｜初五整理维护的14项公关、研究与知识维护Skill，包含方法、参考、模板与脚本；基于真实材料形成有证据边界的判断与交付。

Seedance 2.5 Shot Design Skills

Local-first prompt coach for Claude Code and Codex that improves prompts, observes prompting habits, and analyzes local history with explici

Generate project-based guidance and interview Q&A docs with STAR speaking scripts. 基于真实项目生成导学与面经（含第一人称 STAR 法则口播答案）

Give your CLAUDE.md / AGENTS.md a checkup — audit size vitals, dead references, drifted claims, and backtest every rule against your own ses

把一张图片逆推成生成提示词（Image to Prompt）：中英双语重建提示词 + 风格标签 + 结构化 JSON prompt，零依赖校验脚本 | Forensic image-to-prompt reconstruction. AGPL-3.0 · Commercial u

🧭 给 Claude Code / Cursor / Codex 用的『架构副驾』skill —— 开新项目时用持续深度提问引导你在写代码前想清楚架构(产出架构图 / ADR / 演进路线)。知识源自 awesome-architecture。中英双语。

Codex skill for transcript-driven MiniMax-H3 B-roll planning, T01-T21 motion templates, approval-gated generation, and balanced typography c

Screenplay breakdown & AI prompt-pack studio — import a script, get scenes, elements, bibles, shot lists & a timeline, then export self-exec

Private Skill distribution platform for AI coding agents: publish, install, update, and rollback team skills across Cursor, Claude Code, Cod

Production-grade screenplay studio: converts bullet points & images into strict single-line, timecoded video prompts for MiniMax H3, Maestro

A 21-day hands-on journey to mastering AI for DevOps — covering LLMs, GenAI, CI/CD, Kubernetes, cloud, automation, and AI-powered DevOps pro

My Custom collection of Agent Skills designed for Google Antigravity. It transforms AI coding agents into disciplined, senior-level software

The Dream Machine — a config-driven engine for nightly, cloud-scheduled, evidence-gated repository evolution. Composes @metaharness/flywheel

Claude Code skill & open-source wisdom companion (v6.6.0, Apache 2.0) for CLI, IDE, and web chat. One lens per turn, local SQLite vault, 350

把模糊视觉需求直接变成可落地生成的高质量设计图

⚡ Unit tests for AI. Test prompts, compare models, save money.

An AI prompt-skill that turns 20 cognitive biases into high-converting marketing copy. Playbooks for ads, landing pages, email, social, webi

A Codex skill that keeps human outcomes and creative intent ahead of overengineering.

Build LLM systems you actually control. A free, open engineering book + course — from tokenization to serving your own models. Mechanisms, t

DeepSeek Harness plugin: DietrichGebert/ponytail lazy senior mode & 7-rung ladder port, 6 skills with bilingual descriptions & per-skill tog

Turn any local codebase into clean, structured, AI-ready data.

Turn travel photos into archival photo-and-rubber-stamp field note posters.

Editorial guide for Indonesian academic writing: reduce cliches, clarify structure, and preserve meaning

Alice 二创素材库与垫图规范（Alice / 洛小山）

Claude Code plugin: universal radial-tree exploration engine. One tree skill + swappable presets (brainstorm / attack / design / code-audit)

Turn a production incident into a structured 9-section LLM response (severity, root cause, mitigation, postmortem). Ships with a 5-scenario

High-assurance, artifact-agnostic prompt for authorized security labs, exploit-chain research, PoC validation, and evidence-led reporting.

Disciplined AI coding mode. Understand deeply, write minimally, never hallucinate, stay consistent. Based on Ponytail & LLM Wiki.

Agentic prompts are the most important code you're not engineering. PromptKit fixes that — composable, version-controlled prompt components

Prompt enhancement plugin for the DeepSeek Harness web GUI: one-click rewrite of the composer draft into a structured prompt, with preview,