Shape agent capabilities into your workflow.

Claude AI Music Skills organizes album concepts, sourced research, lyric writing, Suno prompts, stem processing, mastering, and release preparation through 53 skills and an MCP tool server that tracks project state. Music generation still happens in Suno, and the plugin requires macOS or Linux with Python 3.11 or newer; multi-track sessions can consume Claude usage limits quickly.

HeyGen Skills chains three agent workflows: creating a reusable digital twin from a photo, turning ideas or source material into scripted avatar videos, and translating finished videos with dubbed voice and lip synchronization. The skills can use the HeyGen CLI with an API key or a remote MCP connection through OAuth. CLI usage is billed as direct API consumption, while MCP uses credits from an existing HeyGen plan. Both paths require a HeyGen account.

TermCanvas places terminals on a zoomable spatial canvas organized by project, Git worktree, and session, making parallel coding agents easier to monitor. You can see agent state, reopen conversations, inspect diffs and repository status in place, and use the bundled CLI or Hydra toolkit to launch isolated workers. It runs as a desktop app on macOS, Windows, and Linux; the described cloud runtime is still a roadmap item.

AutoHarness is a lightweight governance layer for existing AI agents. It can wrap an LLM client, check tool calls for risk and permissions, sanitize outputs, record decisions, and manage context and token budgets. YAML rules select different governance levels, while multi-agent profiles, per-call cost attribution, and session persistence cover longer-running workflows.

This project turns existing ComfyUI workflow JSON files into callable agent skills. It imports and normalizes a workflow, maps only selected parameters through a schema, and lets an agent run, submit, inspect, or check dependencies through a structured CLI. A visual web interface supports configuration and testing, with routing to local or remote ComfyUI servers for OpenClaw, Hermes Agent, Codex, Claude Code, and similar tools.

Attach skill directories to an agent and let it discover metadata first, then load full instructions, resources, or scripts only when needed. The package supports standard filesystem skills as well as skills created programmatically in Python, exposed through capability or toolset integrations. It also validates skill structure, accepts multiple source directories, and includes safeguards against path traversal.

Install a portable collection that covers read-only PostgreSQL, MySQL, and SQL Server access alongside research, image generation, messaging, text-to-speech, DevOps, and Google Workspace tasks. The skills follow the Agent Skills standard and can be used across Claude Code, Cursor, Codex, Gemini CLI, and other compatible clients. Some integrations need their own service credentials, and the Google Workspace skills require a Workspace account rather than personal Gmail.

Skill Creator Ultra turns a workflow idea into a complete AI skill through an interview or a one-shot quick mode. Its eight-stage process extracts the knowledge, chooses an architecture, generates the package, runs tests and multidimensional evaluation, scans for security issues, iterates, and prepares distribution formats for several agent platforms. It is designed for users who do not already know YAML or SKILL.md, with English and Vietnamese as the documented interaction languages.

visual-style-ppt turns documents, articles, outlines, topics, or visual references into a style-led presentation workflow. It extracts or selects a reusable visual direction, plans the slide sequence, writes page-specific prompts, and generates each slide as a polished Image 2 image; those images can then be assembled into an image-only PPTX. The result prioritizes visual finish over editable PowerPoint layouts. Image 2 is mandatory for every generated page, and PPTX packaging also requires a compatible assembly environment.

Subtask adds a skill and CLI to Claude Code for creating tasks and running Claude, Codex, or OpenCode subagents in parallel, with a separate Git worktree for each task. Its terminal interface shows status, diffs, and conversations, while the lead agent reviews completed work and asks before merging. The project is still in early development, so installation and behavior may continue to change.

Superdesign is a product-design skill for coding agents such as Claude Code, Cursor, and Codex. It reads the current interface and code context, gathers style references, establishes a reusable design system, and creates branchable HTML drafts on a design canvas for new pages or redesigns. The complete workflow also requires the Superdesign CLI and a login, and it is separate from the archived legacy VS Code extension.

bencium-marketplace contains 14 installable skills covering UX design and audits, typography, marketing, software architecture, communication, and decision support. Users can add the full collection or select individual skills through the skills CLI. Because the packages use Markdown-based SKILL.md files, they can also be placed in the prompt or context directories of compatible tools such as Codex, Gemini CLI, and Cursor.

This installable Agent Skill gives coding assistants focused guidance for Playwright testing in TypeScript. It maps the current task to references for end-to-end, component, API, visual regression, accessibility, security, mobile, multi-tab, PWA, Electron, browser-extension, and internationalization testing. Other material covers CI, sharding, reporting, performance, and flaky-test debugging. Installed through `npx skills add`, it helps an agent choose suitable patterns; it does not replace Playwright or run tests by itself.

AWS Skills packages Claude Code plugins for CDK and SST infrastructure, serverless architecture, cost and operations work, and Bedrock AgentCore deployment. The plugins combine focused instructions, validation scripts, references, and AWS MCP integrations for documentation, pricing, Cost Explorer, and CloudWatch. The shared aws-common plugin is a dependency when components are installed individually.

TestMu AI Agent Skills add framework-specific testing guidance to coding assistants such as Claude Code, Copilot, Cursor, and Gemini CLI. The repository covers major automation stacks including Selenium, Appium, Playwright, and Cypress across numerous languages, with skills installable individually. Using the hosted testing platform requires Node.js plus a TestMu AI account, username, and access key.

software-design-philosophy is a reusable agent skill based on John Ousterhout's A Philosophy of Software Design. It gives coding assistants a design framework for code reviews, architecture discussions, API design, module decomposition, refactoring, naming, comments, and error-handling strategy. Users can install it in Claude Code, Codex, or compatible skill managers and invoke it alongside an existing project. The repository supplies guidance for making software-design decisions; it is not a standalone static analyzer or development application.

Social Media Skills provides a coordinated set of workflows for audience context, positioning, editorial calendars, platform strategy, post and thread writing, carousel scripts, visual-platform captions, repurposing, hooks, and performance analysis. It covers LinkedIn, X, Threads, Bluesky, Facebook, Instagram, TikTok, and Pinterest use cases, and skills can be installed together or selectively. With BlackTwist MCP it can publish, schedule, and fetch analytics; without it, the workflows remain advisory.

Dream-to-Video Skill converts a written dream into a cinematic prompt, places it in a local SQLite and JSONL queue, and drives Jimeng through Playwright and Chromium. The worker handles login, submission, progress monitoring, downloads, and an Elliptic Shatter edge effect, producing both original and processed video files. Setup requires Python 3.10+, Chromium, an API key for a supported language model, the repository toolchain, and a one-time QR-code login to Jimeng.