Agent Skills
› langchain-ai/design-agent
› brand-onboarding
brand-onboarding
GitHub根据品牌指南、网站或文件构建并验证品牌包(包含令牌、标志、字体等),确保数据准确并供人员审核。
Trigger Scenarios
需要初始化或更新品牌资产包
从外部源提取品牌设计规范
验证品牌配置文件的合规性
Install
npx skills add langchain-ai/design-agent --skill brand-onboarding -g -y
SKILL.md
Frontmatter
{
"name": "brand-onboarding",
"description": "Build the active brand pack in workspace\/brand\/ from a brand guide, website, files or a Paper file, validate it, and have a person review it."
}
Build a brand pack
The pack is the agent's only source of brand facts: tokens, logos, fonts, voice and graphic
language. Schema: src/design_agent/brand/schema.py; a complete example:
examples/brands/example-studio/. Never invent a rule, colour, font or logo the sources do not show:
leave it out and list it as a question for the person.
uv run design-agent brand initcopies the example pack intoworkspace/brand/(Git-ignored); replace every file's content, logos included.- Sources, best first: the brand's own guide (PDF), its design files (Paper: read tokens,
palette and type nodes with
get_tokens,get_computed_styles,get_jsx; never write to the brand file), the live website's CSS, then existing marketing files. tokens.json: palette, font stacks for display, text and mono, radii, stroke, spacing, and the copy rules the guide states. Check every text/ground pair you list for WCAG contrast; mark accents that fail on light grounds as non-text. Say which colour plays which role indesign.roles.lightanddesign.roles.dark(ground,ink,accent,muted,quiet,rule,series, each a token): charts and diagrams use them, and otherwise guess from the palette. Porting an existing tokens file: names must be--brand-*, hexes carry#,versionis"1", unknown keys are refused, and every font stack ends in a generic family.logos/: SVG where the brand provides it; every variant the guide allows (mark, lockup, reversed). Do not redraw or trace a logo; ask for files.fonts.toml: for each face, an open font infonts/or a licensed file the person supplies inprivate-fonts/(Git-ignored; it reaches the sandbox as deployment files or a mount). Never commit licensed fonts.familyis the name inside the file (the sandbox resolves fonts by it),weighta CSS weight ("400", or"100 900"for a variable face),sha256fromshasum -a 256 <file>.uv run design-agent fonts verifychecks all three. Web formats (.woff2,.woff) are fine:tokens.cssdeclares them with@font-face. If a licensed face is unavailable, name the closest open fallback and say so ingraphic-language.md.voice.mdandgraphic-language.md: short, concrete, sourced ("headlines in sentence case", "one accent per frame"), no generic advice. Anything else the guide has (type tables, icons, pattern art, construction specs) can live in the pack too; link it fromgraphic-language.md, which is what the agent reads first.uv run design-agent brand validate,uv run design-agent fonts verify, thenuv run design-agent brand cssregeneratestokens.css. For a first look, ask for one card (uv run design-agent ask "A 1200x630 card announcing …") and review it with the person;demoalways renders the sample brand.- Hand the person the open questions, including rules the guide contradicts itself on; the pack is done when they have reviewed it.
- Tell them to redeploy. On Managed Deep Agents the pack ships with the deployment, so Slack keeps
the old brand until
uv run mda deploy; local runs pick it up at once. - Offer a Slack app icon in the new brand:
uv run design-agent ask "Our Slack app icon: a 1024x1024 PNG, the logo mark centred on the brand ground, no text". The person uploads it in the Slack app's settings (Basic Information, Display Information). Slack has no API for an app's icon, so neither MDA nor this repo can set it for them.
Version History
- 8134d7c Current 2026-11-20 21:39


