agentleFS
Sign inStart free
iceplandicepland/creative-intel/skills/creative-intelligence/SKILL.md

creative-intelligence

Skill2 starsChanged 3 months agoMITView on GitHub

Analyze ad creatives from AppGrowing, Meta Ad Library, TikTok Creative Center, screenshots, CSV exports, JSON exports, URLs, or local creative folders. Classifies image and video ads by creative format, value proposition, proof mechanism, and audience motivation, then generates privacy-safe HTML, Markdown, or structured reports. Use when analyzing ad creatives, competitor creatives, material libraries, hooks, captions, creator ads, UGC ads, product ads, or creative patterns.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. freshpomelo/agent_skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 7 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill to turn ad libraries and creative exports into structured, privacy-safe creative intelligence reports.

    line 8
  2. Distinctive:

    Always label reports as sanitized if data has been generalized.

    line 62
  3. Distinctive:

    Do not include cookies, tokens, raw request headers, private API payloads, or paid-platform raw exports.

    line 63
  4. Distinctive:

    Use exposure ranges when public sharing is requested.

    line 64
  5. Distinctive:

    Keep AppGrowing or other source links only when they are public or user-approved share links.

    line 65
  6. Very specific:

    When exact data is missing, mark it as not captured instead of inventing numbers.

    line 67
  7. Distinctive:

    Prefer reusable creative patterns over generic marketing commentary.

    line 72
  8. Distinctive:

    Keep public reports clear enough for non-technical marketers to read.

    line 74

≈ “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

Creative Intelligence

Use this skill to turn ad libraries and creative exports into structured, privacy-safe creative intelligence reports.

The default output should feel like a reusable creative case library, not a raw screenshot dump.

Core Model

Analyze every creative through four dimensions:

Creative Intelligence = Creative Format + Value Proposition + Proof Mechanism + Audience Motivation
  • Creative Format: image, video, GIF, carousel, UGC, creator, produced video, app UI, product demo, testimonial, CTA card.
  • Value Proposition: classify with the universal taxonomy in value-proposition-taxonomy.md.
  • Proof Mechanism: identify how the ad proves its promise, such as numeric claim, app screenshot, live demo, before-after, social proof, expert proof, or brand proof.
  • Audience Motivation: explain why the audience would care, such as saving money, reducing risk, saving time, gaining status, feeling safe, or trying something new.

Workflow

  1. Identify the input source:
    • AppGrowing URL or material page
    • Meta Ad Library page/export
    • TikTok Creative Center page/export
    • CSV/JSON export
    • screenshot/browser capture
    • local folder of creative assets
  2. Choose the output mode:
    • quick read: short summary and top patterns
    • case library: image and video case studies
    • public report: sanitized HTML or Markdown
    • release review: public-sharing risk scan
  3. Normalize fields into the shared schema in source-connectors.md.
  4. Separate true video from image-like formats:
    • image: static image, GIF, carousel, multi-picture
    • video: playable video or platform video creative
    • unknown: insufficient evidence; mark for manual review
  5. Apply the privacy rules in data-privacy.md before creating any shareable output.
  6. Classify each creative:
    • creative format
    • value proposition
    • proof mechanism
    • audience motivation
    • visible caption and translation if relevant
  7. Generate the report:
    • Core conclusions
    • Image value proposition and type breakdown
    • Image case studies sorted by estimated exposure range
    • Video value proposition and type breakdown
    • Video case studies sorted by estimated exposure range
    • Reusable creative patterns
    • Source and privacy notes

Output Rules

  • Always label reports as sanitized if data has been generalized.
  • Do not include cookies, tokens, raw request headers, private API payloads, or paid-platform raw exports.
  • Use exposure ranges when public sharing is requested.
  • Keep AppGrowing or other source links only when they are public or user-approved share links.
  • Translate visible non-English captions into the report language when the user asks for localized analysis.
  • When exact data is missing, mark it as not captured instead of inventing numbers.

Report Voice

  • Be specific and case-based.
  • Prefer reusable creative patterns over generic marketing commentary.
  • Explain why a creative works in terms of user motivation and proof.
  • Keep public reports clear enough for non-technical marketers to read.
  • State privacy assumptions explicitly.

Good Invocation Examples

Analyze this AppGrowing URL and create a sanitized image/video creative case library.
Compare these exported creatives across value proposition, proof mechanism, and audience motivation.
Review this report for public GitHub release risk before I publish it.

References

  • value-proposition-taxonomy.md: cross-industry taxonomy and vertical mappings.
  • data-privacy.md: anonymization and public-sharing rules.
  • source-connectors.md: input source handling and normalized schema.
  • report-template.md: recommended report structure.

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.

Check your setup, free