onlyshot
A Claude Code skill for producing AI short dramas, taking a rough idea through scriptwriting, storyboard images, video segments and an editing package. Aimed at creators making short-form video content.
4,248 plugins found in public marketplaces and GitHub repositories, indexed and searchable. Plugin skills also install in Codex, Cursor and 4 more agents. In Claude Code, the 99 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.
A Claude Code skill for producing AI short dramas, taking a rough idea through scriptwriting, storyboard images, video segments and an editing package. Aimed at creators making short-form video content.
An unappealing collection of Claude Skills and resources.
This guidance enables enterprise deployment of Claude Code and Claude Cowork on Amazon Bedrock across command-line (CLI) and desktop surfaces, with secure single sign-on (SSO), usage monitoring, and cost controls.
Orchestrates multi-agent workflows for Claude Code: runs parallel fan-outs, dependency-aware DAG flows, single agents, and saved playbooks, plus a systematic debug workflow for stuck problems.
Push it to GitHub and send us the link. We read it, then it goes live.
Given an investment theme such as AI data center power or HBM memory, this skill reverse-maps the supply chain to surface overlooked upstream bottleneck stocks. It is built on a publicly shared method and is for research and education only, not investment advice.
Command-line tool for the Resend email API, usable by developers, AI agents, and CI/CD pipelines. Includes a skill for selecting a named auth profile when managing multiple accounts.
Lets your AI assistant search a catalog of open source STEP files for standard hardware and components such as screws, bearings, motors and connectors, then evaluate and download the ones you need. Saves you from hunting through manufacturer sites for CAD models.
ABAP FS is a Visual Studio Code extension for ABAP development with AI assistance.
A personal AI assistant with voice, screen and meeting support that learns your patterns and can update its own code. It runs across several Macs and can talk with other people's assistants.
Lets Claude Code create narrated audio episodes with chapters, images, links and a cover, then publish them to Spotify. Useful for daily briefings, language lessons or meeting recaps, and it can also configure chapter-skip playback.
A Claude skill that refactors code to reduce cyclomatic complexity, so it stays readable and maintainable over the long term. It targets AI-generated code that works but has tangled branching.
Playwright skill for writing, debugging, and scaling end-to-end, API, component, visual, accessibility, and security tests, with guidance on CI/CD, page objects, trace debugging, and migration.
Runs BMAD planning workflows for Claude Code users, with brainstorming, document distillation, prose and structural editing, and advanced elicitation to refine recent output. Includes agents for autonomous Ralph runs.
A local MCP server that lets an AI agent control the desktop on Windows, macOS and Linux by reading screen text and UI structure, with screenshots as a last resort. It verifies each action and includes a safety gate.
Library for Jacobian descent with PyTorch. It enables the optimization of neural networks with multiple losses (e.g. multi-task learning).
Query robotics, drone, and IoT data in plain English through an MCP server, with an intelligent edge data reduction pipeline that keeps only the data that matters.
A senior engineering workflow layer for Claude Code. It helps you explore a problem before building, clarify what matters, capture the plan in living HTML, and then hand off to Claude Code's native planning loop, with skills for review, pattern abstraction, and finding more skills.
Gives a Claude Code user a local toolkit for finding and removing personal data from session transcripts before sharing them with the cloud. It can redact names and identifiers, audit a whole folder for leaks, and check whether redacted text can still identify someone.
Gives an AI coding agent the Convex rules a builder would otherwise correct by hand, such as using indexes instead of filters, validators on every function, and safe migrations. Works with Claude Code, Codex, Cursor and other tools that read SKILL.md files.
Lets an AI agent run end-to-end tests on a running app across Flutter, React Native, iOS, Android, Electron, Tauri and more. It connects over MCP so the agent can take screenshots, tap elements and enter text from plain English instructions.
Searches for and downloads images and video clips from a plain language description, and can trim the clips automatically. Use it when you need media pulled in and cut for a project.
Skills for building Convex apps with Claude Code, covering AI agents on the Convex agent component, production patterns and lint rules, reusable components, scheduled jobs and cron tasks, and keeping changes scoped to the request.
