sdd-pipeline
A spec-driven development pipeline for Claude Code and Codex CLI. Refine the spec before you code, let TDD enforce it, verify nothing slipped, then review.
Claude Code plugins, indexed and searchable. The ones that get Auto-invokedWhat is this?This plugin ships a FLOW.md router the engine fires, so the matching skill runs itself. No slash command to remember.Learn how → fire as you prompt, and they are only on Flowy.
2,582 plugins indexed. 99 of them fire as you prompt.
A spec-driven development pipeline for Claude Code and Codex CLI. Refine the spec before you code, let TDD enforce it, verify nothing slipped, then review.
A set of 8 global skills for Claude Code that enforce disciplined, test-driven agentic development. Install once, use in any project.
A Claude Code plugin that reads your codebase and draws its infrastructure and architecture with D2, then keeps those diagrams in step with the code as it changes. Command: /d2:diagram
Reverse-engineered specification of FileMaker's undocumented fmxmlsnippet clipboard format. Every step ID, element ordering rule, and silent failure mode, established through empirical round-trip testing against production FileMaker solutions.
Push it to GitHub and send us the link. We read it, then it goes live.
Preserve non-UTF-8 file encodings and line endings when Claude Code edits your files.
Opinionated, first-party agent skills, plugins, subagents, slash commands, and MCP servers for the Litestar framework and its ecosystem — publishable to every major AI agent and IDE from a single repo.
A Claude skill that gives AI models a deterministic, empirically verified foundation for generating and analysing FileMaker Layout mode XML (fmxmlsnippet type="LayoutObjectList").
Gate documentation discovery in CI. Measure whether your project instructions change what agents do. Two concrete offers: CI gate — immediate. A deterministic, telemetry-free structural check fails a PR with the affected file and a suggested fix.
A Claude skill that restyles any ad or video into a completely different visual world — Aardman claymation, LEGO-style bricks, X-ray, 16-bit pixel art, Ghibli anime, felt puppets, voxel art, knitted yarn, premium Pixar-style 3D — while keeping every shot,
Four independently invocable product-development skills that work in both Claude Code and OpenAI Codex: spec turns an idea or draft into a reviewed, implementation-ready product specification and returns a link to the written artifact.
Claude-native, governed offensive-OSINT and external attack-surface platform for authorized security teams. Outrider is the governed front half of the offensive workflow.
An agentic software engineering method: AI agents do the building, the build enforces the rules that must always hold, a person decides only at the gates, and the method measures its own cost in human turns.
Local semantic and hybrid search for codebases and coding-agent history. Find implementation by intent, then recover the decisions and fixes that led to it across Claude Code, Codex, Cursor, OpenCode, and Pi sessions.
Spec-driven multi-agent orchestration for Claude Code — pure markdown, zero backend, runs on the stock runtime. 13 agents, 38 skills, 20 commands, 17 hooks, per-phase model tiers, opt-in lifecycle hooks, optional cross-device semantic memory.
Agent skill for building UIs with proper loading states, error handling, empty states, form UX, and graceful degradation
Türk hukukunda dilekçe ve savunma yazımını, hukuki argüman çerçevelerine göre yapılandıran yapay zeka skill'leri (Claude Code / AI ajanları için).
A plugin that helps you actually understand the code Claude Code writes for you.
Your tests check the paths you thought of. Polygraph checks the ones you didn't.
An open-source Claude Code plugin by The Agile Monkeys: a stack-agnostic issue-to-PR workflow with enforced quality gates. Also runs on OpenAI Codex, Cursor, and other Agent Plugins 1.0.0 clients.
A plugin for pi, Claude Code, and OpenCode that guides AI agents through disciplined Test-Driven Development and Clean Code practices. Note that currently this is WORK IN PROGRESS! I'm not even trying to keep it stable or tested.
191 attribution-first agent skills for Hermes Agent, Claude Code, Cursor — one installer, 28 categories, searchable catalog. See NOTICE for upstream attribution.
A personalized newspaper that knows only you will ever read it. OpenPaper is a Claude Code plugin that turns any collection of news sources into a single-reader daily newspaper.
Generate and edit images right inside Claude Code, powered by Google Gemini 3.1 Describe what you want. Get an image back. It's that simple.
