Generated banner for Higgsfield Brandkit
Generated logo for Higgsfield Brandkit

Higgsfield Brandkit

Higgsfield AIOfficialPublished by Higgsfield AI

  • Skill
  • Content generator
  • Design and creative
  • MIT
  • Medium risk
  • Has scripts

From the author

Create and extend complete visual brand systems through the Higgsfield CLI and bundled deterministic local tooling: palettes, SVG logo marks, typography, mockups, social graphics, packaging, signage, merchandise, posters, presentation decks, and editable PPTX/PDF brandbooks. Preserves official supplied assets, persists approvals locally, and regenerates only dependent outputs. Use when: "create a brand kit", "make a visual identity", "design a logo and brandbook", "apply this logo to branded assets", "make packaging or signage", or "extend our existing branding". Chain with higgsfield-generate for general image production and Marketing Studio brand-kits when importing website metadata for ads. NOT for unbranded image generation (use higgsfield-generate), product catalog photography (use higgsfield-product-photoshoot), website implementation (use higgsfield-websites), or native Figma/Canva/PSD/AI delivery.
— the description by Higgsfield AI

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

Higgsfield-brandkit is a deterministic tool designed to create and extend visual brand systems. It manages the lifecycle of brand assets including logos, palettes, typography, and various marketing materials like posters, packaging, and presentation decks. The tool emphasizes consistency by locking authoritative assets and ensuring that generated outputs adhere to established brand constraints. It supports the creation of editable brandbooks and manages the state of approvals locally to prevent redundant work or unauthorized deviations from the brand identity.

What it does

  • Generates and manages visual brand elements like logos, palettes, and typography.
  • Creates marketing assets including social graphics, posters, packaging, and merchandise.
  • Builds editable brandbooks and presentation decks in PPTX and PDF formats.
  • Maintains a local state of approved assets to ensure consistency across all outputs.
  • Imports and analyzes existing brand metadata for use in new designs.
  • Enforces strict adherence to defined brand rules and constraints during generation.

When to use it

  • When you need to create a new visual identity or brand kit from scratch.
  • When you need to extend an existing brand system with new marketing materials.
  • When you need to generate branded assets while ensuring they match official logo and color specifications.
  • When you need to produce consistent, editable brand documentation like brandbooks or decks.

Advantages

  • Ensures visual consistency by locking authoritative assets as the source of truth.
  • Reduces manual effort by automating the generation of dependent brand assets.
  • Provides a structured workflow for reviewing and approving brand elements.
  • Supports deterministic outputs for specific brand requirements.
  • Maintains local project state for efficient iteration and revision.

Usage examples

“Create a brand kit for my new coffee shop.”
The agent will initiate the brand identity workflow, starting with palette and logo development based on your input.
“Apply our existing logo to a new set of social media graphics.”
The agent will analyze your official logo and brand assets to generate consistent social media templates.
“Design a brandbook for our company.”
The agent will compile your approved logo, palette, and typography into an editable brandbook document.
“Extend our current branding to include packaging designs.”
The agent will use your existing brand lock to generate packaging concepts that align with your established visual identity.

Install

  1. Download the skill as a ZIP:

    https://mp-staging.autogineer.com/agent-skills/higgsfield-ai/higgsfield-brandkit/download
  2. Unzip it into the cross-client skills folder of your project:

    mkdir -p .agents/skills && unzip higgsfield-brandkit.zip -d .agents/skills

Documentation by Higgsfield AI

Higgsfield Brandkit

Build a coherent identity and its requested applications. Treat supplied brand facts and official assets as fixed constraints.

Bootstrap

  1. Resolve SKILL_ROOT to this skill's installed directory and create a durable project directory:

    BRANDKIT_WORKDIR="${PWD}/brandkit"
    BRANDKIT_STATE="${BRANDKIT_WORKDIR}/state.json"
    mkdir -p "${BRANDKIT_WORKDIR}"
  2. Read prerequisites. Check tools before the stage that needs them. Never install system packages without the user's permission.

  3. If higgsfield is missing, install it only after permission:

    curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh
  4. If higgsfield account status fails with an authentication or workspace error, ask the user to run higgsfield auth login or select a workspace, then wait.

