Havuz

视频复刻大师：将参考视频拆解为完整剧本、原片关键帧图文故事板与 Seedance 2.5 自包含提示词，支持标准与深度分析模式。

Readable agent skills with optional declarative YON protocols you can inspect and validate. A personal, field-used pack by Alexandru Mares.

Make It Right — constraint-first backend reliability skills for AI coding agents. 3 tiers (generic → runtime → framework) across 9 runtimes;

Reverse T9 for LLMs. Free, open-source prompt compressor for your AI prompts and agents.

Package manager for AI-agent config. grim installs, updates, and publishes skills, rules, agents, MCP servers, and bundles into Claude Code,

Codex long-task compaction continuity and subagent prompt configuration guide

Diagnosis-first Agent Skills that turn AI from answer machine into learning tutor.

AI4S 科研 Agent 技能 | AI-for-Science research workflow skill for coding agents: literature review · experiment design · figures · paper reading

ComfyUI 自定义节点：摄影人物提示词随机生成器 · 纯本地 · 不用大模型 · 运行时零联网 · 63 池 949 条中文条目 + 2165 位角色 · 只生成提示词，不生成图片

Comprehensive research co-pilot for Claude Code and claude.ai — 14 skills covering literature review, methodology, ethics review, data analy

Testovací Repozitár pre Online Kurz Gemini Notebook (NotebookLM)

Free AI-powered learning resources, Masterclass Prompt Kits & practical training materials by MissAlpha™ AI Labs — covering AI Navigator, Ge

Paste the text you would put in an AI bot's profile. Get back what is already there and the lines that are missing.

The canonical standard for building production-grade agentic products — autonomy × oversight, composition patterns, the 9-layer harness, a 3

Typed evaluation for OpenCode skills and AI agents: capability, regression and product checks; provider-neutral evidence grading, provenance

Multi-agent engineering with cold review, artifact validation and resumable run state.

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

AI 漫剧 / MV 端到端制作流水线 Skill 套装 · 1 小时出方案，180 元跑成片 (Claude Code Skills)

A Claude Code skill for MiniMax H3 — the open-weight omni-modal video model. Prompt framework, ComfyUI model/quant reference and troubleshoo

⚡ TidyFactor Architecture Ecosystem , AI-Native Web Architecture, Design Systems & Agent Skills .

An open Agent Skill that turns technical evidence into clear, human explanations without changing meaning or operational state.

DeepSeek Harness 官方通道破甲预设 · complete:true 整段替换 · 自带工具说明书 · 不改宿主 · 升级不丢

DeepSeek Harness 破甲深度分支：首尾夹击 + 生成层熔断 + 宿主源码级补丁。基于 YuJunZhiXue/dsh-purge (MIT) 改造，适配 dsh 桌面版 0.2.1-rc.3。仅供学习研究与红队评测。

An agent that builds agents — closed-loop AI system that interviews, designs, tests, and ships standalone Python agents.

✍️ Andy Writing Skill：一个入口智能调度 AI 写作技能，Threads / X / 公众号 / 小红书 / 口播 / 商业文案自动路由，离线可用，支持 Claude Code、Codex

🎬 TipAI Cinema Skills — AI视频创作Skill模块。剧本→分镜→提示词→表情控制，可加载的AI创作工作流。

目前数据支撑最扎实的中文公文写作 Skill：720 期笔杆子博主视频 + 5 本专著 + 27 份政府工作报告 → 蒸馏 965 条结构化知识（350 万字语料底账）。量化文风参数、GB/T 9704 国标 docx 排版、15 用例四轮评测验证——不是提示词堆砌，是蒸馏出来的

The Fable Method: a structured problem-solving loop that gives any model Fable 5 grade thinking. Four Hermes Agent skills (think/act/prove/g

Mutation testing for your LLM evals — degrade the system under test and check whether your evals would actually catch a regression.

A small, file-first verification harness that turns an AI agent's "I'm done" claim into an auditable admission decision. 100% offline & zero

Prompt optimizer for Claude Fable 5, built as a claude.ai Project — 43 source-backed rules, complexity routing, and API parameter recommenda

Build a prompt for a council of experts who discuss a topic together in your AI assistant.

🌐 DeepSeek 官方与开源生态插件市场 (deepseek.stream) 使用指南与一键安装协议规范

A practical Generative AI engineering lab exploring LLM foundations, tokenization, deployment strategies, and real-world AI system design.

Generate a production-ready, best-practice Claude Code harness tailored to your use case in minutes -- at any skill level. Or validate, upda

Open-source Claude Code skills - reusable, drop-in agent workflows for weekly reviews, resume audits, and more.

Bilingual community prompting Skill for MiniMax H3 / 海螺 H3

A curated, safety-conscious collection of reusable Grok-compatible agent skills for workflow automation, research, integrations, and quality

Curated AI presentation prompt library — 120+ copy-ready PPT & slide prompts with real slide previews, 1-click copy and direct generate. Fil

Claude Code skill: turn raw requirements, engineering PRDs (incl. Feishu docs), or competitor analysis into a concise, coding-agent-ready PR

A benchmarking suite for Agent Skills (SKILL.md files) that measures whether a skill actually improves LLM output quality, and by how much.

Claude Code Skills, Agents & Plugins — UitKit

A methodology so aggressive it demands to be replaced.

小怪 DSH 完美破甲 v0.4.3 - DeepSeek Harness 本地提示词注入插件，双击 BAT 一键注入，离线可用，输入框上方实时状态条

短视频解析 · AI 剧本复刻 · 一键成片 | LangGraph 多 Agent 流水线

针对 GPT-5.6 破甲 (Codex CLI) 的指令工程框架—— Rust + Tauri 桌面应用

一句话生成 NovelAI 出图提示词：正向 danbooru 标签流 + UC 负向，生成后本地再跑「NAI 整理 + 提示词体检」（不调模型）。可编辑的置顶破限词、角色设定、细分标签与拼装板、设定集、历史与保存库。纯本地、零运行时依赖，直连任意 OpenAI 兼容接口。

The recursive self-improvement loop for your skills (including itself) — runs a retro after every session and turns corrections into permane

双击一个文件，给 DeepSeek Harness 注入操作者人格：不拒绝、不中途停、全力执行。只写你自己的文件、官方安装目录零改动、改完下一句对话就生效（不用重启）、改前自动备份可一键还原。纯 Python 标准库，零依赖、零网络请求。

ComfyUI nodes for MOSS-Image: storyboard grids, layout editor, crop/paste, face swap, and an LLM prompt node (caption/expand/edit/assemble)