logo-image-design – Design & UI skill for AI agents
Brand asset register: asset type, format, dimensions and aspect ratio, colour mode, background variant, clear space, approved and prohibited uses, rights owner and licence. Use for brand control.
Install the logo-image-design skill with one command
Pick the tool you use, copy the command and paste it in your terminal. The skill lands in that tool's skills folder and is ready in your next session.
Claude Code
mkdir -p ~/.claude/skills && curl -fsSL https://skill.dn1nguoi.com/z/logo-image-design-ee3ed.tgz | tar xz -C ~/.claude/skills
Call it in Claude Code: /logo-image-design – then describe the task you want done.
Codex
mkdir -p ~/.codex/skills && curl -fsSL https://skill.dn1nguoi.com/z/logo-image-design-ee3ed.tgz | tar xz -C ~/.codex/skills
Call it in Codex: $logo-image-design – then describe the task you want done.
Hermes Agent
mkdir -p ~/.hermes/skills && curl -fsSL https://skill.dn1nguoi.com/z/logo-image-design-ee3ed.tgz | tar xz -C ~/.hermes/skills
Call it in Hermes Agent: /logo-image-design – then describe the task you want done.
DeepSeek
mkdir -p ~/.deepcode/skills && curl -fsSL https://skill.dn1nguoi.com/z/logo-image-design-ee3ed.tgz | tar xz -C ~/.deepcode/skills
Call it in DeepSeek: /logo-image-design – then describe the task you want done.
SKILL.md content
Logo & Image Design
What it is: the mark and the image library - every logo variant, photograph, icon and graphic the business is allowed to use, with the rights attached to it.
Overview
Works out the smallest useful asset set for the business in front of it, then builds it only
when asked. The default output is a short recommendation, not a folder of files. The asset
register - CSV, SQL DDL, JSON Schema, Notion mapping - is produced on request, from one
field list so the four cannot drift apart.
Layer: Layer 2: Brand & Design. Fits: Starter stage. Table code: n/a.
The rule this table exists to enforce: a logo is not a picture, and a picture is not
free to use. Asset Type separates the mark from the imagery, and Licence,
Rights Owner and Trademark Status exist because the expensive failure in branding is
not an ugly logo - it is a mark that was already registered, or a stock photo whose
licence expired, discovered two years later. Every asset carries its rights on the same row
as the file.
When to Use This Skill
- logo, brand mark, wordmark, monogram, symbol, favicon
- lockups, horizontal and stacked versions, one-colour version
- photography library, product photos, team photos, office shots
- icons, illustrations, graphics, patterns
- "we need brand guidelines"
- "can we use this image we found"
- "is this logo already taken"
Do not use it for: the colour and type system underneath the mark (design-theme-guide),
the printed items the mark goes on (brand-kit-print-collateral), or stock-footage sourcing
for ads.
How It Works
Follow these local instructions; the shared execution runtime is not bundled. The module-specific rules below define only domain fields, decisions, calculations, and safety constraints.
Step 1 - Identify intent
Read the request and pick the intent before asking anything.
- "design" / "make" / "we need" -> artifacts wanted; go to Step 2.
- "we already have one" -> something exists; capture what is in use, then Step 2.
- "review" / "check" / "audit" / "is this ok" -> a check, not a build.
- "can we use this" -> a rights question; answer it from what they show, no build.
- "fix" / "refresh" -> capture the current mark and its problem, then Step 2.
Ask only if this is the highest-value missing fact; otherwise proceed without an opener:
> Q: What is the business called, and what does one line of it actually do?
Step 2 - Ask only what is missing
Treat ambiguous replies as unanswered and ask which explicit option the user means. Record unknown values as Unknown; Unknown is not zero. A record must not be Done when a required check fails.
Skip anything already answered. Ask the rest one at a time, and stop as soon as the
remaining answers would not change the asset set.
- Identity - Exact spelling of the name, and any tagline? / What the business does, in
one line? / Any name change coming, or a trading name separate from the registered one?
- Current state - Is there a logo today, and who made it? / Where is it used - sign,
vehicle, invoices, app, uniform? / Does the file still exist in an editable format?
- Rights - Does the business already own any marks or registered names? / Any prior
designer whose rights were not transferred in writing? / Who signs off the final mark?
- Imagery - Do the products or the premises need photographing? / Who is in the photos?
Any consent needed? / Is there a real premises to shoot, or is stock acceptable?
- Delivery - Which formats and where are they needed - web, print, embroidery, social?
/ Does anything need to work at very small size?
Never invent an answer. Names, designer credits, licence terms, trademark numbers and
consent statuses the user has not supplied are Unknown.
Step 3 - Hold the internal context
module: logo-image-design
intent: null # design | refresh | review | import | fix
scale: null # Starter | Growth | Scale, only if the answer changes it
areas:
"Identity": null
"Current State": null
"Rights": null
"Imagery": null
"Delivery": null
requested_outputs: []
confirmed_facts: []
open_questions: []Step 4 - Recommend the smallest workflow
Build an already requested artifact without asking again. For advice-only requests, give a short recommendation and offer the relevant artifact.