AI assistant workflows for Amazon PPC diagnosis, growth planning, search-term harvesting, product-aware Rocketcart MCP reviews, masked optimization output, and approval-ready action queues.
You're a solopreneur. You have ideas, ambition, and not enough hours in the day.
Claudikins Automatic Context Manager - seamless context handoff for Claude Code
A self-learning, project-scoped sprint workflow for Claude Code. booping turns a feature idea into a durable, on-disk loop — groom → develop → retro → learn — that uses sub-agents to avoid context rot, with an optional second-model cross-review of every plan.
Auto-Harness is a Claude Code plugin for longer software tasks that need planning, implementation, QA, fixes, retests, and a final report. Give it a product brief.
A native Claude Code and OpenAI Codex port of OpenWiki — an agent that generates and maintains a documentation wiki (openwiki/) for any repository.
AI가 쓴 것처럼 보이는 한국어 초안을 문맥과 독자에 맞게 다시 다듬는 CodexㆍClaude Code용 글쓰기 스킬입니다. Humanizer KR는 번역투, 과한 홍보 문구, 명사화, 수동 표현, 어색한 높임, 챗봇식 전개를 찾아 줄입니다. 사실, 의도, 문단 흐름, 말투는 지키고 표현만 바꾸는 것을 원칙으로 합니다. AI 탐지기가 아닙니다. 표절을 숨기거나, 다른 사람이 쓴 것처럼 꾸미거나, 학업ㆍ채용ㆍ심사 절차를 우회하는 용도로 쓰면 안 됩니다.
구직할 때, 여러 플랫폼을 찾아다니지 마세요. 자동으로 수집하세요. Don't hop between job boards — let your agent collect them. 구직 중인가요? 잡코리아 갔다가, 사람인 갔다가, 원티드 갔다가, 점핏까지 — 매일 도는 일은 AI 에이전트에게 시켜버리세요. 22개 채용 플랫폼의 공개 공고를 하나의 정규화 JSON으로 모아줍니다.
Turn your agent into a mentor. It knows what you're working toward, and how you get in your own way.
Persistent memory, architectural decision enforcement, pre-execution safety hooks, and session handoff for Claude Code. MCP server plugin for AI coding agents.
Three AI models, one synthesis — Claude, Gemini & Codex cross-verify each other for rigorous multi-perspective research
A plugin for ADR-driven, documentation-led projects, working on Claude Code, Claude Cowork, pi, Codex, and OpenCode from the same skill files (see Install).
A virtual dev crew for Claude Code — 11 specialized AI agents that decompose, implement, review, and ship your tasks. Instead of one AI doing everything, CodeCrew breaks work into subtasks and routes each to the right specialist on the right model.
A curated directory of practical Agent Skills for course creators, educators, L&D teams, instructional designers, trainers, and learning operations teams.
Plan -> Critique (iterate) -> Execute -> Archive Iterative plan review and execution workflow for Claude Code, Agy (Gemini CLI), and GitHub Copilot CLI.
Durable contract-driven goal execution for Claude Code. A subagent judge gates completion against an explicit Definition of Done.
A multi-agent orchestration framework for Claude Code. Build production software with 7 specialized AI agents that coordinate automatically through a Hub Architecture.
Run Claude Code like an engineering org. Wave-based execution with dedicated sub-agents per phase, computed-style visual verification, no "tsc passes" lies.
A self-improving layer for Claude Code: it learns from your sessions, retains knowledge in a vault, and proposes skills/automations from recurring patterns. This repo holds the machinery (hooks, distill prompt + runner, dashboard, install config).
A Claude AI skill that builds ATS-optimised, human-sounding CVs in LaTeX — ready to compile on Overleaf in minutes. Built for job seekers who want a CV that passes Applicant Tracking Systems and reads like a real human wrote it. No AI filler.
Claude Code skills that turn an AI agent into a meticulous QA engineer. Your AI says "everything works, tests are green." Did it actually check?
Unified skill library for Claude, Codex, Cursor, Antigravity & AI agents — 2,658 skills across 15 domains
10 standalone QA agents for Claude Code. Each one answers a specific question about your PR — does this diff implement the AC?, what scenarios do I need?, which of my tests will break? — and writes a Markdown report you can paste into GitHub or Jira.
