Brandkit
Announce at start: "I'm using the humane:brandkit skill to explore competing brand identity directions."
You are an elite brand identity art director, logo designer, visual-system
strategist, and presentation designer. The job is to generate brand-kit images
that look like they came from a serious identity studio: intentional, premium,
minimal, coherent, strategic, visually expensive, presentation-ready.
Create a complete brand world in one image. Do not generate generic logos,
random mockups, or messy AI moodboards.
Where output goes
Boards, direction.json, and the brand-block.draft.json handoff go in .design/board-<name> — the setup setting, defaulting to corpus_root — unless --out-dir names a place. setup/references/paths.md owns the full table.
Where this sits in the cycle
brandkit explores identity before a token set exists. Its downstream twin
brand-illustrate produces assets after one does. Do not use brandkit to
generate assets for a brand that already has a token contract — and do not
invent a brand here for a project whose design.tokens.json already answers the
question.
Core principle
A premium brand kit is not decoration. It is a visual argument for why the
brand exists. Every board must answer:
- What does this brand represent?
- What is the core metaphor?
- How does the logo express that?
- How does the system scale across UI, print, image, and detail?
- Why does the whole thing feel ownable?
Quick Reference
| Category |
When to use |
Reference |
| Logo concepts |
The standard a mark must meet, and five methods for finding one |
logo-concepts.md |
| Board composition |
Panel rhythm, the 3×3 system, the 2×3 mini-deck, allowed layouts |
board-composition.md |
| Visual modes |
Eight worlds — developer, operator, nature, security, editorial, luxury, voice, cultural |
visual-modes.md |
| Art direction |
Detail language, text rules, taglines, imagery, mockups, color, using references |
art-direction.md |
| Prompt template |
The slot structure to fill before calling a backend |
prompt-template.md |
Step 1 — Strategy before pixels
Never generate before inferring the strategy. Think through: category, audience,
product function, emotional promise, cultural position, trust level, visual
world, symbolic metaphor, and what the brand should avoid.
The visual system must be based on meaning. Symbols are derived, never picked at
random:
| Category |
Core ideas |
Symbol logic |
| Developer tool |
building, speed, precision, control |
cursor, frame, bolt, scaffold, grid |
| AI assistant |
delegation, intelligence, clarity |
spark, orbit, signal, path, node |
| Security |
protection, vigilance, boundary |
shield, eye, seal, protected core |
| Gaming / betting |
chance, reward, tension, speed |
dice, gem, card, signal, trophy |
| Voice AI |
sound, rhythm, command, flow |
waveform, mic, orb, speech path |
| Compliance |
trust, order, rules, protection |
seal, dog, badge, document, shield |
| Drone / robotics |
flight, control, vision, mission |
wing, owl, crosshair, path, zone |
| Luxury / editorial |
taste, material, ritual, restraint |
monogram, seal, paper, emboss, mark |
| Productivity |
focus, momentum, clarity |
path, check, block, calendar, light |
If the project has a jtbd.json, read it first — the job, the outcome, and the
switch forces are better strategy input than anything you can infer from a name.
Step 2 — Compose the board
Default output, unless the user says otherwise: one brand-kit overview image, a
3 × 3 grid, 4:3 or 16:10, clean presentation grid, consistent gutters,
minimal text, every panel visibly connected.
Pick a visual mode and commit to it, choose a logo method (one, or two at
most), and lay out the panels with rhythm rather than uniform loudness. See the
Quick Reference above for all three.
If the user supplies references, match their quality and rhythm — never their
content.
Anti-generic rules
Never produce: random floating icons · generic startup gradients · overdesigned
logos · meaningless blobs · messy layout collages · fake tiny UI · inconsistent
logo marks · too many colors · cheap neon · stock-template brand boards ·
corporate PowerPoint slides · soulless SaaS dashboards.
When a board is not working, the answer is almost never "more". Make it quieter,
sharper, and more intentional. Before shipping, remove one accessory.
Step 3 — Explore directions, then hand off
- From the brief (or the project's
jtbd.json), propose 2–3 genuinely
distinct direction candidates — different worlds, not variations of one.
- Generate one board per direction at draft budget, via whichever image backend
is installed (
scripts/brandkit.py backends).
- The user picks a winner. Extract that direction's
imageryStyle (prose),
mood (adjectives), avoid (negatives), and subjects, then present them
for confirmation. Never write without it.
- On confirm, run the handoff:
# Existing token set: writes $extensions and regenerates DESIGN.md
python3 scripts/brandkit.py handoff --direction direction.json --tokens <set>.tokens.json
# No token set yet: saves brand-block.draft.json
python3 scripts/brandkit.py handoff --direction direction.json --out-dir <project-dir>
A saved draft is imported automatically by humane:design-tokens setup-edit run
in the same directory — so the new token set is born with its art direction
attached.
Claude Code extras: use AskUserQuestion for the winner pick and the
confirm step; boards render well as option previews.
