agentleFS
adityareddy-devadityareddy-dev/deskstudio/skills/brand-kit/SKILL.md

brand-kit

Skill43 starsChanged 23 days agoMITView on GitHub

Build a brand kit from one or two colours, a name or a URL: three directions rendered as real work, one picked, written to brand/ and .desk/DESIGN.md. Use when a project has no brand yet or needs a proper one.

17 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use expert-pov, funnel-strategy and 4 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • matteotittaSkill

    expert-pov

    Extracts contrarian beliefs, market perspectives, and philosophical stances from founder interviews or questionnaire

    Also in 3 projects that use this

  • matteotittaSkill

    funnel-strategy

    Maps a company''s GTM motion (PLG, SLG, or Hybrid) to concrete funnel stages with inputs, outputs, and qualification

    Also in 3 projects that use this

  • growthack88Skill

    icp-research

    Scrapes case studies, testimonials, and solutions pages from a target website to build structured ICP documentation. Produces TAM analysis, firmographic segments, champion and economic buyer personas, use case mapping, customer proof points, and voice-of-customer synthesis with normalized attributes. Requires website URL as primary input. Upstream: recommended company-context. Downstream: feeds positioning, product-messaging, landing-page-copy, content-strategy, and outreach-emails.

    Also in 3 projects that use this

  • nocodeworkSkill

    company-context

    Interview the user to build or update a reusable company context file for AI tools — what the company does, its offer, clients, personas, positioning, voice, and the questions clients ask most. Use when the user says "build our company context", "create company context", "set up business context for AI", "update our company context", or wants AI to answer clients and write content in the company's voice without re-explaining the business each time. Produces company-context.md.

    Also in 3 projects that use this

  • YepAPISkill

    competitor-research

    Competitive analysis between domains using YepAPI.

    Also in 4 projects that use this

  • +1 more from matteotitta

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 15 edited versions we read keep these.

  • 0

    Distinctive

    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. Very specific:

    Run: Read ${CLAUDE_PLUGIN_ROOT}/skills/desk/SKILL.md now and follow it from step 0 to step 7 as the Design Manager with the desks above.

    line 34

“Common” is measured: kept by at least 6 in 10 of the 15 edited versions of this file we could read. “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

Make a brand as the Design Manager.

Deliverable and standard. A brand kit to ${CLAUDE_PLUGIN_ROOT}/skills/desk/standards/brand-kit.md: mark, wordmark, lockups, palette by job, type, spacing, motion language, rules, the kit sheet and three applications (a card, a hero, a 3 second sting), plus the DESIGN.md the studio reads from now on.

Desks.

DeskAgentTierDoes
Brand Strategistdesk:brand-strategistdirectorthe position line and the three direction briefs
Typographerdesk:typographerseniortypeface, weights, scale, wordmark tracking per direction
Design System Leaddesk:design-system-leadseniorthe palette by job with contrast ratios, spacing, radii, the DESIGN.md front matter and palette.css
UI Designerdesk:ui-designerbuilderthe three rough sheets at the senior model, the card and hero applications, polish rounds
Icon Designerdesk:icon-designerbuilderthe mark and lockups as SVG on the grid
Motion Designerdesk:motion-designerbuilderthe motion language and the sting
Art Directordesk:art-directordirectornotes on the three directions, no pick (the user picks)
Creative Directordesk:creative-directordirectorsign-off on the chosen kit

Inputs. Text (a name, a one-line position), one or two hex colours, or --from URL to pull the colours and type a site already uses. Nothing at all is fine: the Brand Strategist asks one question.

Proof sizes. desktop for the sheet, linkedin and ig-post for the card, phone and desktop for the hero, slide for the sting (recorded).

Output under .desk/out/<id>/:

  • direction-1/, direction-2/, direction-3/: each a full kit folder per the standard's file contract, with sheet.html, so the user picks between three real brands.
  • compare.html: the three sheets side by side at thumbnail size with the position line under each.
  • brand/: the chosen direction, polished and signed off, copied to the project's brand/ and its DESIGN.md to .desk/DESIGN.md.

Run. Read ${CLAUDE_PLUGIN_ROOT}/skills/desk/SKILL.md now and follow it from step 0 to step 7 as the Design Manager with the desks above. Command name for state and events: brand-kit. Changes to the loop for this command:

  • Step 0's brand check is skipped: this command makes the brand. Use the house style as the brand for the roughs.
  • Roughs are the three directions, each a kit folder, each from a Brand Strategist brief naming a pattern from the standard. The Art Director writes notes per direction but does not pick.
  • The pick is the user's. Set waitingOn to { "type": "pick", "text": "Three directions in compare.html. Which one, 1, 2 or 3?" }, say it in one line, and stop until they answer or control.json has pick.
  • Polish, proof and sign-off run on the chosen direction only. On sign-off, copy the kit to brand/ in the project and DESIGN.md to .desk/DESIGN.md, and say so in the handback.

The ask: $ARGUMENTS

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.

Reviews can't be read right now.

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.