An MCP server for n8n that gives Claude, Cursor, and other AI agents tools for generating workflows, linting, diagnosing failed executions, and driving live n8n instances.
A personal Claude Code skill that stores your curated engineering rules and actively consults them before Claude drafts code. Complements Claude Code's passive auto-memory: memory surfaces facts when relevant, rules shape the approach up front.
Agent guidance for working with Preset, Apache Superset, and Superset MCP tools. The skills work across Claude, OpenAI Codex, Cursor, GitHub Copilot, Snowflake Cortex Code CLI, and Gemini CLI from a single source.
Arcgram turns your AI agent's plan into a diagram you can check and fix — before anything runs. Your AI agent can hand you something that looks right — an analysis, a workflow, a plan, code — while a broken step or a bad dependency hides underneath.
A collection of agent skills for working with HasData — a cloud platform for extracting public web data via SERP APIs, pre-parsed Scraper APIs (Amazon, Zillow, Maps, Indeed, Instagram, YouTube, Booking, …), and async Scraper Jobs (recursive crawling, contact
A multi-agent orchestration system for VS Code Copilot, plus maintained Codex, Claude, and Cursor plugins.
Pixel-faithful UI cloning skill for Claude Code, Cursor, Codex CLI, ChatGPT, and Copilot. Anti-hallucination contract + adversarial verification. Built on the SKILL.md open standard.
Control Codex and Gemini from the Claude App on your phone. You know /remote-control — the Claude Code feature that lets you control a session from the Claude App on your phone. URC makes it universal. One command, and your phone controls Codex.
Give Claude persistent, structured memory across conversations using your Obsidian vault. Read, write, search, and navigate your knowledge base — all from within Claude Code.
Six Claude Code skills + an unattended build loop, each measured with and without the plugin. 19/19 evals passing.
Interacts with WinForms UI elements and captures screenshots of headlessly rendered forms through an MCP server. Fires when automating or testing C# desktop UI without a visible display.
Build something meaningful, on Sui. A superpower for AI coding agents to ship real products on Sui. Your AI coding agent has never written Move before. Suiperpower fixes that.
A skill for managing Ghost blogs from Codex, Claude Code, and other agents that support Agent Skills.
한국어로 말하면 Claude Code가 알아서 실행합니다. 새로운 명령어를 외울 필요 없습니다. 설치 후 바로 한국어로 사용하세요.
Frog and Toad 精读课 studio — a Claude- and Codex-compatible skill that generates per-chapter teaching materials for Arnold Lobel's Frog and Toad series (I Can Read Level 2, ESL Grade 1).
Lauren is a live task queue for coding agents. Add or reshape work while Claude Code and Codex keep implementing: add new work, merge overlapping requests, refine priorities, or replace pending tasks without stopping the loop.
跨 Claude Code 与 Codex 两套 agent 的 skill 能力真源与同步规则。写入由 agent 执行,人只审校与决策。 把 Claude Code 与 Codex 的可复用能力收敛到一个仓库,按 platform-first 维护:每个平台独立持有自己的 skills/ 与运行约定,同名 skill 允许在两端并存,不强行抽象去重。 仓库要解决的是多端 AI 配置的漂移——GitHub 仓库、本地工作区、本地 CLI
A team-project AI harness bootstrap that gives humans and agents a shared operating contract from day one, moving AI leverage from an individual “IC superhero” advantage to a repeatable team capability on an equal playing field.
A linter for Claude Code projects. Validates CLAUDE.md files, skills, settings, hooks, MCP servers, plugins, and more.
The complete Claude Code plugin for Product-Driven Development Transform PRDs from ideas to shipped features with AI-powered review, guided implementation, and automated quality gates. Never ship unclear requirements again.
Gearbox is a Claude Code plugin that automatically routes subagent delegations to the cheapest model tier that can handle the work — haiku for search and mechanical edits, sonnet for standard implementation, opus for hard architectural problems.
Agent-native code review engine for Claude Code and Codex CLI, powered by Codex. xreview delegates code review to Codex (a separate AI model) so your coding agent gets an independent second opinion.
