The best plugins are on Flowy :)

A Claude Code / OpenClaw skill for generating video clips with Chinese video models across four providers — Alibaba Bailian (Wan/PixVerse/Kling/Vidu/HappyHorse), Volcengine Ark (Jimeng/即梦), MiniMax (海螺 AI), and Tencent Hunyuan (混元).

Production-ready Claude Agent Skills for social media managers, paired with the Planable MCP server and — for the cross-channel skills — the SE Ranking MCP server.

Quality gates for Claude Code. An agent should never grade its own work, outbound content should be pretested before it costs you money, research should be grounded in more than one perspective, and the reasoning behind a hard solve should outlive the session

My global Claude Code setup, mirrored from ~/.claude: the rules, the hook scripts that enforce them, and the global CLAUDE.md.

One line in, a gold-quality image prompt out. image-prompt turns a short idea into a structured, copy-paste-ready prompt for any major image model: posters, landing and UI mockups, ads, editorial, game art, logos, infographics.

Claude knows React. It doesn't know why your pod install just failed. A Claude Code plugin that adds the React Native knowledge you only get from shipping apps: build failure triage, SDK upgrades that don't eat a weekend, Hermes crash decoding, push

A Claude Code plugin that enables powerful data transformation and export using DuckDB SQL.

CSW takes a ticket from your tracker to a merged pull request, then cleans up after itself. Superpowers owns how the work gets done. CSW owns *how it gets shipped and closed out*. This is one person's idiosyncratic workflow, and it is probably not yours.

A growing collection of GTM skills for Claude Code, built by 5050Growth. Skills you can drop into Claude Code (or run as plain Python) to handle the GTM work that doesn't justify a SaaS subscription.

Two composable, tool-agnostic skills for design-to-code fidelity — get the real design out of Figma, then prove the running app actually matches it.

Your docs can never lie again. You change code and the README quietly stops being true. Nobody notices until a stranger does.

Loop engineering plugin for Claude Code — instead of steering the model with ever-longer prompts, design loops where it self-corrects from environment feedback and accumulates memory across sessions.

6-step workflow: Plan → Review → Finalize → Code → Deep Check → Audit. Run all at once, or step-by-step and switch models between steps.