Havuz

Route Claude Code and Codex work through one lead Skill per phase. Your workflow as config, every route inspectable. Plugin + MCP or standal

A Claude Skill for revising draft prose — essays, papers, memos, reports — on the principle of idea flow before linguistic flow. Diagnoses s

渡鸦商业与线索获客 Skills：客户定位、获客判断、短视频与小红书及公众号创作、矩阵团队、量子阅读。1 个入口，12 项能力，23 篇专业知识。

A local-first, MCP-native toolkit for building AI agents: engram (memory) + skillet (skills) + tracelet (tracing). One runnable end-to-end r

Recommend AI coding harness changes from repository context and coding signals, then distribute approved rules, skills, hooks and agents to

Agent skill: make short videos with code — the agent asks what you want, writes a seven-block prompt (role / context / task / specs / style

12 Claude skills for building financial models in Excel: model architecture, driver builds, scenarios, sensitivity analysis and formula audi

Learn your codebases through self-quizzing and study. Track your knowledge coverage over time.

A browser for LLMs, not humans.

Evidence-aware personal knowledge system for AI agents: schema-governed Obsidian vault, proposal-gated MCP gateway, and the skills around it

Deterministic Markdown-to-Word (.docx) compiler & MCP server for academic papers, theses and AI agents | 确定性 Markdown 转规范 Word 与 MCP 服务

Audit every skill installed on your agent. Finds the ones that can never fire, measures what they cost you on every message, and flags any s

C(H+A)RM build diary — a CRM for Human & Agent collaboration, built in public with Claude Code. Framework: github.com/tonydzi/charm-os. Engl

喜茶风涂鸦海报 | Portable Agent Skill: photo-to-doodle posters, prompt-only fallback and optional 4s animation.

MIT-licensed code knowledge graph: index any source repo into a queryable graph of symbols, call chains and blast radius — with wiki generat

A 3D game engine in strict TypeScript: WebGPU with a WebGL2 fallback, deterministic physics, animation, audio, rollback netcode, DriftScript

Know what your stack will cost before the bill arrives. Free agent skill for Claude Code, Cursor and Codex: prices every service at your usa

How do you KNOW if a 'skill' is any good - deterministically? This runs controlled skill-vs-no-skill experiments. It doesn't just ask, “Did

DeepSeek Harness 社区记忆插件集：中文与扩展汉字全文检索、工具去重、混合召回、跨会话核心记忆、可追溯压缩与技能管理。8 个包、97 项单测；已验证 DSH 0.2.0-rc.2 完整 Web 宿主、真实持久化与冷重启。用户固定的记忆与技能受来源保护。

Design Taste skill for AI agents — 15 style DNA folders, decision engine, anti-slop rules, taste scoring. Teaches agents to analyze product

A modular Agent Skill system for strategy, creative, content, and brand teams—from brief framing and evidence to insight, narrative, visual

Agent Skill for reading and modifying Twenty CRM data on any self-hosted or cloud deployment.

Convert public bug bounty hackerone reports (9,950) into reusable AI security skills and vulnerability knowledge.

Give your AI assistant a physical side phone.

One-stop AI toolkit for building, integrating, and scaling AI-powered products with JPMorgan Payments APIs.

Claude skill that goes past word-list humanizers: strips the full catalog of AI tells, refits the text to its channel (LinkedIn, X, cold ema

Agent skills built from Algorithms for Decision Making (Kochenderfer, Wheeler & Wray). Expected utility, value of information, bandits, robu

⚡ High-frequency (~60Hz) in-browser behavior tree execution engine for autonomous AI agents. Reactive priority interrupts, safety guardrails

Agent Skill: read CLAUDE.md & project rules before coding. Optional CLI audit + hooks. Claude/Codex/Cursor.

itr-wala, Hindistan gelir vergisi beyannamesini hazırlamak için AI agent’lara belge okuma ve yönlendirme becerisi, Python tabanlı deterministik vergi hesaplama motoru sağlar.

