skills/web-design/design-inspiration/SKILL.md
Loads visual design references to guide any design creation or modification task. ALWAYS use this skill whenever Claude is about to create or modify any design artifact — including UI components, landing pages, web interfaces, dashboards, React/HTML code, Figma outputs, slide decks, or any visual/frontend work. Even if the user doesn't say "use my references" — if a design is being made or changed, consult this skill first. The references folder contains images and notes representing the target aesthetic; Claude must read and internalize them before producing any design output. Also use this skill when the user says "save to gallery", "add to gallery", "save this design", or wants to archive a reference, screenshot, or URL into the laniameda.gallery Design pillar.
npx skillsauth add michailbul/laniameda-skills design-inspirationInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This skill has two responsibilities:
Before writing a single line of design code or producing any visual output:
ls /mnt/skills/user/design-inspiration/references/ to see what's available.view tool and study it carefully..md or .txt file found, read it with the view tool.If no references exist yet, note this to the user and proceed with your best judgement, suggesting they populate the folder (see Adding References below).
From the references, identify and internalize:
| Dimension | What to look for | |---|---| | Color palette | Background, surface, accent, text, border colors. Exact hex values if readable. | | Typography | Font families, weights, sizes, line heights, letter spacing. | | Spacing & layout | Grid density, padding rhythm, margin scale, component gaps. | | Shape language | Border radius, sharp vs. rounded, card styles, button shapes. | | Depth & elevation | Shadows, blur, layering, glassmorphism, flat vs. skeuomorphic. | | Motion cues | Any noted animations, transitions, interaction patterns. | | Mood / tone | Minimal, brutalist, editorial, dark luxury, playful, corporate, etc. | | Recurring patterns | Repeated UI motifs, icon styles, dividers, decorative elements. |
Use the extracted design language as constraints when generating code or describing designs:
If you intentionally deviate from the references (e.g. for accessibility, technical constraints, or because a reference doesn't cover the required component), say so explicitly.
Use this workflow when the user wants to save a design reference, screenshot, URL, or note
to the gallery. All design saves go to pillar: "designs".
Determine the content type from what the user provides:
| What they give you | Content type |
|---|---|
| A URL (Dribbble, Figma, website, etc.) | url |
| A local image file path | imagePath |
| A description / notes only | designInspiration text + allowPromptOnly: true |
| An uploaded image | Save it locally first, then use imagePath |
From the content being saved, extract relevant typedTags. Use only valid categories:
design_style — e.g. "dark-luxury", "brutalist", "editorial", "glassmorphism"design_type — e.g. "landing-page", "dashboard", "card", "navigation", "modal"color — e.g. "amber", "near-black", "warm-white"style — e.g. "minimal", "dense", "airy"content_type — e.g. "ui-screenshot", "figma-export", "mockup"platform — e.g. "web", "mobile", "desktop"component_type — e.g. "button", "input", "hero-section"Format: { "category": "<category>", "value": "<value>" }
{
"pillar": "designs",
"designInspiration": "<brief description of what this is and why it's inspiring>",
"url": "<url if applicable>",
"imagePath": "<local path if applicable>",
"allowPromptOnly": true,
"ingestKey": "design-<slug>-<YYYY-MM-DD>",
"typedTags": [
{ "category": "design_style", "value": "dark-luxury" },
{ "category": "design_type", "value": "landing-page" }
]
}
Rules:
pillar: "designs"url, imagePath, or designInspirationallowPromptOnly: true when saving text/notes without a file or URLingestKey for retry safety (e.g. design-vercel-dashboard-2026-03-27)ownerUserId — it's read from env (KB_OWNER_USER_ID=278674008)bun run ~/.agents/skills/laniameda-gallery-ingest/scripts/ingest.ts '<payload-json>'
If env vars aren't set in the shell, prefix them:
CONVEX_URL=<from-env> KB_OWNER_USER_ID=278674008 \
bun run ~/.agents/skills/laniameda-gallery-ingest/scripts/ingest.ts '<payload-json>'
Both CONVEX_URL and KB_OWNER_USER_ID are already set in /root/.openclaw/.env — no need to pass them manually in most contexts.