Zenith is an agent harness for long-running work that may last days or weeks, with skills for browser-based user-flow validation, benchmark and scrutiny validation, and mission playbooks for engineering and optimization tasks.
Helps hardware teams turn product requirements into a reviewable, buildable PCB design plan. Covers embedded architecture, MCU or SoC selection, power tree, interfaces, sensors, connectivity, and BOM risk.
A skill that helps Claude Code apply VueUse composables when building Vue.js and Nuxt features, aiming for concise and maintainable code.
Builds a personal knowledge base from your Claude Code, Codex CLI, Cursor, Gemini CLI, and Obsidian sessions. Ingest documents, query your past work, and sync session transcripts into the wiki.
A thinking partner that analyzes problems and reviews decisions through the mental models and communication style of Charlie Munger, drawn from his speeches, shareholder meetings and interviews. Useful for investing and for anyone who wants a critical second opinion.
Production-grade robotics knowledge for AI coding agents. Drop these SKILL.md files into Claude Code, Autohand Code, Cursor, Copilot-style agents, or custom agent frameworks to make them generate better ROS1/ROS2 software: safer nodes, correct QoS, lifecycle.
Task tracking for AI agents. Persistent memory for complex, multi-session work.
Gives Claude Code a long-term memory layer with semantic search, recall injection, and graph entities, letting agents recall, save, inspect, and audit memories through bundled MCP tools.
Gives security testers ready-made wordlists, fuzzing payloads, sensitive data patterns and LLM test prompts for authorized penetration testing, bug bounty work and CTF challenges, so the agent can reach for them without you hunting them down.
Searches a codebase by meaning and keyword together, with neural reranking, to find implementations, answer questions grounded in source code, and keep memory across sessions.
Skills for building Android apps that work with Meta AI glasses, covering camera streaming, photo capture, audio streaming, Kotlin conventions for the Device Access Toolkit, and live documentation search through an MCP server.
A Ghidra-powered skill that lets Claude Code perform reverse engineering on binaries: decompiling functions, tracing call graphs, renaming and annotating symbols, and diffing binary versions.
Gearsystem is a very accurate, cross-platform Sega Master System / Game Gear / SG-1000 emulator written in C++ that runs on Windows, macOS, Linux, BSD and RetroArch, with an embedded MCP server for AI debugging and development.
Lets you ask a trading question in plain English and get back earnings dates, company financials, option Greeks and account balances from your Interactive Brokers account, so you stop switching between broker, screener and spreadsheet tabs.
Style-driven Codex Skill for turning documents, articles, and visual references into image-first presentation decks.
Observes your Claude Code sessions to learn recurring behaviors as instincts, then surfaces relevant ones when you start a task. Keeps context across sessions and can export or import what it has learned.
Lets an AI assistant inspect and control a running Flutter app, reading its widget tree and driving it at runtime. Works as a Dart MCP server paired with a Flutter package, for debugging and validating apps.
Manages Alibaba Cloud resources from Claude Code, covering ECS, OSS storage, SLS log queries, and DashScope models. Fires when you provision a server, query logs, or call Qwen, Wan, or CosyVoice APIs.
A collection of Claude skills distributed as a Claude Code plugin marketplace. Skills are primarily designed for the Claude.ai PaaS skill compute environment; mileage will vary if used as Claude Code Agent Skills.
A set of skills that helps coding agents like Claude Code do software iterations well, from defining the real problem through to verifying results. Covers code review, architecture analysis, entity model auditing, and challenging or pressure-testing proposals.
Reads and writes GEDCOM X genealogy data for family history records. Fires when you parse, convert, or validate family tree files.
Compares symbols, types and syscalls of Windows binaries across OS versions and patch levels, using a web UI or an LLM skill to generate and interpret security-research diffs.
A desktop app that lets you run Claude Code, Codex and other ACP-compatible coding agents side by side in one window, without losing context when you switch between them. Tool calls appear as readable cards with diffs and terminal output, and each project gets its own terminal, git and MCP panels.