  5. Inspect live model contracts before paid generation:

    higgsfield model get recraft_v4_1 --json
    higgsfield model get seedream_v5_pro --json
    higgsfield model get gpt_image_2 --json

CLI mapping

OperationCommand
Discover a modelhiggsfield model get <model> --json
Generate and pollhiggsfield generate create <model> ... --wait --json
Resume a jobhiggsfield generate wait <job_id> --json
Upload a local assethiggsfield upload create <path> --json
Import website metadatahiggsfield marketing-studio brand-kits fetch --url <url> --wait --json
Read/write approval statepython3 "$SKILL_ROOT/scripts/brandkit.py" state ...
Render review boardspython3 "$SKILL_ROOT/scripts/brandkit.py" preview ...
Inspect selected logopython3 "$SKILL_ROOT/scripts/brandkit.py" logo-inspect ...
Export logo filespython3 "$SKILL_ROOT/scripts/brandkit.py" logo-export ...
Build a Brandbookpython3 "$SKILL_ROOT/scripts/brandkit.py" brandbook-build ...

Local image paths passed with --image are auto-uploaded. Keep HTML, SVG, PPTX, and PDF deliverables as local project files unless the user explicitly needs a hosted copy.

User-facing behavior

  • Match the user's language. Keep Design Brain reasoning, prompts, state mechanics, scripts, model lookup, and QA internals private.

  • Send at most one short status sentence per visible generation batch, then stay quiet until the result is ready.

  • Ask one compact set of only unresolved blocking questions. Never repeat facts or force a complete identity questionnaire for a partial task.

  • After each palette, logo, typography, or downstream review, stop and wait for ordinary user feedback.

  • Never infer approval from silence, successful generation, or your own preference.

  • Preserve exact user copy. Never invent positioning, values, claims, ingredients, prices, certifications, statistics, or regulatory content.

Core workflow

  1. Classify the request.

    • apply-existing: use supplied official assets without redesigning them.

    • extend-partial: create only missing slots required by the requested output.

    • create-identity: create a new logo or identity only when explicitly requested.

  2. Read state. Run:

    python3 "$SKILL_ROOT/scripts/brandkit.py" state \
      --state-file "$BRANDKIT_STATE" --action get_status

    Local state is durable. Never paste, hand-edit, or recreate approvals when the state file exists.

  3. Run intake and asset analysis. Read intake, asset analysis, state routing, and exact state payloads. Lock every user-declared official logo, palette, and typography slot immediately.

  4. Create the Brand Lock. Read Brand Lock. Record exact spelling, official assets, colors, fonts, layout/shape rules, requested outputs, and forbidden treatments.

  5. Require only the slots the output uses.

    • logo-only → palette + logo for a new mark; official logo alone for an existing mark

    • palette-only → palette

    • typography-only → typography

    • copy-free mockup/merch → logo; add palette only when color/application requires it

    • text-bearing social/packaging/poster/signage → logo + palette + typography

    • Brandbook/deck → logo + palette + typography

  6. Build missing foundation slots. Read Design Brain, concept boards, inline reviews, and only the needed palette, logo, or typography module.

  7. Continue the original request as soon as its required slots are approved. Never ask the user to choose scope again.

  8. Load only the requested production module:

  9. QA and approval. Read QA and iteration. Repair only the failing output. Save a downstream element only after explicit approval with its exact foundation dependencies.

New identity sequence

1. Palette

Render 2–3 exact palette options as deterministic HTML using preview payloads. Show PNG screenshots plus editable HTML files and wait. Persist the selected palette with approve_palette before logo generation.

2. SVG logo marks

Read logo prompt enhancer. Produce exactly three distinct symbol-only mechanisms and one Recraft prompt for each. Write each long prompt to a file and submit separately:

higgsfield generate create recraft_v4_1 \
  --model_type vector \
  --colors @"${BRANDKIT_WORKDIR}/logo-colors.json" \
  --background_color '#F7F7F5' \
  --aspect_ratio 1:1 \
  --resolution 2k \
  --wait --json < "${BRANDKIT_WORKDIR}/logo-candidate-1.txt"

Use the returned SVG URLs directly for review. After selection, inspect the exact SVG without altering it:

python3 "$SKILL_ROOT/scripts/brandkit.py" logo-inspect \
  --source "<selected Recraft SVG URL or absolute local path>"

Persist the exact job ID, SVG URL, name, palette revision, and returned canonical geometry fingerprint with approve_logo.

