Anycap Media Production
Run a full AnyCap production loop—generate image, video, and music assets, refine with annotation feedback, and deliver finished creatives from the CLI inside your agent session.
Overview
anycap-media-production is an agent skill most often used in Build (also Validate, Launch) that runs the full AnyCap workflow from concept through delivery for image, video, music, and audio assets.
Install
npx skills add https://github.com/anycap-ai/anycap --skill anycap-media-productionWhat is this skill?
- Covers image, video, music, and audio from concept through delivery
- Supports text-to-media, image-to-image, image-to-video, and annotation-driven precise edits
- Iterative refinement workflow with interactive visual annotation and human feedback
- Explicit handoff: read the anycap-cli skill for command reference and parameters
- MIT-licensed; requires anycap CLI binary and internet access
- Skill metadata version 0.3.6
- Four media families: image, video, music, and audio
Adoption & trust: 1 installs on skills.sh; 33 GitHub stars; 2/3 security scanners passed (skills.sh audits); trending (+100% hot-view momentum).
What problem does it solve?
You need consistent AI-generated visuals and audio with iteration and precise edits, not disconnected one-off generation commands.
Who is it for?
Solo builders producing launch creatives, explainers, or product media who already install the anycap CLI and want agent-guided production discipline.
Skip if: Pure command cheatsheet lookups without a production goal—use anycap-cli only; also skip if you cannot run shell commands or allow network access to AnyCap.
When should I use this skill?
Creating images, videos, music, or audio with AnyCap—including iterative refinement, image-to-image, image-to-video, or annotation-driven edits—or when triggers mention media production, asset generation, or creative wor
What do I get? / Deliverables
You get finished, refined media assets delivered through a documented production sequence, with CLI details resolved via the anycap-cli skill.
- Finished image, video, music, or audio assets
- Iteratively refined visuals after annotation feedback
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Build is the primary shelf because the skill drives hands-on asset creation and iteration, which is where most solo builders first install generative media tooling for product and marketing deliverables. Docs fits as the canonical subphase because output is finished media and copy-adjacent assets (thumbnails, explainers, audio beds) rather than application backend code.
Where it fits
Generate hero images and short clips to test positioning on a smoke-test landing page before full build.
Produce tutorial screenshots, diagram art, and background music for in-app onboarding content.
Create ad variants and social video cuts, then refine frames via annotation-driven edits.
Refresh lifecycle email headers and blog visuals using the same iterative AnyCap production loop.
How it compares
A procedural production playbook for AnyCap, not a hosted design tool MCP—pair with anycap-cli for parameters.
Common Questions / FAQ
Who is anycap-media-production for?
Indie builders and content-heavy SaaS founders who want agent-guided AnyCap workflows for images, video, music, and audio with iterative human-in-the-loop refinement.
When should I use anycap-media-production?
In Validate when prototyping landing visuals; in Build when creating docs and product media; in Launch when producing distribution creatives—whenever you need generate image/video/music or annotate-and-refine cycles.
Is anycap-media-production safe to install?
It requires shell and network access to third-party generation services—review the Security Audits panel on this page and your API or CLI account policies before production use.
Workflow Chain
Requires first: anycap cli
SKILL.md
READMESKILL.md - Anycap Media Production
# AnyCap Media Production > **Read this entire file before starting.** It covers the full production workflow across image, video, music, and audio -- including iterative refinement with human feedback. Workflow guide for producing media assets with AnyCap. Covers image, video, music, and audio -- from initial generation through iterative refinement to delivery. This skill is about **how to produce media**. For CLI command reference and parameters, read the `anycap-cli` skill. ## Prerequisites AnyCap CLI must be installed and authenticated. Read the `anycap-cli` skill if setup is needed. ## Quick Reference | Media | Generate | Refine | Typical duration | |-------|----------|--------|------------------| | Image | `anycap image generate` | Annotate + image-to-image | 5-30s | | Video | `anycap video generate` | Re-generate with adjusted params | 30-120s | | Music | `anycap music generate` | Re-generate with adjusted prompt | 30-90s | | Audio | Coming soon | -- | -- | All generation commands follow the same pattern: ``` 1. Discover models anycap {cap} models 2. Check schema anycap {cap} models <model> schema [--mode <mode>] 3. Generate anycap {cap} generate --model <model> --prompt "..." -o output.ext ``` Always use `-o` with a descriptive filename. ## Image Production ### Text-to-Image Generate an image from a text prompt: ```bash anycap image generate \ --prompt "a cozy home office with a wooden desk, laptop, coffee cup, and plants by the window" \ --model nano-banana-2 \ -o workspace-v1.png ``` ### Image-to-Image (Edit / Transform) Use `--mode image-to-image` with a reference image to edit or transform an existing image: ```bash anycap image generate \ --prompt "make it a watercolor painting" \ --model nano-banana-2 \ --mode image-to-image \ --param images=./photo.png \ -o photo-watercolor.png ``` Reference images can be local paths or URLs. The CLI handles upload automatically. ### Multiple Reference Images Some models accept multiple reference images for style transfer, composition blending, or subject-driven generation. Use JSON array syntax to pass multiple files: ```bash # Combine style from one image with composition from another anycap image generate \ --prompt "merge the architectural style of the first image with the color palette of the second" \ --model nano-banana-2 \ --mode image-to-image \ --param images='["./style-ref.png","./color-ref.png"]' \ -o blended.png # Mix local files and URLs anycap image generate \ --prompt "a portrait in the style of the reference images" \ --model nano-banana-2 \ --mode image-to-image \ --param images='["./local-ref.png","https://example.com/style-ref.jpg"]' \ -o portrait-styled.png ``` Tips: - Use JSON array syntax `'["path1","path2"]'` -- repeating `--param images=` overwrites rather than appends. - Local file paths inside the array are auto-uploaded, same as single-file mode. - Not all models support multipl