Havuz

Thompson-mode systems discipline for AI agents. Think first, build bottom-up, brute force until measured, rewrite over patch.

Open Steps, coding agent'ların yaptığı işleri teknik olmayan kullanıcılara sade raporlar, net sonuçlar ve takip adımlarıyla aktarmasını sağlayan bir skills paketidir.

Neden yükseliyor · Vibe coding ve agent kullanımında teknik olmayan kişilerin artan ihtiyaçlarına odaklanıyor. 33 günde 951 yıldız ve son 28 günde 40 commit ile dikkat çekmiş; 4 farklı yazar aktiviteye katkı olduğunu gösterse de bu veriler tek başına benimsenme veya kalite kanıtı değil.

Learn while your agent works. A Claude Code plugin that quizzes you on the concepts behind the code it just wrote — local knowledge graph, s

Press both Option keys and the window you're looking at - screenshot plus every word in it - lands in your next Claude Code message.

Install, run and verify OSINT tools from GitHub automatically, on any OS

Скажи словами, что построить — получи работающую версию, проверенную до того, как её назовут готовой. Плагин для Claude Code: сам собирает т

Active Directory pentest methodology for Claude Code: skills, agents and slash commands for internal AD red-team work (Kerberoasting, ADCS E

Skill router and prompt-injection firewall for AI coding agents: gives Claude Code, Codex and Cursor the few skills, MCP servers and tools e

Portable coding-agent workflows adapted from Cursor’s pstack for Codex, Claude Code, and OpenCode.

Multi-agent orchestration for Claude Code, Codex and Cursor: parallel coding agents that settle shared files before the merge, QA agents tha

Answers you can judge and act on without reading code — Claude Code plugins that keep implementation detail below a marked line. Off by defa

scroll-craft, coding agent’lara özgün ve scroll-driven web siteleri üretmeleri için tasarım kuralları, iş akışı ve araçlar sağlayan bir agent skill’dir.

Neden yükseliyor · 36 günde 2.800 yıldız alması kısa sürede belirgin ilgi gördüğünü gösteriyor; ancak ilginin nedenini kesin olarak bilmiyoruz. Son 28 günde 7 commit ve 1 farklı yazar olması, yıldız artışına kıyasla geliştirme etkinliği ve katkı tabanının sınırlı olduğuna işaret ediyor.

A live local HTML report Claude keeps updated as it works — status board, running narrative, screenshots, newest-first log, live-reload. No

Your coding agents remember what you decided — and what you changed. Plain-Markdown memory in Obsidian, shared by Claude Code, Codex and Cur

A /human-review skill for Claude Code: assembles one page that lets a human review a change set fast — diagram deltas, Code City, a feature

Free Claude Code plugin: learn Anthropic products hands-on from the official Claude Academy curriculum, and get your Claude Code setup and h

Socratic debugging for AI agents. Don't give me the answer. Help me find it.

Claude Code plugin that stops Claude writing like an AI. 29 researched patterns, loaded every session and checked on every file write.

agy-staff, Claude Code, OpenAI Codex ve Pi kullanıcılarının Google Antigravity CLI üzerinden Gemini tabanlı bir agent’ı farklı görevler için çağırmasını sağlayan bir plugin’dir.

Neden yükseliyor · Farklı coding-agent harness’leri üzerinden agy’ye görev devretme fikri dikkat çekici; 40 günlük yaşına karşılık 652 yıldız ve son 28 günde 14 commit ile 3 farklı yazar görünür bir ilgi ve geliştirme faaliyetine işaret ediyor. Bu veriler kullanım veya kalite kanıtı değildir.

A TypeScript-based Garmin Connect plugin and MCP server with secure browser-based MFA, built for DeepSeek Harness and designed to work with

Chart a project from a loose idea, then navigate it ticket by ticket on GitHub Issues.

The missing tool to sift your Claude Code sessions: regex search across all record types, recover files, extract images, inspect subagent to

The self-improving context engine for coding agents.

Hyperliquid trading desk for AI agents: 7 roles, 17 skills and keyless market tools. Research first; execution requires your API wallet and

Senior-developer discipline for AI coding agents. A commit gate that counts unchecked as failing, quality controllers that refuse to call un

Free, open-source memory for Claude Code. Your own database, no cloud, no subscription.

The most comprehensive agent skills for writing real, idiomatic Rust and porting code from other languages.

Bridge Deepseek-harness into Claude Code for review, critique, delegation, and session import.

Procedural writing-style skills for AI agents: official frameworks (plain language, business writing, GOV.UK, AP style, STE-100, developer d

Ground truth for FiveM / GTA V development: a knowledge tree, offline data layers built from your own game, a searchable snippet database an

Production-ready Claude Code decision intelligence marketplace with adversarial routing, evidence-driven analysis, specialized agents, bench

A local detector for AI-writing patterns. Scores every prose file your agent saves. Python standard library only, no network, no model.

Builds up to a goal in a field you have no expertise in: splits it into the foundations that goal actually needs, mobilizes what you already

Spec-driven development for Claude Code, layered on OpenSpec. You read one spec; parallel agents ship it to a tested commit.

Deterministic, local-only audit reports for Claude Code AI agent sessions. Rust + SQLite. Zero network calls. MCP server for agents.

Load-bearing comments only. Stops Claude Code narrating your code back to you in comments.

A minimal, evidence-gated harness for Codex and Claude Code: reuse what works, add only what is missing, verify before evolving.

A build playbook that turns your coding agent into the foreman of a website build. It interviews you, forces the design and scope decisions,

Image generation (gpt-image-2) and GPT-5 subagents for Claude Code — through the Codex CLI login you already have. No OpenAI API key.

Контроль качества 1С-разработки для Claude Code: стандарты, принципы ООП и паттерны, XML метаданных, блокирующие гейты и проверяемый след пр

Software engineering discipline grounded in named primary standards (OWASP, ITIL, IETF RFCs, ISO, BABOK, SBAR, and more), shipped as a Claud

Make Claude readable again. Three ready-made output styles for Claude Code, plus a picker command. Works in the terminal and the Desktop app

Skill-Atlas

One command to take a bare Windows or Mac machine to a working Claude Code setup — plus a plugin that keeps diagnosing it afterwards.

Cambium, LLM agent’larıyla sürdürülen bilgi depolarındaki işleri kurallar, durum kayıtları ve doğrulanabilir kanıtlarla yöneten bir governance standardı ve Python araç setidir.

Neden yükseliyor · 55 günde 457 yıldız ve son 28 günde 81 commit ilgi ve yoğun geliştirme sinyali veriyor; ancak farklı yazar sayısının 1 olması katkı tabanının dar olduğunu gösteriyor. Yıldızların ne zaman kazanıldığı verilmediği için yükselişin hızını veya nedenini doğrulayamıyorum; LLM agent’ları, auditability ve MCP kesişiminin ilgi çekmesi olası bir açıklama.

给AI伴侣增强时间感的小器官（电脑端专用）

Watch your Claude Code subagents work as a pixel-art office. Rewind any second, see what every agent cost, and turn any session into a timel

A creature for every git worktree, living in your coding agent's status line. Deterministic species, rarity bands, and one view across every

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

Stop agents from designing sloppy UI. Inspired by Impeccable, but without the plugin machinery. Just one SKILL.md file.