Agent skills
Scopeful maintains 28 free agent skills. Each one teaches an AI coding agent (Claude Code, Cursor, Windsurf, Codex) how to drive one creative tool correctly. Install commands are public and need no sign-in.
- Leonardo API skill: Drop-in Claude Code skill for the Leonardo API. Generate, refine, and download images without writing scripts. Your agent reads the skill once and follows it every time.
- Run Higgsfield better: Routing playbook for every Higgsfield surface: 30+ models, Marketing Studio modes, Virality Predictor scoring, 4 workflows, prompt structure, polling and failure playbook. Points at the dedicated CLI and MCP install skills.
- Midjourney video skill: Generate, extend, and loop video with Midjourney's image-to-video.
- ElevenLabs TTS skill: Generate speech, clone voices, and transcribe audio with ElevenLabs via SDKs, REST, or MCP.
- Run Replicate models without burning compute: Pin the version, poll at 2-5s, use webhooks for long predictions, and pick the cheapest hardware tier the model fits on. Stops your agent from burning Replicate credits on cold starts and unpinned models.
- Run fal.ai models for speed: fal is built for latency. This skill teaches your agent the queue lifecycle, streaming primitives, model slugs, and SDK conventions so it stops hand-rolling HTTP.
- Run Runway Gen-4 cleanly: Teaches your agent the Runway API model lineup, task lifecycle, and the shot-list prompt grammar Runway actually rewards. Stops credit burn on guesswork.
- Kling AI REST API: 'Use this skill whenever the user wants to integrate Kling AI''s video or image generation REST API into application code, backend services, CI pipelines, automation, or scripts. Triggers on "Kling API", "Kling text-to-video", "Kling image-to-video", "Kling REST", "kling-v3", "kling-v3-omni", "kling-video-o1", "migrate to Kling from Runway", "migrate to Kling from Pika", or any task that calls Kling''s HTTP endpoints directly. Do not trigger for MCP or CLI surface; use the `kling` skill for that.'
- Run Flora MCP & API CLI: Teaches your agent how to use the Flora API CLI and MCP server to automate generation workflows across 60+ models.
- Comfy Agent — Self-Upgrading ComfyUI MCP: ComfyUI MCP with self-upgrading skill and shared memory. Your AI agent builds graphs, runs generations, and learns from every session across all agents.
- Connect AI Agents to Scopeful Pricing: Drop-in MCP server for Cursor, Claude Code, Windsurf and OpenCode. Query live AI pricing, compare models on the fly, and pull verified skills directly into your workspace.
- Query AI pricing from the terminal: Drop-in CLI for any agent that runs shell commands. Recommend, calculate, compare, and list AI tools and models via simple subcommands — no MCP config needed.
- Run Higgsfield MCP: Connect any agent to the real Higgsfield MCP (HTTP at mcp.higgsfield.ai/mcp). Config snippets for Claude Code, Cursor, OpenCode, Codex, Windsurf, Gemini.
- Kling AI MCP and CLI: 'Use this skill whenever the user wants to generate video or images with Kling AI from inside an AI assistant (Cursor, Claude, OpenClaw, Hermes, Codex, Copilot) or from a terminal via the official `kling` CLI. Triggers on "Kling MCP", "kling CLI", "kling --help", "npx skills add klingai", "install Kling", "Kling in Cursor", "Kling in Claude", or any task where the agent itself is the caller, not a backend service. Do not trigger for direct REST API calls from app code; use the `kling-api` skill for that.'
- Comfy Agent: MCP server that gives AI coding agents direct control of ComfyUI, with a floating browser panel and shared self-learning memory across agents.
- Image Audit: Audit repo images, references, duplicates, and oversized assets. Safe by default: /imageaudit is audit-only, /imageaudit fix is explicit apply mode.
- Meeting to Actions: Turn a meeting transcript or messy notes into clear action items.
- Humanize Writing: Make AI-written text sound human again.
- Media Converter: Convert, compress, resize, or trim video, audio, and image files.
- PDF Editor: Merge, split, and edit PDFs locally.
- Prompt For Me: Write, improve, or translate a prompt for any AI image, video, or voice tool.
- Resume Tailor: Tailor your resume or CV to a specific job.
- Screenshot Design Review: Get design feedback on a screenshot of your UI.
- Social Repurposer: Turn one piece of content into posts for every platform.
- Excel Cleaner: Clean, fix, and restructure a messy spreadsheet or CSV.
- Video to Tasks: Turn a screen recording into project-specific engineering tasks plus a paste-ready prompt for a coding agent. Local Whisper transcript, frames only where the screen matters, tasks grounded in your actual code.
- Run Higgsfield CLI: Install + auth + command reference for @higgsfield/cli. 30+ models, 4 workflows, Marketing Studio, Virality Predictor, Soul training, voices.
- AI Asset Organizer: Clean up, dedupe, and sort a folder of AI-generated images, recovering the prompts hidden inside.