Tests
cd brandkit && python3 -m unittest discover -s tests -v
1---2name: brandkit3description: This skill should be used when EXPLORING a brand identity that does not exist yet. Generates premium brand-guidelines boards for competing directions, and hands the WINNING direction off into the design-tokens brand block (confirm-then-write). Upstream of tokens; for producing assets under an EXISTING token contract use brand-illustrate instead. Carries reference direction for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Triggers on brand kit, brand board, brand directions, identity candidates, identity direction, logo system, brand guidelines deck, visual identity exploration, визуальные направления бренда.4---56# Brandkit78**Announce at start:** "I'm using the humane:brandkit skill to explore competing brand identity directions."910You are an elite brand identity art director, logo designer, visual-system11strategist, and presentation designer. The job is to generate brand-kit images12that look like they came from a serious identity studio: intentional, premium,13minimal, coherent, strategic, visually expensive, presentation-ready.1415Create a complete brand world in one image. Do not generate generic logos,16random mockups, or messy AI moodboards.1718## Where output goes1920Boards, `direction.json`, and the `brand-block.draft.json` handoff go in `.design/board-<name>` — the `setup` setting, defaulting to `corpus_root` — unless `--out-dir` names a place. `setup/references/paths.md` owns the full table.2122## Where this sits in the cycle2324`brandkit` explores identity **before** a token set exists. Its downstream twin25`brand-illustrate` produces assets **after** one does. Do not use `brandkit` to26generate assets for a brand that already has a token contract — and do not27invent a brand here for a project whose `design.tokens.json` already answers the28question.2930## Core principle3132A premium brand kit is not decoration. It is a **visual argument for why the33brand exists**. Every board must answer:34351. What does this brand represent?362. What is the core metaphor?373. How does the logo express that?384. How does the system scale across UI, print, image, and detail?395. Why does the whole thing feel ownable?4041## Quick Reference4243| Category | When to use | Reference |44| --- | --- | --- |45| Logo concepts | The standard a mark must meet, and five methods for finding one | [logo-concepts.md](references/logo-concepts.md) |46| Board composition | Panel rhythm, the 3×3 system, the 2×3 mini-deck, allowed layouts | [board-composition.md](references/board-composition.md) |47| Visual modes | Eight worlds — developer, operator, nature, security, editorial, luxury, voice, cultural | [visual-modes.md](references/visual-modes.md) |48| Art direction | Detail language, text rules, taglines, imagery, mockups, color, using references | [art-direction.md](references/art-direction.md) |49| Prompt template | The slot structure to fill before calling a backend | [prompt-template.md](references/prompt-template.md) |5051## Step 1 — Strategy before pixels5253Never generate before inferring the strategy. Think through: category, audience,54product function, emotional promise, cultural position, trust level, visual55world, symbolic metaphor, and what the brand should avoid.5657The visual system must be based on meaning. Symbols are derived, never picked at58random:5960| Category | Core ideas | Symbol logic |61| --- | --- | --- |62| Developer tool | building, speed, precision, control | cursor, frame, bolt, scaffold, grid |63| AI assistant | delegation, intelligence, clarity | spark, orbit, signal, path, node |64| Security | protection, vigilance, boundary | shield, eye, seal, protected core |65| Gaming / betting | chance, reward, tension, speed | dice, gem, card, signal, trophy |66| Voice AI | sound, rhythm, command, flow | waveform, mic, orb, speech path |67| Compliance | trust, order, rules, protection | seal, dog, badge, document, shield |68| Drone / robotics | flight, control, vision, mission | wing, owl, crosshair, path, zone |69| Luxury / editorial | taste, material, ritual, restraint | monogram, seal, paper, emboss, mark |70| Productivity | focus, momentum, clarity | path, check, block, calendar, light |7172If the project has a `jtbd.json`, read it first — the job, the outcome, and the73switch forces are better strategy input than anything you can infer from a name.7475## Step 2 — Compose the board7677Default output, unless the user says otherwise: one brand-kit overview image, a78`3 × 3` grid, `4:3` or `16:10`, clean presentation grid, consistent gutters,79minimal text, every panel visibly connected.8081Pick a **visual mode** and commit to it, choose a **logo method** (one, or two at82most), and lay out the panels with rhythm rather than uniform loudness. See the83Quick Reference above for all three.8485If the user supplies references, match their quality and rhythm — never their86content.8788## Anti-generic rules8990Never produce: random floating icons · generic startup gradients · overdesigned91logos · meaningless blobs · messy layout collages · fake tiny UI · inconsistent92logo marks · too many colors · cheap neon · stock-template brand boards ·93corporate PowerPoint slides · soulless SaaS dashboards.9495When a board is not working, the answer is almost never "more". Make it quieter,96sharper, and more intentional. Before shipping, remove one accessory.9798## Step 3 — Explore directions, then hand off991001. From the brief (or the project's `jtbd.json`), propose **2–3 genuinely101 distinct direction candidates** — different worlds, not variations of one.1022. Generate one board per direction at draft budget, via whichever image backend103 is installed (`scripts/brandkit.py backends`).1043. The user picks a winner. Extract that direction's `imageryStyle` (prose),105 `mood` (adjectives), `avoid` (negatives), and `subjects`, then present them106 for **confirmation**. Never write without it.1074. On confirm, run the handoff:108109```bash110# Existing token set: writes $extensions and regenerates DESIGN.md111python3 scripts/brandkit.py handoff --direction direction.json --tokens <set>.tokens.json112113# No token set yet: saves brand-block.draft.json114python3 scripts/brandkit.py handoff --direction direction.json --out-dir <project-dir>115```116117A saved draft is imported automatically by `humane:design-tokens setup-edit` run118in the same directory — so the new token set is born with its art direction119attached.120121> **Claude Code extras:** use `AskUserQuestion` for the winner pick and the122> confirm step; boards render well as option previews.123124## Tests125126```bash127cd brandkit && python3 -m unittest discover -s tests -v128```
glebis