Havuz

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

Open-source Codex plugin for Sol-governed multi-agent coding, bounded AI code review, model routing, and LLM cost optimization

27 Skills that diagnose, build, and optimize every architectural layer of your Claude environment

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

local-first MCP discovery runtime for agents — search before invoke, reduce prompt bloat, and route to local MCP tools

A deterministic, zero-dependency prompt-pruning layer for long-running LLM conversations — expires stale tool state, collapses duplicate con

Aileron Protocol: A strict system harness override enforcing deterministic AI behavior through codebase-first execution, strict token econom

Turn travel photos into archival photo-and-rubber-stamp field note posters.

A collection of AI prompts for generating comprehensive manual test scenarios from software projects, covering features, edge cases, securit

A full-stack AI prompt library for discovery, structured authoring, safe imports, moderation, and shareable agents.

Claude Code skill that forces AI to understand before executing. Three disciplines: cognition check, requirement understanding, method searc

Cognitive training practices for AI agents. Self-applied. Open source. Built by an independent Vancouver yoga studio.

1,017 system prompts from real AI products, audited span by span against the eight AISPA assurance dimensions

Interactive AI tutor built as a Claude Code skill — teaches with spaced repetition, personalized project examples, and a visual progress das

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

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

CLAUDE.md + AGENTS.md 12-rule behavior file for Claude Code, Codex, Cursor, Hermes — drop-in, ~700 tokens, cuts AI coding mistakes ~40%→~3%

A Claude Code skill that rewrites your prompts for clarity before they run.

Project continuity for Claude Code and Codex: a roadmap beside your code, grounded handoffs, and clear task status.

Chain two LLMs — local or cloud: a Prompter that refines your idea, and a Coder that writes the code.

Make any Claude model adopt Claude Fable 5's working style in Claude Code — always-on output style + zero-dependency MCP + subagent injectio

AI agents now operate with authority. Authority without discipline is how complex systems fail. Nuclear’s control loop, ported to AI-assiste

A structured workflow system for AI coding agents - harness engineering, execution loop, skills, hooks, and a learning loop. Works with Clau

OpenCode agent configuration — a read-only orchestrator delegates to 6 specialized subagents. Expert model plans, fast models execute. Isola

三位老师，一段故事，零个标准答案。——当苏格拉底教学法遇上轻小说叙事，学习便不再孤独。

A pure-Python structured memory benchmark for multi-agent LLM systems — context graph vs vector RAG vs raw history dump, five scenarios, 18

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

Claude Code Architecture Deep Analysis — 14-chapter report, 7 languages | Claude Code 架构全景分析 — 14章报告，7种语言

High-performance computer vision implementation featuring real-time image segmentation matrices, dynamic alpha-channel compositing, and auto

Compact operational charter that turns LLM coding agents into disciplined principal engineers. Eleven rules + one meta-rule.

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

Turn vague product or feature ideas into clear, checkable requirements before planning or coding—mapping rough descriptions to professional

Turn a production incident into a structured 9-section LLM response (severity, root cause, mitigation, postmortem). Ships with a 5-scenario

A curated collection of Claude Fable 5 system prompts for developers and researchers. Discover more advanced prompt engineering tools at Moe

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

Harmonist, AI coding assistant’lar için agent’ları, workflow kurallarını ve denetimleri IDE hooks aracılığıyla bir araya getiren taşınabilir bir orchestration framework’üdür.

Neden yükseliyor · 158 günde 2258 yıldız dikkat çektiğini gösteriyor; mekanik workflow denetimi de agent araçlarına ilgi duyan geliştiriciler için anlaşılır bir vaat. Ancak son 28 günde commit ve farklı yazar sayısı sıfır; yıldızların ne zaman kazanıldığı bilinmediğinden yükselişin sürdüğü doğrulanamıyor.

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.

Offline prompt engineering manager for Windows

`xxg-portrait-rebuild-light` is an image-edit skill for existing portrait photos. It reconstructs the key light, fill, shadows, and backgrou

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

Open, MIT context format for AI coding agents: centralized .aigx/ rules + a per-file boundary index that targets the right rules, forbidden

Agent Skill that silently refines prompts for the currently running model

Learn any journal's writing conventions from its published papers, then revise your manuscript to match — section by section.

Universal, model-agnostic operating harness for AI agents (Claude, Codex, Gemini, …) — a lean core + work-type profiles assembled by one set

Claude Code plugin: universal radial-tree exploration engine. One tree skill + swappable presets (brainstorm / attack / design / code-audit)

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

AINL helps turn AI from "a smart conversation" into "a structured worker." It is designed for teams building AI workflows that need multipl

Offline prompt-contract auditor for Hermes, Claude Code, Codex, OpenCode & OpenClaw. Pre-write guard before agents ship vague code. Zero dep

Spec-driven, agentic workflow framework for AI coding agents. Turn a request into a verifiable goal loop — plan, act, verify — with durable