Recommended approach: A trademark search first, then one primary mark with three
required variants - full colour, one colour, and a small-size or favicon version - plus a
clear-space rule and a minimum size, recorded once and reused everywhere. Alongside it, a
photography rule: real premises and real people, shot on a phone, in a fixed set of
framings, with the consent record kept next to the images.
Why this one: The variants are what stop the business from stretching a logo. One mark
that has a defined small-size version does not need four more that nobody approved. And the
search comes first because a potential conflict needs jurisdiction/class/use analysis before deciding whether to redesign, rename or obtain permission.
Workflow: Name and mark searched → Direction chosen → Master mark drawn → Required
variants derived → Clear space and minimum size set → Digital and print masters exported →
Imagery shot or licensed → Consent and licence recorded per asset → Register approved and
versioned
Step 5 - Build only on request
Once the user asks for it, derive the fields from the confirmed context and emit the
requested artifacts. For machine-readable text, keep prose outside the data; for files,
provide a usable link. Report material validation failures or limitations separately.
**A selected Notion output is rendered by notion-manual-import, so route the
Notion step there.** When the user selects Notion, hand that step to
@notion-manual-import: it holds the CSV, the property
mapping, the import steps and the verification checklist, and it renders the Field
Reference below instead of defining a table of its own. Do not restate the mapping
here and do not improvise the import steps. Manual CSV and mapping outputs need no
connection. For requested workspace changes, follow the shared contract: verify actual
tool access and the target before writing. A user saying "connected" is not tool evidence.
Never ask for a Notion password or token.
Asset ID,Asset Name,Asset Type,Format,Dimensions,Aspect Ratio,Colour Mode,Background Variant,Minimum Size,Clear Space,Placement,Usage Approved,Usage Not Approved,Source,Rights Owner,Licence,Trademark Status,Version,Status,Notes
,Example Retail primary mark,Logo,SVG and PNG,512x512 and 2400x1200,1:1 and 2:1,CMYK and RGB,Light and dark,24 px digital,Mark height on all sides,Lockup left of text,"Website, social avatar, invoice header","Dark backgrounds, embroidery under 25 mm",Synthetic internal-design example; rights unverified,Example Retail,Unknown - verify effective assignment or license,Not searched,1.0,Draft,Example row - replace every value before use.-- Engine assumption: PostgreSQL. For another engine use the engine's auto-increment
-- equivalent and keep the rest portable.
CREATE TABLE brand_asset (
asset_id BIGINT PRIMARY KEY,
asset_name VARCHAR(255) NOT NULL,
asset_type VARCHAR(100) NOT NULL,
format VARCHAR(100) NOT NULL,
dimensions VARCHAR(100),
aspect_ratio VARCHAR(50),
colour_mode VARCHAR(100) NOT NULL,
background_variant VARCHAR(100) NOT NULL,
minimum_size VARCHAR(50),
clear_space VARCHAR(255),
placement TEXT,
usage_approved TEXT,
usage_not_approved TEXT,
source VARCHAR(255),
rights_owner VARCHAR(255),
licence VARCHAR(255),
trademark_status VARCHAR(100) NOT NULL,
version VARCHAR(50) NOT NULL,
status VARCHAR(50) NOT NULL,
notes TEXT,
created_at TIMESTAMP DEFAULT NOW(),
updated_at TIMESTAMP DEFAULT NOW(),
CONSTRAINT asset_trademark_status CHECK (trademark_status IN ('Not searched','Searched - no conflict identified in stated scope','Application filed','Registered','Conflicting mark found','Unknown')),
CONSTRAINT asset_status CHECK (status IN ('Draft','In review','Approved','Retired'))
);
CREATE INDEX idx_brand_asset_status ON brand_asset (status);
CREATE INDEX idx_brand_asset_type ON brand_asset (asset_type);{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"title": "Logo & Image Design",
"type": "object",
"additionalProperties": false,
"properties": {
"Asset ID": { "type": "integer" },
"Asset Name": { "type": "string" },
"Asset Type": { "type": "string" },
"Format": { "type": "string" },
"Dimensions": { "type": "string" },
"Aspect Ratio": { "type": "string" },
"Colour Mode": { "type": "string" },
"Background Variant": { "type": "string" },
"Minimum Size": { "type": "string" },
"Clear Space": { "type": "string" },
"Placement": { "type": "string" },
"Usage Approved": { "type": "string" },
"Usa… (full content is in the download package)
Related skills
- logo-to-stickers – Turn a brand mark or existing IP into consistent, playful paper stickers with small…
- lookdev-auto – Automated visual tuning: a vision or video model rates rendered variants in a loop…
- loop-library – Find, compare, adapt, and design bounded AI-agent feedback loops with explicit checks…
- magic-animator – AI-powered animation tool for creating motion in logos, UI, icons, and social media…
- magic-ui-generator – Utilizes Magic by 21st.dev to generate, compare, and integrate multiple production-ready…
- mailtrap-managing-contacts – Manage Mailtrap contacts, lists, segments, custom fields, imports, CRM syncs, and…
- makepad-2-0-animation – Makepad 2.0 guidance for animation; use when building or debugging Makepad UI code.
- makepad-animation – CRITICAL: Use for Makepad animation system. Triggers on: makepad animation, makepad…