A set of skills for SEO work, covering content briefs, E-E-A-T page audits, expert interviews, featured snippet optimization, and rewriting underperforming pages. It suits marketers and content writers who plan and refresh search-focused articles.
Searches Korean government and public agency support programs such as startup funding, incubation space, R&D grants, and vouchers. Sorts matches against your project profile into immediately eligible, eligible if requirements are met, or eligible with changes.
Benchmarks and optimizes code for performance using CodSpeed, with CPU-simulated measurements, differential flamegraphs to find regressions commit by commit, and PR status checks. Includes skills to set up benchmark harnesses and to optimize code iteratively.
Claude Code artifacts graded by Skill Crossroads, click the badge for the evidence-cited scorecard. Your Complete Guide to AI-Powered Productivity.
Skills and agent plugins that let AI coding agents such as Claude Code work with Databricks, covering AI Functions, Agent Bricks, AI/BI dashboards, GPU training workloads and Databricks Apps design.
An MCP server that lets Claude read, search, organize, and send email over IMAP and SMTP. It runs on Windows, macOS, and Linux, and includes a skill for safe email operations and account setup.
A business research router that runs an industry analysis for questions about market structure, supply chains and outlook, or a company analysis for questions about how a firm earns money, its financials and whether it is worth investing in or joining.
Gates agent actions behind configurable approval policies and writes an audit trail. Fires when the agent calls a tool, edits config, or hits a policy-flagged action.
Gives security testers ready-made attack material for authorized work: fuzzing payloads, common password lists, sensitive-data patterns, exploit test files, and LLM safety test prompts. Pulled from SecLists and usable directly from an AI coding agent.
Spec-driven development skills for Claude Code, Cursor, Codex, and Antigravity. By Fernando Herrera.
A dashboard for viewing and managing memories, skills, MCP servers, hooks, and configs across Claude Code and Codex CLI. It also offers security scanning, context budget tracking, and backups.
Spec-driven workflow skill for Claude Code that turns requests into a plan, act, verify loop with durable specs and evidence kept in your repo. Covers project setup, change routing, validation, and archiving.
Your Claude Code usage, at a glance. 5h / 7d rate-limit bars, reset countdowns, model, context window, and prompt-cache freshness, inline in Claude Code's status line. Claude Code tells you almost nothing about where you stand against your rate limits.
A meta skill for Claude Code that turns a rough workflow, prompt, SOP, or old skill into a discoverable, tested skill. It covers design, trigger evaluation, format checks, README generation, and release steps.
Live data for AI agents, search, research, markets, crypto, X/Twitter. Pay-per-call via x402 micropayments.
Connect AI agents to Autodesk 3ds Max through the Model Context Protocol. Automate everything!
A session log viewer for Claude Code that browses and tails local JSONL files stored in ~/.claude/projects/. It also includes a cut-release skill that automates versioned releases.
Gives an AI assistant packet analysis through Wireshark and TShark. Drop in a pcap or pcapng capture, ask questions in plain English, and get answers backed by real TShark data for network troubleshooting and security investigation.
Helps a bioinformatics or biostatistics analyst run common analyses in Claude Code, from Bayesian models and survival analysis to statistical tests with reporting and regression. Each analysis is guided step by step instead of built from scratch.
Turns long videos into short vertical clips for social media. Claude picks the most engaging moments, transcribes the audio, and renders the clips with animated captions.
Automates repeatable founder work such as cold emails, pitch decks, call prep, contract review and job descriptions, so you spend less time on routine tasks. Covers fundraising, sales, legal, engineering and growth.
A security knowledge base for Claude Code that answers questions on business risks, evasion methods, attack tools, threat actors, and industry terms, with example cases. Useful for security teams doing risk review or red-team planning.
Detects AI writing patterns in Korean, English, Chinese, and Japanese text and rewrites them so the result reads as if a person wrote it, while checking that the original meaning is preserved.