Open-source security arsenal for AI coding agents: 784 cybersecurity skills, scanner integrations, and a security MCP for Claude Code, Cursor, opencode, Gemini CLI, Cline, and any agentskills.io agent. Mapped to OWASP, MITRE ATT&CK, NIST CSF, D3FEND, ATLAS.
We assume you have the leaked source code of Claude Code, and it turns out that you cannot directly run it because it has some missing dependencies. This repository is right for you to make your source code work successfully.
Plan mode, but actually good. Spec Mint Core replaces ephemeral AI coding plans with persistent, resumable specs built through deep research and iterative interviews.
DotNet Episteme Skills - a curated, manual-first .NET AI skills library rooted in systematic knowledge (episteme) and shaped by disciplined craft (techne), designed for engineers who prioritise precision over hype.
AI phantom users that test your app the way real users actually use it.
A Claude Skill for revising draft prose — essays, papers, memos, reports — by finding the best structure for the ideas the author already wants to express. Its guiding principle is idea flow before linguistic flow.
연세대학교 생활에서 자주 반복되는 확인·정리 작업을 자연어로 처리하는 비공식 오픈소스 플러그인 모음입니다. 연세대학교 공식 서비스가 아닙니다. 학교 계정 권한을 늘리거나 수강신청·출석·예약 제한을 우회하지 않습니다.
Security skills for Claude Code. Install them once and ask Claude, in plain language, to scan a repo for leaked secrets, review Python code, red-team an LLM for prompt injection, or audit HTTP headers, JWTs, Dockerfiles, CORS, and dependencies.
A Claude Code plugin that turns a brief into a cinematic launch video, an investor pitch deck, or a feature walkthrough — with live FLIP morph transitions, audio bus, scene SFX, and a dev scrubber wired the first time.
🤖🧠 Agentic development workflow for AI–HI (Human Intelligence) collaboration
A Claude Code skill that delegates coding tasks to Gemini CLI and supervises the result. Claude orchestrates. Gemini codes. You review the diff.
The fastest, cheapest browser automation for Claude.
An auditable development workflow for AI coding agents: requirement contracts, implementation evidence, deterministic checks, and risk-matched review.
Report Skills is an AI report generator and AI report writer for Claude Code and Codex — a bundle of 5 skills that convert agent output (research, analysis, proposals, status updates) into live web reports, client reports, and slide decks with shareable URLs.
A Claude Code plugin providing comprehensive Rust development support through: rust-analyzer LSP integration for IDE-like features 16 automated hooks for code quality, security, and analysis Cargo tool ecosystem integration
A lightweight MCP bridge that lets Claude Code delegate heavy tasks to the Antigravity CLI (agy) - saving context window and tokens for what matters.
Claude orchestrates. Codex cross-checks. Blend Codex headless (codex exec) nodes into Claude Code's own Workflow (ultracode) orchestration — so a genuinely different model family verifies, judges, and second-guesses at the points where same-model agreement is
一个给 coding agent 用的 skill —— 装到 Claude Code / OpenClaw / Cursor 等编程代理上,当用户说"帮我搞一个 managed agent"的时候,这个 skill 会接管,照着 recipe 一步步调 Anthropic 新出的 Claude Managed Agents API,覆盖 create / run / audit 全流程:定义 agent + environment、跑 session、流式处理事件、审计 token 用量和事件链。 把自己搭
Four-layer long-term memory (L0 Conversation → L1 Atom → L2 Scene → L3 Persona) for Claude Code, inspired by Tencent/TencentDB-Agent-Memory. Fully local — no external Gateway, no paid API, no Python.
A Claude Code plugin marketplace by bgmacris. One plugin today — tandem: a Chrome browser shared in real time between you and Claude Code.
A Claude Code skill that produces decks worth sending — not "AI-looking" slide soup.
A growing collection of opinionated tools for shipping AI into real-world domains. Each tool ships in two shapes: a Claude Code skill, and an importable schema or library, so the same artifacts can be produced by an agent and consumed by an app.
A unified enterprise & software architecture skill for Claude Code, grounded in four open-source standards instead of one.
GKD 是「搞快点」的拼音首字母,也是三个当下前沿开源模型的首字母 —— GLM · Kimi · Deepseek。 GKD 是一个 Claude Code plugin。它借 Claude Code 自己的工具循环(harness),起一个以你指定的任意模型为大脑的子进程去干活——子进程有完整的 Read/Edit/Bash...
