Havuz

Codex skills for scientific infographics, research cover visuals, and publication-grade paper figures using ChatGPT image generation.

Local proxy that compresses your LLM API requests so you pay less, with no change to the answers. Trims wasted tokens from prompts, history,

AI 漫剧/短剧连载创作引擎（Agent Skill）| 一句话到剧本+分镜+配音+AI提示词的工业化流水线 | 七个记忆文件+22项跨文件一致性检查，解决长线连载人设崩坏与伏笔丢失 | Agent-agnostic (Claude Code / Codex / Copilot

Codex Cost Router Skills - preflight task routing skills for Codex to reduce token waste, choose model tiers, reasoning effort, permissions,

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。

Auditable context capsules for LLM handoffs, coding agents, and OpenCode MCP workflows.

Agents config for development

By a 12-year product manager who builds 0-to-1: takes a beginner from a vague idea to a buildable plan, then guides the build (GitHub basics

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

Agent Skill that silently refines prompts for the currently running model

Practical guide and toolkit for physicists and mathematicians using Claude Code — built from months on a real research project

A Codex CLI plugin that grades how you collaborate with Codex across 9 dimensions in 3 categories — your Codex model writes a free-form diag

Prompt Engineering skill for Claude Code — rewrites and optimizes prompts using proven techniques (Anthropic, OpenAI, Gemini, The Prompt Rep

End-to-end AI short-video production pipeline. FastAPI orchestration + Spring Boot gateway with multi-model failover, circuit breaker, meter

Xiaohei 2.0 Codex Skill for Chinese real-object article illustrations and long-scroll story images

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

Blind A/B testing for AI agent skills, .cursorrules, CLAUDE.md, and system prompts. Detects placebo and harmful instructions.

Automate a WeChat group's daily work-report roll-call — start, chase non-submitters, and LLM-summarize for the manager. wxauto + FastAPI + h

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

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

Expert-thinking AGENTS.md profiles that teach AI agents to reason like senior scientists and engineers.

Platform-agnostic AI agent: one Full-Stack Software Engineer brain, compiled into ready-to-paste adapters for ChatGPT, Claude, Copilot, Gemi

AI academic PPT workflow skill for Codex / ChatGPT: paper-to-editable PowerPoint, planning table, mockup family, and PPTX generation.

Pravidla, díky kterým AI píše český text jako člověk a nikoliv jako AI generátor. Krátký prompt do AI chatu, plný průvodce a skill pro AI ag

Codex skill for director-level Eastern beauty AI image prompts, covering gu feng, Eastern fantasy, modern Chinese aesthetics, SweetHomeGirl

花 4 個月慢慢一步一步調整到可以自動化去防 AI Slop 的機制，包括：CLAUDE.md 跟 Hook 之間的設定跟腳本，目的就是幫助整個系統在運作的時候減少 AI Slop。

Codex-compatible prompt-template workflow for architecture, landscape, and urban design analysis diagrams

A curated skillstack for AI agents. Make your AI code editor write code like a Tech Lead. Stop copy-pasting instructions. Install 794 expert

GAN-style self-improvement loop for any text artifact: mutate, grade with a SEPARATE model, keep only verified wins (pairwise-judged), rever

AI Agent 面试知识库：覆盖 LLM、Prompt、RAG、MCP、Tool Use、Agent 架构、Multi-Agent、LangGraph、Claude Code、Codex CLI、工程化评估、安全与源码解析。

AI Paper Reviewer: LLM-based tool for academic paper review

LLM应用&Agent开发面试题全集：21个专题、380+道题、41000+行、覆盖Python/FastAPI/LangChain/CICD

Guardian Runtime sits securely on your machine, acting as a bodyguard for your code. Whenever you use AI tools like Cursor or Claude Code, i

Agent skills for AI filmmaking, cinematic prompting, and model-specific prompt export.

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

Your agent invents things because it has no memory, and can't touch your database because it has no arms. rsc is the meta-harness that gives

A reasoning skill for AI agents to improve complex judgment, premise auditing, counterargument pressure, and verifiable conclusions.

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

Codex ve uyumlu agent ortamlarında portre girdilerini yapılandırılmış, ayrıntılı AI image-generation promptlarına dönüştüren bir Skill paketidir.

Neden yükseliyor · 120 günde 1603 yıldıza ulaşması görünür ilgiye işaret ediyor; ancak son 28 günde commit ve farklı yazar olmaması, ilginin sürdürülen geliştirme veya topluluk katkısına dönüştüğünü göstermiyor.

MindSpark - Mind Map for Everyone

211 free visual cards about large language models, from tokenization to deployment. Full collection: 376 cards.

Goal-based planning and proof gate for AI coding agents

Convert long AI conversations into portable conversation state graphs for LLM handoffs.

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

Curated PRD prompts that turn a spec into a fully working, mock-data-driven frontend prototype with one AI coding assistant run.

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

Boring Is All You Need: a Codex Desktop workflow replacement with transactional migration, audit-only managed hooks, risk-based review, scop

让 AI 主动记错题、自我迭代的协作机制 · A framework that makes your AI reflect on its own mistakes and stop repeating them

Drop-in prompt-caching fixes for the LLM agent harness you use. Point your AI coding agent at this repo and it ships the patches.

Portable fresh-agent QA loop prompt for finding bugs without biased self-checks / 通用自动 QA 循环 SKILL