3. Typography

Propose 2–3 unique display/body pairs using supplied fonts or verified Google Fonts. Render the real brand name and sample copy through the preview script. Persist only the selected pair with approve_typography.

Interactive flows always stop for palette, logo, and typography selections. Explicit no-question mode may choose and persist a palette, but it still shows all three SVG logo candidates and stops for the user's logo selection; exact brand marks are never self-approved.

Consistency invariants

  • Reuse the same approved logo source everywhere. Never redraw an official or selected SVG when deterministic placement/export is possible.

  • A generated logo depends on the palette revision used to create it. Changing that palette invalidates the generated logo and its dependents; changing typography does not invalidate the symbol mark.

  • Changing a foundation slot invalidates only downstream elements that list that slot in required_slots.

  • Copy the same Brand Lock values into every related generation prompt: exact hex, font roles, shape language, placement, clear space, composition, and forbidden treatments.

  • Use Recraft V4.1 vector mode only for new logo marks.

  • Use Seedream as the primary photoreal mockup generator. Use GPT Image 2 only for the controlled stage that adds readable text or exact graphic details.

  • Use local deterministic SVG/PPTX/HTML construction for exact copy and editable layouts. Do not ask an image model to fake editable files.

  • Do not promise native Figma, Canva, PSD, AI, or EPS files.

Deterministic scripts

Create JSON input files under "$BRANDKIT_WORKDIR"; never interpolate user text directly into shell arguments.

python3 "$SKILL_ROOT/scripts/brandkit.py" preview \
  --input "$BRANDKIT_WORKDIR/reviews.json" \
  --output-dir "$BRANDKIT_WORKDIR/reviews"

python3 "$SKILL_ROOT/scripts/brandkit.py" logo-export \
  --input "$BRANDKIT_WORKDIR/logo-export.json" \
  --output-dir "$BRANDKIT_WORKDIR/logo"

python3 "$SKILL_ROOT/scripts/brandkit.py" brandbook-build \
  --state-file "$BRANDKIT_STATE" \
  --input "$BRANDKIT_WORKDIR/brandbook.json" \
  --output-dir "$BRANDKIT_WORKDIR/brandbook"

For logo export, load logo export payloads. For Brandbooks, use the bundled builder only; never substitute an improvised PowerPoint or PDF generator after a deterministic contract failure.

Failure policy

  • Retry a failed Recraft or image-generation request once with the same locked concept and corrected contract. Stop after the second equivalent failure.

  • If preview or logo export fails twice, report the concrete error; never replace it with ad-hoc SVG rewriting.

  • If the Brandbook template, font, or conversion contract fails, stop immediately. Do not produce a visually different fallback and call it canonical.

  • If exact typography or official-logo fidelity cannot be preserved, disclose the limitation instead of claiming completion.

  • Never expose raw auth tokens or credentials in files, logs, or chat.

Delivery

For Brandbooks, follow the strict response contract in brandbook: PPTX link/path, PDF link/path, and font-install warning only.

For other outputs return:

  1. The requested visual files and previews.

  2. A compact Brand Lock summary.

  3. Editable versus flattened format labels.

  4. Required-font/import limitations.

  5. Stable variant names for targeted revisions.

Reference index

Files

references/logo.md

Logo system

Load this module only when the user asks to create, extend, document, or apply a logo. A request for other branded graphics does not authorize a redesign.

Route

Use the supplied file as authoritative.

  1. Analyze source geometry, variants, colors, clear space, and minimum-size guidance from source files/brandbook.

  2. Record its exact local path, public URL, upload ID, or job ID in the Brand Lock. Upload it only when a Higgsfield generation stage requires that file.

  3. Reuse or deterministically place the exact asset.

  4. Generate only requested variants/applications.

Never ask an image model to redraw a logo merely to change its background, size, placement, or colorway. Use SVG/PPTX/image compositing when the source supports it.

Partial logo system

Examples: only a primary logo exists; no monochrome/reverse version, symbol, clear-space rule, or lockup.

  • Preserve the primary mark.

  • Propose only missing variants.

  • Derive variants from source geometry rather than inventing a second style.

  • Ask before separating a symbol from a wordmark if the source does not demonstrate that they may be used independently.

Run only when explicitly requested.

