agentleFS
forsvn-labsforsvn-labs/meta-skills/skills/brief-creative/SKILL.md

brief-creative

Skill14 starsChanged 3 months agoMITView on GitHub

Create an implementation-ready creative brief. Use for landing pages, campaign graphics, product previews, screenshots, demo videos, short-form video, out-of-home, social media assets, or any design and production request that needs a clear communication job, concept, hierarchy, requirements, and acceptance criteria.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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:

    Ask only when a missing decision would materially change the concept.

    line 26
  2. Distinctive:

    Keep the brief precise about communication and flexible about craft decisions that belong to the creator.

    line 63
  3. Distinctive:

    When the user needs prompts or a production bundle, add one handoff per genuinely different asset:

    line 68
  4. Distinctive:

    Never invent a logo, product screen, person, metric, or customer.

    line 79
  5. Distinctive:

    Do not fabricate product UI, performance, customers, or consent.

    line 84

≈ “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

Brief creative work

Turn a marketing decision into a production brief that a designer, developer, photographer, or video creator can execute without guessing.

Define the communication job

Establish:

  • target audience and viewing context;
  • action or belief the asset must create;
  • one message hierarchy;
  • product mechanism and proof to make visible;
  • destination and campaign promise;
  • format, placement, dimensions, duration, language, and accessibility constraints;
  • available source assets and factual restrictions.

Ask only when a missing decision would materially change the concept. Label reasonable assumptions.

Choose one concept

Express the concept as a concrete relationship between message, product evidence, and form. A concept is not a mood-board adjective. Explain why the chosen form makes the claim easier to understand or believe.

Prefer:

  • product behavior, demonstration, comparison, or artifact as evidence;
  • one dominant idea and deliberate hierarchy;
  • native composition for the destination;
  • readable type, useful contrast, captions, and reduced-motion alternatives;
  • modular production that supports the required variants.

Reject arbitrary gradients, stock symbolism, decorative dashboards, fake UI, fabricated metrics, and visual novelty disconnected from the message.

Specify the production

Deliver:

  1. communication job and audience moment;
  2. single concept and why it works;
  3. frame, section, shot, or scene sequence;
  4. exact copy hierarchy and required product evidence;
  5. art direction: composition, imagery, typography behavior, color roles, and motion;
  6. asset inventory, source-of-truth files, and production constraints;
  7. variant matrix for formats that genuinely need different composition;
  8. accessibility and localization requirements;
  9. acceptance criteria and rejection conditions.

For a landing page, specify scan order, sections, proof placement, objection handling, and responsive behavior. For video, specify hook, beat timing, visual proof, captions, audio role, CTA, and end state. For product previews, distinguish representative mockups from shipped functionality.

Keep the brief precise about communication and flexible about craft decisions that belong to the creator.

Prepare a render-ready handoff

When the user needs prompts or a production bundle, add one handoff per genuinely different asset:

  • the exact output dimensions, aspect ratio, safe zones, crop behavior, and file format;
  • the exact copy strings to render, marked verbatim;
  • source assets by path or attachment, with explicit logo and product-UI grounding;
  • composition, subject, camera or illustration behavior, lighting, texture, color roles, and exclusions;
  • engine-specific syntax only when the target tool is known; otherwise use plain production language;
  • a variant table only where the concept or composition changes, not cosmetic prompt churn;
  • a verification checklist for copy fidelity, brand marks, product truth, legibility, accessibility, dimensions, and visible render defects.

Never invent a logo, product screen, person, metric, or customer. Use a labeled placeholder when a required source asset is absent. If the host has an image or video tool, render only when the user asked for production and the tool is available; review the actual output against the brief before delivery. Otherwise return the complete handoff without implying that an asset was rendered.

Do not fabricate product UI, performance, customers, or consent. Keep production orders, uploads, publishing, and external writes behind explicit approval.

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.