Havuz

从 165 个顶级 AI 产品系统提示词中蒸馏出的 15 个可执行 Agent skill

25 fixed illustration styles for Codex: 9 skills, prompt recipes, and visual references

A reusable AI learning skill for mastering almost any subject through project-driven learning, mastery checks, and authoritative sources.

JD-driven Chinese resume optimization skill for China job seekers. 解析岗位 JD、诊断简历缺口、生成真实可信的中文定制简历、ATS 纯文本版和面试追问。

Pi extension: rewrite rough prompts into precise technical prompts before send

An open-source, agent-guided creative-direction workflow for turning one visual reference into a connected brand system with Lovart Agent.

Loop until it's better — drop-in agentic loops (autoresearch, scientific writing, data analysis, code/SQL/prompt optimization, red-teaming)

AI video prompt cheat sheet & Claude Skill: cinematic camera angles, camera movement, lighting, composition, color grading for Veo 3, Kling,

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

Open-source, bilingual AI video-prompt skill — rewrite ideas into model-ready text-to-video prompts. A portable Agent Skill (Claude Code, Co

Build a person once, then shoot a whole series: framing, pose, placement, expression and aspect ratio vary while the person stays the same.

Codex skill for analyzing still images and writing restrained, image-specific motion prompts.

Offline prompt engineering manager for Windows

Air traffic control discipline for agent output. Written for a reader with ADHD.

Principal-PM-level product-teardown skill — reverse-engineer any product as a system and render a bilingual (EN + ZH) HTML report with a pro

A universal, industry-neutral taxonomy of cognitive core skills (perception, memory, reasoning, planning, action, verification, learning, go

Open-source local implementation of MiniMax H3 Context-IR. Turn simple prompts into structured, validated H3 video briefs.

OpenCode skill suite for MiniMax H3 directing, routing, multishot planning, prompt generation, and review.

Переписывает промпт под правила модели, где вы работаете (Claude Opus 5.5, Fable 5.1, GPT-6 Astra/Sol/Luna, Codex), и подсказывает, на каком

Nano Banana Pro prompts: tested prompt recipes with example renders, aspect ratios, the model id (gemini-3-pro-image-preview) and the cost e

东方文化编辑海报 v2 Codex skill：Image 2 出图、中文标题精炼、真实文化物证、A/B/C 三联测试

Production-Stage Visual Design & In-Codebase UI Engineering Suite

Production-grade Agent Skills for AI coding agents—composable workflows for planning, TDD, debugging, review, UI/UX, releases, incidents, an

Curated archive of jailbreak and prompt-injection experiments for AI model robustness research, red-teaming, and defensive evaluation.

Bounded, evidence-driven SKILL.md evolution under frozen evaluation and safety contracts.

Complete Production Environment for professional MiniMax Music 3 audio generation, including Prompt Generation, Metadata generation includin

The open archive of how AI agents actually work. A versioned, verifiable archive of system prompts, developer instructions, tool schemas an

Reference-first Codex workflow for edit planning, keyframe approval, and MiniMax H3 prompts.

Local, read-only audit for stale AGENTS.md, CLAUDE.md, and generic SKILL.md instructions.

Agent Dispatcher, Claude Code ve Codex için görevle ilgili kod bağlamını bulup uzman yönergeleri ve doğrulama adımlarıyla sunar.

Neden yükseliyor · 9 günlük yaşında 52 yıldız ve 108 commit dikkat çekiyor; ancak farklı yazar sayısı 1. Bu, yoğun geliştirme ve erken ilgi gösterir, bağımsız benimseme veya olgunluk kanıtı değildir.

Quirón, Claude Code, Codex ve Cursor için metni AI yazım kalıplarına göre düzenleyen ve değişikliği ölçen bir agent skill’idir.

Neden yükseliyor · Beş günlük bir repoda 49 yıldız ve son 28 günde 42 commit dikkat çekiyor. Ancak farklı yazar sayısının 1 olması, aktivitenin tek bir geliştiricide toplandığını gösteriyor; yükselişin nedeni veya kullanıcı benimsemesi hakkında daha güçlü kanıt yok.

oh-my-fable, Anthropic’in prompting yönergelerini Claude Code oturumlarına hook ve skills aracılığıyla uygulayan bir eklentidir.

Neden yükseliyor · 25 günlük bir repoda 56 yıldız ve son 28 günde 34 commit dikkat çekiyor; ancak tüm commit’lerin tek yazardan gelmesi nedeniyle bu hareketlilik bağımsız katkı veya benimseme kanıtı olarak yorumlanmamalı.

PromptLedger, prompt şablonlarını fingerprint ile sürümleyip aday yanıtları karşılaştıran ve sonuçları tekrarlanabilir raporlara dönüştüren bir Python aracı ile Go CLI sunuyor.

Neden yükseliyor · 25 günlük bir repo için 35 yıldız dikkat çekiyor; ancak son 28 günde yalnızca 1 commit ve 1 farklı yazar var. Bu nedenle ilginin kalıcı benimsemeye dönüştüğünü gösteren yeterli aktivite kanıtı henüz yok.

Spot it. Save it. Free, local-first Chrome extension for images, videos and prompts. Explore 2,000+ curated cases and connect your library t

24 open-source agent skills that turn taste into instructions — ten genre identities, each proven by a same-brief before/after demo

可同时输入多个初版提示词，开启多轮自动优化，连续得到高分后得到最终结果。

Claude Code, Codex, and multi-agent configuration system: principles, hooks, skills, and workflow patterns for AI-assisted development

A pure-Python context management layer for LLM systems — retrieval, re-ranking, memory decay, and token-budget enforcement in one pipeline.

情圣 · Claude Code 中文恋爱教练技能 · 微信/探探/Soul/Bumble/青藤之恋聊天截图分析 · 高情商回复生成 · 7阶段关系推进

台灣正式文件撰寫 AI Skill：公文、存證信函、陳情書、合約 — 匯入 ChatGPT / Claude / Gemini 即可使用

Agent Skills lifecycle toolkit: mine repeated coding-agent workflows, audit and personalize skills, and generalize personal skills for publi

一个可以帮你快速反推出网页上图片的提示词，并快速生图测试提示词效果的插件。A Chrome extension to reverse-engineer prompts from web images and instantly validate them via live gen

三个 skill 画论文图：fig-analyze 看材料，fig-draw 先看 6 种风格再出图。交付后询问要不要做成可编辑 PPT，同意后 fig-pptx 才做。npx skills add Azhi-ss/academic-figure-skills

One-stop shop for AI skills and agents. Search 110K+ community skills, install and track them declaratively, and deploy across all major AI

Make AI output sound human. Strips AI-isms (sycophancy, stock vocab, hedging stacks, em-dash pileups), preserves code/URLs/headings. Plugin

大师.skill — 输入行业，自动调研 6 轨[行业大佬 / 工具地图 / 工作流 / 知识正典 / 信息源 / 术语标准] → 提炼为可运行的行业 Master OS skill；装到任意 Claude Code / OpenClaw / Codex / Hermes age

The most expensive bug in AI-assisted building is shipping the wrong thing, well. A drop-in CLAUDE.md / AGENTS.md for PM + eng teams using C

Global instructions for coding agents: evidence, parallelization, validation, all in one AGENTS.md / CLAUDE.md

Stop hooks that stop AI coding agents (Claude Code, Codex) from claiming "done" without proof. A Lean quality system: every defect becomes a

AGENTS.md patterns for context engineering in coding agents: safer command output, token efficiency, validation, and prompt-injection resist