Neden yükseliyor · README, bir Instagram reel’inin bir haftada 1,2 milyon görüntülenme aldığını ve deponun en yoğun haftasını yaşadığını belirtiyor; 63 günde 871 yıldız bu görünürlükle uyumlu olabilir. Ancak bu ilginin gerçek kullanıcıların beyannameyi başarıyla tamamladığını veya hesaplamaları bağımsız biçimde doğruladığını gösterdiği söylenemez. Son 28 günde 3 commit ve 1 farklı yazar olması da aktivite kanıtının sınırlı olduğunu gösteriyor.

seanswarm, coding agent’lar için araştırma, doküman okuma ve yazılım teslim süreçlerini rol ayrımı ve mekanik kontrollerle düzenleyen bir workflow paketi.

Neden yükseliyor · 11 günlük repoda 54 yıldız kısa sürede görünürlük kazandığını gösteriyor; ancak mevcut veriler yükselişin nedenini veya kullanıcı benimsemesini doğrulamıyor. Son 28 günde 4 commit ve 1 farklı yazar, geliştirme etkinliğinin tek katkıcıyla sınırlı olduğunu gösteriyor.

qiaomu-codex-imagegen, Codex’in yerleşik image generation özelliğini MCP, CLI ve Agent Skill üzerinden farklı agent’ların kullanmasına yarayan bir araçtır.

Neden yükseliyor · Herhangi bir agent’tan görsel ürettirme vaadi ve çok sayıda hazır tasarım yönü projeyi kolayca denenebilir kılıyor; ancak 1 günlük geçmiş, 3 commit ve tek farklı yazar nedeniyle ilginin kalıcı benimsemeye dönüştüğüne dair kanıt henüz yok.

GPUtw-Skill, AI coding assistant'lara GPUtw cloud REST API'sini kullandıran Agent Skill içerikleri ve beta bir MCP server sunuyor.

Neden yükseliyor · 12 günlük bir repoda 53 yıldız ve son 28 günde 6 commit dikkat çekiyor. GPU cloud işlemlerini birden fazla AI coding assistant ile kullanma vaadi ilgi çekebilir; ancak yükselişin kesin nedeni veya benimsenme düzeyi verilen ölçümlerden anlaşılamıyor. Commit'lerin tek yazardan gelmesi bağımsız katkı kanıtını sınırlıyor.

Browse, create, and edit AI agent files across Claude Code, Cursor, Codex, and 12 coding tools — from Obsidian.

司南：个性化 AI 任务总控 Skills 系统 /COMPASS: Personal Alignment Skills OS for AI Agents

한국 법령 기반 개인정보처리방침·이용약관 자동 생성 Claude Code 스킬. 2025.4.21 작성지침 및 2026.3 개정 법령 반영.

Plugin for Butterbase.ai

Run a task with AI as a flow of steps you keep, reuse, and refine, not a one-off chat.

Deterministic safety solutions for probabilistic AI agents

A single CLAUDE.md file to improve Claude Code behavior, derived from Linus Torvalds' observations on coding pitfalls.

AI Agent Skills for Chinese Knowledge Workers: iMandalArt, FIRE, planning, and publishing workflows for Claude Code, Codex, and LLM agents.

Turn project work into reusable knowledge — an AI-agent skill for Claude Code & Codex

codexqa: 11 local-first Agent Skills for Cursor, Claude Code, Codex & OpenClaw — change impact analysis, AI code review, defect scan, testca

Feed your agent papers and half-formed ideas — it links them into a system design you can defend. Markdown keeps the record; a visual canvas

AI private learning coach for Codex: learn through real projects, adaptive dialogue, debugging, evidence-based mastery, and visible progress

Shared standards and reusable skills for Claude Code, Codex CLI, and other AI coding agents.

Claude-type skills for institutional equity research — 25 AI agent skills with SEC filings, XBRL financials, earnings calendars, DCF/comps

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

Minecraft AI agent skills and dual-target plugin bundle for Codex and Claude Code.

Open-source AI CLI and local MCP server connecting 25 clients—Claude Code, Cursor, Codex, ChatGPT, Hermes, and OpenClaw—to 2,000+ models/API