Audits a codebase for serious bugs such as data integrity problems and trust boundary flaws, and explains existing code changes or GitHub issues in plain language. Helps you judge what changed and what to build before you act.
A two-pass pipeline for removing the signs of AI writing from outward-facing text, packaged as Claude Code Skills. Most humanizers only fix words. That is the easy half, and it is the half that is decaying fastest.
An exam-prep tutor for Claude Code that takes your lecture slides, notes, homework and past papers, teaches chapter by chapter with page citations, shows the figures, and quizzes you with your own material.
Runs named, repeatable multi-step workflows such as code review, research and spec checks, where several agent workers each handle a step and pass results along. Each run is recorded so you can inspect, stop or resume it, and you choose a workflow and describe the task in plain language.
Coordinates multiple Claude Code agents to run tasks in parallel, with automated quality gates, a simulated expert board for major decisions, and planning and code-review workflows. Aimed at developers building larger multi-step projects.
Persistent Linux workspaces for software development. container gives each project its own Docker or Podman environment, with coding harnesses and development tools already installed. Workspaces persist across sessions, including packages and configuration.
Runs AI-powered multi-agent code review, with a customizable team of reviewer personas that discuss the changes and can post findings to GitHub pull requests. Useful for developers who want several reviewer perspectives on a change.
Turns a one-line video request into a reproducible video project covering source material, storyboard, subtitles, transitions, motion effects, rendering and quality checks. Built for Claude Code users who want to make or edit videos from a short prompt.
An MCP server that lets an AI assistant analyze RenderDoc GPU frame captures, inspect shaders, pixel history and pipeline state, and diagnose black screens or visual artifacts.
Gives you ready-made prompts for common work such as testing, access control and sprint planning, so you can get expert-style help from an AI assistant without writing the prompt yourself.
A Claude Code skill for generating and editing images using the Gemini CLI's nanobanana extension.
An agentic skill that iteratively optimizes GPU kernels for maximum speedup, with benchmarking. Works with CUDA, Triton, TileLang and C++ code for developers tuning kernel performance.
Helps physicians and medical researchers plan and check clinical research in Claude Code, from literature search and study design to statistics, figures, manuscript drafting and reporting-guideline checks. Scripts recompute results, but a qualified researcher still reviews every output.
A model gateway that routes Claude Code requests across providers, translating between API protocols and adding usage analytics and remote control through messaging apps. Includes skills for UI preview and SDK updates.
Creates hand-drawn architecture, workflow, and swimlane diagrams in dark neon or light paper styles, with editable Excalidraw sources, PNG previews, and animated GIF output.
A personal setup of Claude Code and Codex instructions, bundling a browser automation tool for working with websites, a Bun guide in place of Node.js tooling, a Chrome Web Store release setup walkthrough, a cleanup pass that strips AI-generated code clutter from a branch, and a favicon generator.
Gives Claude Code and Codex a ready kit for browsing and filling websites, cleaning up AI-written code, generating favicons, and setting up Chrome Web Store releases.
A Claude Code workspace layer that remembers context across sessions, keeps its own state current, and maps code structure. Includes a help skill that explains the base CLI and its commands.
A Claude Code skill for black-box penetration testing of web apps and APIs, running several agents in parallel to fingerprint targets, crawl, test for vulnerabilities including business logic flaws, and produce a security report with remediation advice.
Skills for AI coding assistants writing Jetpack Compose for Android, covering state, side effects, modifiers, Navigation, Paging, coroutines and animations. Also includes an audit skill that checks Compose code for performance and state issues.
Monitors a Laravel application's performance by collecting metrics and sending them to the hosted Nightwatch platform. Lets you control sampling, filtering and redaction of sensitive data so you see what matters without flooding the dashboard.
A Claude Code skill that turns a dream description, diary entry, or spoken dream into cinematic video prompts, submits them to the Jimeng platform through browser automation, and downloads the finished video files.
Connect Claude to Korea's MOLIT real estate API and simulate buy now / buy later / invest only scenarios based on your income, savings, and retirement goals.
