agentleFS
Starlight-IntelligenceStarlight-Intelligence/starlight-agent-skills/skills/studios/media-studio/SKILL.md

media-studio

Skill1 starsChanged 4 months agoMITView on GitHub

Create original music, art, motion, video, sound packs and licensable media collections with governed creative direction, masters, provenance and technical QC. Use when producing or packaging media, cinematic derivatives, release assets, scores, stems, captions or commercial licenses.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create distinctive media with durable editable masters, controlled generation spend, complete rights provenance and channel-ready …

    line 11
  2. Distinctive:

    Run taste, originality, continuity, similarity, brand, audio/visual technical, accessibility, caption, checksum and rendition inspection.

    line 32
  3. Distinctive:

    Use GitHub for specifications, policy, manifests and receipts.

    line 42
  4. Distinctive:

    Every asset and contributor is traceable.

    line 47

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Media Studio

Purpose

Create distinctive media with durable editable masters, controlled generation spend, complete rights provenance and channel-ready renditions.

When it fires

  • Producing original songs, scores, albums, art packs, motion graphics, videos, sound packs or licensed media collections.
  • Enriching a product or world with governed music, visual, motion or video assets.
  • Preparing Bandcamp, distributor, BeatStars, Canva, Creative Market, Gumroad, itch.io or owned-store packages.

Inputs

  • Product manifest, Media Studio task envelope, creative brief and exact source revision.
  • Pinned brand/design pack, approved reference registry, asset IDs, rights/consent/split records, external credit ceiling and target channels.
  • Prior masters, continuity rules, release metadata and known restrictions.

Workflow

  1. Resolve the product, Media Studio pack, media policy, design authority and channel adapters. Distinguish canon, references, generated layers, factual UI/text and approved owned assets.
  2. Bind emotional premise, audience effect, medium, constraints, exclusions, token budget and external credit/cash ceiling. Do not spend without an explicit envelope.
  3. Assign creative direction, production, continuity, rights and independent technical verification to distinct owners.
  4. Preflight references, consent, samples, contributor splits, inbound licenses, model/tool terms, attribution and prohibited uses before irreversible production.
  5. Produce editable source and masters. Composite typography, logos, factual data and partner marks deterministically from exact approved assets rather than asking generative tools to imitate them.
  6. Run taste, originality, continuity, similarity, brand, audio/visual technical, accessibility, caption, checksum and rendition inspection.
  7. Compile channel-specific masters, previews, metadata, licenses and instructions while preserving one work identity and rights record.
  8. Emit an evidence receipt with prompts/tools where relevant, contributors, versions, spend, QC, approvals, placements, takedown and remaining human decisions.

Output contract

Return creative premise, editable masters, approved renditions, asset/cue sheet, rights and provenance record, channel packages, spend actuals, technical/taste evidence, release receipt and release decision.

Tools and MCP

Use GitHub for specifications, policy, manifests and receipts; Drive for private masters and review handoff; Figma/Canva for governed deterministic layouts; Remotion or HyperFrames for code-driven motion; specialist audio/video tools for production and mastering; and runtime storage only through the accepted media-fabric contract.

Quality bar

  • The work has an authored premise and survives a substitution test.
  • Every asset and contributor is traceable; samples, voices, marks and likenesses are controlled.
  • Editable masters, delivery masters, previews and metadata agree.
  • Human sensory review complements technical checks.
  • Publication, paid generation beyond the envelope, licensing grants and minting remain explicit human gates.

Built on SIP — Starlight Intelligence Protocol Vertical: federated-product-studios · portable capability layer

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.