After a successful ingest, confirm with:
ingestKey used (useful for future updates)If the ingest fails, show the error and suggest checking CONVEX_URL env var or verifying the skill is installed:
bunx skills add https://github.com/laniamedaHQ/laniameda-gallery/tree/main/skills/laniameda-gallery-ingest -g -a openclaw
Save a URL:
{
"pillar": "designs",
"designInspiration": "Vercel dashboard — clean dark UI with tight spacing and monospace data display",
"url": "https://vercel.com/dashboard",
"allowPromptOnly": true,
"ingestKey": "design-vercel-dashboard-2026-03-27",
"typedTags": [
{ "category": "design_style", "value": "dark-minimal" },
{ "category": "design_type", "value": "dashboard" },
{ "category": "platform", "value": "web" }
]
}
Save a local screenshot:
{
"pillar": "designs",
"designInspiration": "UI screenshot showing amber-on-dark card layout with tight grid",
"imagePath": "/Users/michael/Desktop/card-reference.png",
"ingestKey": "design-card-amber-dark-2026-03-27",
"typedTags": [
{ "category": "design_style", "value": "dark-luxury" },
{ "category": "design_type", "value": "card" },
{ "category": "color", "value": "amber" }
]
}
Save notes only:
{
"pillar": "designs",
"designInspiration": "Reference aesthetic: near-black bg #0A0A0A, amber accent #F59E0B, Inter font, 8px radius on cards, no shadows — depth via layering only",
"allowPromptOnly": true,
"ingestKey": "design-aesthetic-notes-2026-03-27",
"typedTags": [
{ "category": "design_style", "value": "dark-luxury" },
{ "category": "color", "value": "amber" }
]
}
To add design references to this skill's local folder, place files in:
/mnt/skills/user/design-inspiration/references/
Accepted file types:
.png, .jpg, .webp, .gif — screenshots, mockups, inspiration images.md — written design notes, token values, brand guidelines.txt — color palettes, font stacks, spacing scalesTips:
.md note alongside each image describing what you like about it.dark-card-01.png, dark-card-02.png).PRIORITY.md to explicitly rank them.~/work/laniameda/laniameda.gallery/skills/laniameda-gallery-ingest/SKILL.mddevelopment
Seedance 2.0 video prompt director. Converts plain-text scene descriptions into production-ready bilingual EN+ZH video prompts optimized for the Seedance 2.0 video generator. Handles all Seedance work — action (combat, pursuit, stunts), general (landscapes, journeys, atmosphere), dialogue (confrontations, negotiations, interrogations), and non-narrative commercial work (ad spots, music videos, fashion films, automotive inserts, product shots, pet/character demos, cutaway montages, social reels for TikTok / Reels / YouTube Shorts). Use whenever the user wants to create a Seedance video prompt, mentions Seedance, or describes a cinematic scene for video generation. For NARRATIVE screenplay-integrated work, use seedance-screenwriter instead.
development
Write Seedance 2.0 prompts in screenplay format for narrative storytelling — when the prompts will be cut into a film, short, or scene. Use whenever you're generating shots that will be edited into a continuous story with dialogue, character beats, scene continuity, or coverage. Pairs with the screenwriter skill — read the scene's screenplay first (or the project's `scene.md` if it exists), then translate each shot into a Seedance prompt that reads as a screenplay page, not as an engineering spec.
documentation
Скилл-инструмент для сценариста полнометражного фильма или сериала. Используй всегда, когда пользователь хочет писать сценарий, поэпизодник, разрабатывать сцены, бит-шит, диалоги, делать ревизии, считать экранное время, резать длину, работать с персонажами или мифологией истории. Скилл работает на основе методологий Макки, Кэмпбелла и Аристотеля, выдаёт Hollywood-формат .docx, поддерживает билингвальные сценарии (диалог на одном языке + перевод в скобках под ним), и помогает аудитировать структуру по причинности и движению ценности. Скилл не привязан к конкретной истории — пользователь приносит свою.
development
Extract shot composition DNA from any car photograph into structured JSON — camera angle, lens, framing, lighting — stripped of car-specific details. Then reuse extracted angles with any car identity to generate new images at scale. Use when: extracting angles from reference photos, building a shot library, batch-analyzing car photography, replicating a great angle with a different car, running extraction pipelines in Freepik or Flora. Triggers: "extract this angle", "steal this composition", "shot DNA", "analyze this car photo", "replicate this shot with my car", "batch extract angles", "car photography analysis", "angle extraction", "build a shot library".