Gives Claude Code working knowledge of AWS, covering CDK infrastructure code, serverless design, cost analysis with CloudWatch and CloudTrail, and Bedrock AgentCore agents, so AWS tasks go faster with less manual lookup.
A Claude Code plugin for stock investment research. It guides a structured due diligence process with skills for refining stock questions, running parallel research agents, and validating citations in the final report.
The one place for the skills, keys and memory of every agent you use. Formerly OMNI.
Crypto trading, wallet management and AI market analysis through the Minara CLI. Covers token swaps, perpetual futures, transfers, deposits, withdrawals, limit orders and autopilot trading.
Gives Claude access to device features such as the clipboard, contacts, call log, location, dialogs, and device controls like vibration and battery status. Adds skills for haptic feedback, flashlight, and quick status checks on a phone.
Project memory workflow for Claude Code that keeps project context across sessions, with setup, session-end logging, document archiving, and versioned update logs.
Persistent memory for AI agents that carries lessons across sessions, with a correction ledger and recurrence tracking. Offers session start and end, remember, recall and check tools through an MCP server.
A multi-agent team operating system for Claude Code, with skills for running structured meetings, a shared task wall, persistent team memory, and cross-session messaging between Claude Code and Codex. It also includes a release checklist and workflow guidance for orchestrating sub-agents.
Gives AI coding agents like Claude Code and Cursor your team's shared engineering rules and architecture context, so they stop guessing from a few open files. The instructions are versioned in Git and can run inside your own perimeter.
Gives Claude Code direct control of an existing Chrome browser through the Chrome DevTools Protocol. It handles multi-tab management, form automation, and content extraction, and can run as a skill or as an MCP server.
An email marketing operating manual for AI agents, with hard send-safety gates. It helps plan, write, design, audit and send campaigns, newsletters, welcome series and abandoned-cart emails.
A skill for Claude Code that designs a brand identity as one system: logo, typography and colour palette built together from one idea, measured, shown side by side as identity cards, and handed over as a brand guidelines kit for the set you pick.
Helps your coding agent surface what you don't yet know before work starts: hidden assumptions, blind spots in unfamiliar code or domains, and risky technical guesses. Each finding is caught early, while it is still cheap to fix.
Guides your AI research agent through a disciplined analysis workflow, from framing a question and planning the analysis before touching data, to investigating anomalies, running parallel checks and executing a pre-registered plan with review checkpoints.
Official AI skills for PixiJS. These skills teach AI coding agents how to correctly use PixiJS.
See which of your agents is working, stuck, waiting on another one, or burning tokens, across all your Claude Code, Codex, Mistral Vibe and Cowork sessions, at zero token cost.
A Socratic teaching skill that guides you to discover answers yourself through questions instead of receiving direct answers. It triggers when you mention Socratic or Socrates in a message.
A modular plugin collection for Claude Code offering skills, agents, commands, and MCP servers for Java, TypeScript, Python, PHP, and AWS work, plus RAG, prompt engineering, and CloudFormation patterns.
A security plugin with skills that help AI coding agents write secure code, guide migration of C and C++ code to memory-safe languages, and produce markdown security review reports for a repository.
Helps Claude Code users find, compare, audit, and install reusable agent skills before an agent acts. Activates when a user asks for a skill, plugin, or a tool for a task.
Runs tasks from a task file on its own when your Claude usage window reopens, so queued work gets done without you starting each session. It uses permission-skipping autonomous mode, so review the tasks before you leave it running.
A content audit tool for Chinese social platforms like Xiaohongshu, Douyin, Kuaishou, WeChat Channels and Bilibili. It checks an account against similar creators, breaks down viral videos, and drafts rewrite scripts, plus generates sourced product scripts for commerce accounts.
A Claude Code plugin that helps freelancers and employees in Japan file income and consumption tax returns, from bookkeeping through entering data into the NTA e-Tax preparation corner. It also works as a Agent Skills package for other AI coding agents.
© 2026 Flowy
Built for Claude Code · Not affiliated with Anthropic
Logos are trademarks of their owners.