agentleFS
tesslagoblintesslagoblin/fashion-brand-claude-skills/skills/moodboard-queries/SKILL.md

moodboard-queries

Skill0 starsChanged 50 days agoMITView on GitHub

Produces Pinterest (or any image search) queries for a campaign moodboard: a frozen set of base queries per campaign mood, plus 2-3 campaign-specific queries, plus an optional pointer to a curated mood board. Trigger: moodboard, moodboard queries, Pinterest searches, reference images, vibe board, inspo for this campaign.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    Confirm the mood: No mood, no queries. Ask.

    line 35
  2. Very specific:

    Add the board pointer: if curated boards exist: Also check board: [Mood].

    line 40
  3. Distinctive:

    Every campaign gets a moodboard, including small ones, unless it is on the skip list.

    line 46

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Moodboard Queries

Gives your designer or your deck builder a ready list of image searches for each campaign. Base queries are fixed per mood so boards stay consistent; the model only adds the few queries that are specific to this campaign.

Setup

brand_reference: "[FILL IN]"     # the brand-guardrails reference (mood keywords live there)
search_tool: "[FILL IN]"         # e.g. Pinterest, Are.na, Google Images
curated_boards: "[FILL IN]"      # one board per mood, or "none"
skip_list: [FILL IN]             # campaigns or product lines that never get a moodboard, or []

base_queries:                    # frozen: 5 per mood, never regenerated per run
  "[Mood A]": [FILL IN 5 queries]
  "[Mood B]": [FILL IN 5 queries]

Inputs

  • Campaign name, mood, collection or product focus, and any event, place, or season it ties to

Workflow

  1. Confirm the mood. No mood, no queries. Ask.
  2. Pull the 5 base queries for that mood exactly as stored. No rewriting.
  3. Add 2-3 campaign-specific queries that pair the campaign's context with a visual style (e.g. "coastal linen editorial golden hour", "sailing club poster typography"). This is the only generated part.
  4. Add the board pointer if curated boards exist: Also check board: [Mood].
  5. New mood with no base row: build 5 base queries from the mood's keywords in the brand reference, add them to base_queries, and treat them as frozen from then on.

Rules

  • Every campaign gets a moodboard, including small ones, unless it is on the skip list.
  • Base queries are frozen. Consistency across months is the point.
  • Mix subject queries (outfits, products, scenes) with design queries (type, poster, color, texture) so the designer gets both.
  • Private boards cannot be pulled automatically. Output the board name for manual use.

Output format

Campaign: Coastline Weekend
Mood: Coastline
Base queries:
  - coastal linen outfit editorial
  - sun-bleached seaside photography
  - nautical stripe graphic design
  - hand-lettered beach poster
  - warm film grain summer moodboard
Campaign queries:
  - linen weekend packing flat lay
  - harbor town golden hour portrait
Board: Coastline

Example brand: Northwind Apparel.

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.