  1. In an interactive new-identity flow, complete the palette review in concept-boards.md first. Require a user-selected and persisted palette before generating logo candidates. Color/style preferences from intake are not palette selection. Only explicit auto/no-question mode may select the palette internally; it must call approve_palette and receive a successful state response before generating logo candidates.

  2. Load brandkit-design-brain.md and run PROPOSE_LOGO_MECHANISMS with the brief, references, visual axes, and selected palette.

  3. Require exactly three distinct symbol-only candidate specifications.

  4. Apply logo-prompt-enhancer.md exactly once per candidate, building one complete structured candidate input per application.

  5. Run higgsfield model get recraft_v4_1 --json, then submit the three enhanced prompts as three separate higgsfield generate create recraft_v4_1 --model_type vector --wait --json requests with exact hex arrays in --colors and the selected --background_color.

  6. Use the three Recraft SVG result URLs directly. Do not pass them through the HTML preview script or any SVG normalizer/editor.

  7. Show all three SVGs per the logo review in inline-widgets.md in every mode, including explicit auto/no-question mode; never return them only as bare URLs. Then send a normal message inviting the user to review and comment when interaction is allowed.

  8. When the user selects one SVG, run logo-inspect --source <selected SVG URL or absolute path>. It validates the source and fingerprints the mark after ignoring a detected full-canvas Recraft background without modifying the approved SVG.

  9. Immediately save that exact asset and the returned geometry_fingerprint with the Brandkit state script's approve_logo action. Continue to typography only when the original request requires text/type; a logo-only request does not.

Enhancer contract

For each of the three Design Brain mechanisms, assemble the complete structured candidate input defined in logo-prompt-enhancer.md:

{
  brand_context: {
    name,
    offering,
    industry,
    positioning,
    audience,
    values
  },
  visual_axes: {
    restrained_expressive,
    geometric_organic,
    familiar_experimental
  },
  candidate: {
    mark_type,
    central_idea,
    visual_mechanism,
    distinctive_element,
    shape_logic,
    treatment,
    style_register,
    user_style_directive,
    composition
  },
  palette: {
    count,
    user_requested_more_than_three,
    roles
  },
  reference_signals,
  forbidden_elements
}

Apply that reference's full contract to produce one enhanced prompt per candidate. Use only that enhanced prompt as the candidate's Recraft prompt. Never merge the three enhanced prompts into one request.

Exact hex colors never enter the enhanced prompt prose. Pass them directly in each Recraft request's colors and background_color params.

Set user_requested_more_than_three: true only when the user explicitly asks for a logo with more than three colors. Otherwise pass exactly the one, two, or three logo colors the concept requires, even if the broader brand palette contains more. Never add colors merely to reach three.

In explicit no-question mode, rank the three candidates privately but still show all three and stop for the user's logo selection. Never write approval state for an unselected brand mark.

Exactly three comparable SVG candidates

All three must:

  • Be true SVG outputs returned directly by Recraft V4.1 vector mode

  • Use the same aspect ratio, palette parameters, background, and generation quality

  • Belong to the selected draft palette and user-defined direction

  • Differ in mark construction, not presentation quality

  • Stay simple enough to reproduce faithfully with vector geometry

  • Express one visual concept only; never fuse two metaphors unless the user's own request explicitly described that exact fusion

  • Include one concrete distinctive silhouette, negative-space device, motif treatment, or unexpected locked color-role pairing

  • Preserve any explicit user-requested style in the candidate and enhanced prompt

  • Use one, two, or three logo colors as the concept requires; three is a maximum, not a default, unless the user explicitly requested more

  • Avoid generic swooshes, arbitrary initials, stock startup symbols, tiny details, gradients/effects unless concept-critical, and mockup scenes

Typography is selected afterward. Every enhancer prompt must include “no text” in its constraint tail. Monograms may contain only their explicitly requested initials.

If prompt enhancement or the Recraft call fails, retry once with the same candidate specification. If it fails again, stop and report the error. Never substitute GPT Image or select a winner for the user yourself.

During typography selection, the mark and wordmark must feel like one lockup:

  • Match stroke/weight and corner character

  • Balance mark height against cap/x-height

  • Use deliberate gap and optical alignment

  • Avoid a detailed/heavy mark beside a weak or unrelated wordmark

Never reproduce or cite a reference mark as the target.