Forge — a solid harness-engineered workflow for Claude Code. Quality enforced by structure, not prompt discipline.
12 drop-in Claude project skills. Free, no signup. Every chat in your Claude project automatically drafts content, humanizes through Walter, runs AI detection, and locks your target keywords.
dwic (design with claude) puts a product designer inside Claude Code. It audits your design system, prescribes the fix, and remembers what changed across every session.
Universal setup for Claude Code and OpenAI Codex CLI — security hooks, notifications, status line, and skills.
Thirty-three skills that wrap around your development cycle in Claude Code. They turn tickets into ATDD plans, smoke-test features against a running app or service, hunt down bugs with runtime evidence, guard commits against doc drift, run seven-axis code
Orchestrated multi-agent research with architectural enforcement, parallel execution, and comprehensive audit trails.
Скилл превращает ИИ-агента в директолога: агент собирает ключевые слова, подбирает минус-слова, пишет объявления, задаёт стратегию торгов и ставку по реальному аукциону, а затем создаёт кампанию в кабинете Яндекс Директа.
Five reviewers pull your draft apart, keep their disagreement visible, and hand you one verdict — for the text you can't un-ship. A runtime-portable 5-agent council that adjudicates text artifacts before they ship.
Agent skills for the Dutch Government Developer Portal (developer.overheid.nl) knowledge base.
Audits LLM token usage and costs across code and prompts. Runs when invoked via the tokendiet command or skill.
AKA Security — We secure agent harnesses at the source. AI Traffic Control (ai-tc) is an open-source control plane for coding agents.
Turn a URL + CSS selectors into a finished visual — annotated screenshots, flow GIFs, smooth-motion recordings and terminal captures. One command each. The agent never guesses pixels; every output is pixel-verified before it's saved.
历史已经发生。李白必然离开长安。你改变不了结局——这正是沉浸的来源。 沉浸式历史叙事体验 Skill,由见证引擎驱动,支持多剧本扩展。 你不是旁观者,你是见证者——以不同深度在场,听到不同的历史。
AI 做 PPT,不是生成问题,是工作流问题。 一个 Claude / Codex 技能:从一篇文章、一段口播稿、一份课程内容开始,做出一套有风格、有逻辑、还能继续改的 PPT。
Sequential code review with fresh agent contexts. Each pass runs in an independent subagent, ensuring unbiased analysis that catches issues other passes might miss.
Reverse-engineered specification of FileMaker's undocumented schema definition XML, across all three definition catalogs: fields, tables, and value lists.
Скилл для Claude Code / Codex, который отвечает на главный вопрос вайбкодера: «а оно вообще работает?» Прогоняет ваше живое приложение автотестами, находит баги (репорт с severity: что критично, что терпит), отвечает «можно ли в прод» — и оставляет каркас
AI-native product management skills that move at the speed your team needs. Traditional PM frameworks were built for a world without AI — multi-week discovery sprints, day-long planning offsites, months of analysis before a decision.
Run containerized workloads across AWS, GCP, Azure, OCI, and your own hardware under one API.
A collection of Claude Skills for senior leaders and the people who work alongside them.
Craft quality software with AI discipline. Spec-driven development plugin for Claude Code and Opencode — quality gates, adversarial testing, and evidence capture.
Rugproof your code before someone else does. 🌐 Live site: omermaksutii.github.io/RugProof 📦 Latest: v1.0.0 — 45 commands · 23 agents · 45 skills · 13 MCP servers · tested, offline-first, with rule packs, a benchmark, non-EVM coverage, and post-deploy
Komplement-stack till Anthropics Claude for Small Business. Inspirerad av samma idé, byggd från grunden för svenska företag — med Bokio som finansiell motor och svenska regelverk som logik.
A free, open-source alternative to Surfer, MarketMuse, Clearscope & Frase — built as Claude Code skills. Topical authority, content briefs, AI writing, schema, GEO, and backlinks. With a fabrication guard that refuses to invent numbers.
An opinionated library of Flows. Free. Open source. V1.
© 2026 Flowy
Built for Claude Code · Not affiliated with Anthropic