Havuz

Local-first tool that strips emails, secrets, paths, and other identifying content out of your prompts before they reach a cloud LLM — and r

一段提示词让 Codex 与 ChatGPT 分工：研究、本地执行、独立验证 | One prompt pairing Codex with ChatGPT for research, local execution and independent verification

Production-ready Agent Skills for Codex, Claude Code, OpenCode and OpenClaw | 小红书图文、学习路径、论文解读与 YouTube 播客笔记

Long-term memory for AI agents with no LLM call: an MCP server and Claude Code plugin, plus local-first context compression for LLM apps.

AI가 쓴 한글 글의 AI 티를 제거하는 Kiro CLI 에이전트 (im-not-ai kiro ver.)

Bilingual community prompting Skill for MiniMax H3 / 海螺 H3

Tier-1 strategy-consultant frameworks (MECE, Issue Trees, Hypothesis-Driven, Pareto, So What?) packaged as Claude Skills + LLM-agnostic prom

12 agent skills for AI-driven software development — a gated idea-to-ship pipeline: 7w3 design, build-ready specs, executable architecture,

Eval-driven multimodal agent for identifying trees, logs, bark, leaves and wood from photographs. Dendrology is the reference domain; the e

Sách miễn phí tiếng Việt về vibe coding cho Tester, PM, BA — người làm IT không viết code. 20 chương, 3 phụ lục, 54 hình. Học cách chỉ đạo A

DSH plugin: host-resident scheduled-jobs × AI-agent engine (hermes-agent cron inspired) — 60s ticker fires real agent sessions via cron; pin

Built for OpenClaw and beyond, Chat Selfie lets your AI Agent send you emotional selfies in every conversation, with mood-aware replies, hea

面向个人与小团队的 AI 导演工作台：把 Brief、创意路线和剧本转成可确认、可执行、可追溯的分镜与生成提示词。

Codex 短剧带货 Skill：salpx 生成分镜首帧，MiniMax H3 API 生成视频，支持美国市场本地化与剧本保真。

Seedance 2.5 视频分镜提示词生成 Skill for Agent | 把商业意图+素材转成可直接用的视频脚本prompt | Turn business intent + assets into ready-to-use Seedance 2.5 storyboard

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

Open-source GEO engine for personal GEO promotion workflows. Reach Discord：https://discord.gg/GcNhAHPZu

A complete AI-powered real estate agency — 12 specialized agent paired with 12 production skills that generate CMAs, offer strategies, marke

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

Extract a person into an AI agent — through an 8-week therapist-style interview, not a form. The open-source alternative to $4K AI clone cou

Token-efficiency linter for LLM prompts and payloads

非技术背景秋招人用 AI 把投递→面试准备→模拟面试→复盘跑成闭环：4 个 Agent 的 Skill 提示词 + 转写函数源码

A Claude / AI security review prompt for shipping safe apps. TRAP (True Readiness Audit Prompt) turns Claude Code, Cursor, or Copilot into a

Hypertaks = "A founder who owns a library of more than 1,400 books, knows exactly which book to consult for this issue, and has a strict SOP

A complete engineering team in one folder: 26 specialist agents, 20 workflow skills, orchestrated workflows and quality gates.

Open-source bundle of agent methodologies and Hermes-compatible skills.

930+ AI-powered skills and 31 agent plugins for Claude Code, OpenAI Codex, Gemini CLI, GitHub Copilot, and Perplexity Computer. The largest

Plain-English legal writing skill for AI agents (Claude Code, Codex, Antigravity). For lawyers, paralegals, and in-house counsel: audits and

AI Novel Diagnosis Desk：一站式 AI 网文诊断工作台，可自动解析小说文本，生成小说人物关系图谱，诊断读者流失原因，并输出可执行的智能改稿 Prompt。

43 Claude Code skills for making content that doesn't read like a machine made it — prose editing with an offline linter, prompt engineering

Snapshot testing for LLM apps and agents, built to run locally and block regressions in CI.

AI Storyboard Director v5.2: open-source director-grade AIGC storyboard skill for turning scripts into executable cinematic shot chains.

将简单设定扩写成中国式宏大场景故事、连续分镜与成对图片视频提示词的 Codex Skill

Validate and retry LLM outputs for ruby_llm. Describe the JSON response you expect, fall back to a stronger model when the cheaper one fails

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

Your coding friend in the terminal.

Skill + Agent + Model + Thinking depth — auto-routed before any tool fires. One SKILL.md for Claude Code. 90% routing accuracy, per-step mod

Evidence-first multi-agent debate skill: get a second opinion by pitting Codex × Claude Code (or GLM/DeepSeek/Qwen) to independently review,

A decision protocol for AI agents — critical thinking, evidence verification, and structured review. Less confident advice, more testable de

Production-grade, agent-portable image prompting skill for Nano Banana Pro and Nano Banana 2 in the Gemini image family

面向小团队的一站式 NLP 小模型平台:数据集版本管理 · 训练 · 评估 · 在线部署 · Badcase 闭环,内置大模型 Prompt 盲测评测(人工 + AI 双指标)。

Markdown-first, human-gated multi-agent editorial workflow with explicit research, planning, writing, and review artifacts.

Prompt-only Krea moodboard search and style nodes for ComfyUI.

Open-source middleware for AI agents — catches mid-run failures,compresses stale context, and grows a reasoning library across runs. Any mod

See when AI is making things up.Make AI more honest — and show its receipts.

小红书图文笔记 Agent Skill，支持看图理解、主动提问、智能选题、实时热梗搜索、标题正文、标签评论钩子和风险检查。

安克创新 AI 飞行员试炼面经：AI 协作能力测评复盘、Prompt 多轮对话模板、结构化思维训练

Context optimization layer for LLMs. 65-90% token savings with zero quality loss. Drop-in proxy for Claude, GPT, Gemini, and local LLMs (Oll

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

AI Prompt工作流库（自用分享）：详情页制作工作流、电商、TikTok、中泰本地化翻译、AI 生图、视频分镜与自动化