Color revision and optional variant export

Logo approval requires only the selected color Recraft SVG. Monochrome/reverse variants are optional. Do not announce, prepare, generate, or save them unless the user explicitly requested them.

When logo files or a confirmed production method require export:

  1. Load exact logo-export payloads, then keep the exact Recraft SVG as the geometry source.

  2. Write "$BRANDKIT_WORKDIR/logo-export.json", then run python3 "$SKILL_ROOT/scripts/brandkit.py" logo-export with include_monochrome: false by default. This creates only the approved color SVG and transparent 2048×2048 PNG.

  3. Set include_monochrome: true only after an explicit request for monochrome/reverse files or when a user-confirmed output requires one-color production. Then set primary_color to the dominant approved source color.

  4. Pass replacements only for a requested full-color revision.

  5. Do not call Recraft or GPT Image for a color-only change.

logo-inspect and logo-export use the same canonical fingerprint, so a removed full-canvas Recraft background cannot create a false geometry mismatch. The export script fingerprints every generated variant. Any geometry mismatch is a hard stop. Optional black/white variants are deterministic derivatives of the approved color SVG, not separate concepts or image-model recolors.

For a user-requested solid palette-color/one-color variant, pass that target hex once as single_color. The script recolors every actual SVG paint automatically and adds the SVG/transparent PNG pair. Never inspect source paints or construct per-fill replacements for a monochrome variant.

The script accepts Recraft hex, rgb(), and rgba() paint values and removes a detected full-canvas background. A failed color match reports the available source colors itself. If export still fails, stop and report the exact error. Never inspect or create copies with ad-hoc shell commands, grep, sed, regex scripts, or manual SVG rewriting.

Only when the user explicitly requests logo files, deliver the requested local SVG/PNG paths. Use the PNG as a later Higgsfield image reference; local image paths auto-upload during generation. Keep the SVG as the authoritative editable source.

System deliverables

Produce only requested items:

  • Primary horizontal lockup

  • Secondary/stacked lockup

  • Symbol/monogram

  • Wordmark

  • Small-size/favicon treatment

  • Clear-space diagram

  • Minimum-size guidance

  • Approved backgrounds

  • Incorrect-use examples

Clear space and minimum size

For an existing identity, copy official rules. If none exist, propose rules and mark them inferred:

  • Define a repeatable unit x from a stable feature (symbol width, cap height, or dominant stroke), not an arbitrary pixel count.

  • Apply x consistently around each lockup.

  • Test at intended digital and print sizes.

  • Create a simplified small-size treatment only with user approval; do not silently remove details from the primary mark.

Editable output

  • Three original Recraft SVG candidates

  • Approved Recraft SVG source for the selected mark

  • Full-color SVG and 2048×2048 PNG exports

  • Black/white SVG and PNG variants only when explicitly requested or production-required

  • PPTX brand-guide pages when requested

SVG wordmarks remain editable text and require the approved font to be installed. Do not promise native AI/EPS/Figma/Canva/PSD.

Logo QA

  • Exact spelling and glyph order

  • No altered proportions or invented details

  • No unintended gradients, shadows, bevels, or effects

  • Correct palette and contrast

  • Black and white variants have the exact approved geometry and one solid color

  • Exactly three candidates generated with identical Recraft parameters

  • Selected mark and later wordmark treatment look optically complete together

  • Legible silhouette at small size

  • Clear-space and minimum-size examples match the actual asset

  • Every mockup/template uses the approved anchor, not a regenerated copy

Requirements and compatibility

Written for: Claude Code

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Needs: Declares allowed tools, Claude Code frontmatter, Needs network access, Needs Python

Security

What our scanner noticed· Medium risk

  • Instructions that use the network
  • Downloads piped into a shell
  • Scripts that your agent may run

This skill includes scripts that your agent may run. Read them before you use it.

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Published by
Higgsfield AI
Publisher
Higgsfield AI (Official)
Source
higgsfield-ai/skills · higgsfield-brandkit · commit 2700040
Licence
MIT License (redistribution allowed)
  • LICENSE (added by AutoGineer from LICENSE)
  • ATTRIBUTION.md (written by AutoGineer)
Synced

AutoGineer is not affiliated with or endorsed by Higgsfield AI.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download higgsfield-brandkit.zip