Brand identity

Skill event4u-app/agent-config/src/skills/brand-identity

Universal AI Agent OS — audited skills, governance rules, replayable state. One contract, every host agent.

Install

npx -y skills add event4u-app/agent-config --skill brand-identity

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

7 stars7 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Define a brand identity constraint set from a confirmed strategy — colour story, type story, logo direction, imagery direction. Defines the tokens that token emission and asset generation consume.

SKILL.md

5.5 KB, ~1.2k tokens by cl100k_base, as published. Nobody here has run it

brand-identity

Grounding + Method skill. Turns a confirmed brand strategy into an identity constraint set: colour story, type story, logo direction, imagery direction. It DEFINES tokens and constraints — it does not render marks. Dependency direction: pack-brand (B) exports constraints; pack-ai-image (A) consumes them. brand-to-tokens emits the DTCG token file from these constraints. logo-generation and brand-asset-generation generate the actual marks from these constraints. Never invert that direction.

When to use

After brand-strategy is confirmed (archetype, voice, positioning settled).
When deriving the colour story, type story, logo direction, or imagery direction for a project.
Before running brand-to-tokens to emit the DTCG token file.
Before handing constraints to logo-generation or brand-asset-generation in pack-ai-image.

Procedure

Receive the confirmed strategy — archetype, voice, positioning, and target sector from brand-strategy. Refuse to proceed if strategy is still a draft.
Ground the colour story via the brand corpus:

./scripts-run <skills-root>/corpus-grounding/scripts/ground search \
  --manifest <skills-root>/brand/data/manifest.json \
  "<archetype + sector>" --domain color --json

Read confidence and evidence_gap from the response. Record both verbatim in the output. Derive colour roles (primary, secondary, neutral, accent) and direction (temperature, contrast ratio floor, emotional register).

Ground the type story via:

./scripts-run <skills-root>/corpus-grounding/scripts/ground search \
  --manifest <skills-root>/brand/data/manifest.json \
  "<archetype + sector>" --domain typography --json

Output is a pairing-filter + heading/body class labels, not concrete tokens. Hand this filter to typography-system for the actual type tokens.

Ground the logo direction via:

./scripts-run <skills-root>/corpus-grounding/scripts/ground search \
  --manifest <skills-root>/brand/data/manifest.json \
  "<archetype + sector>" --domain logo --json

Capture mark style, form language, and vector requirement. Note: any mark that the consumer may need in editable form MUST be specified as editable vector (SVG/AI), not raster.

Derive imagery direction from archetype and sector context: subject matter, mood, composition style, colour treatment, and what to avoid.
Assemble the identity constraint set — the structured seed for downstream skills. Record confidence and evidence_gap verbatim from all three corpus calls.
Human confirms the constraint set before any downstream step runs.
Export — hand off: brand-to-tokens receives the colour + type constraints and emits .tokens.json (DTCG); logo-generation and brand-asset-generation receive the logo direction and imagery direction. Direction of flow: B (pack-brand) -> A (pack-ai-image).

Output format

Colour story — roles (primary, secondary, neutral, accent) with direction (temperature, contrast floor, register), cited from corpus with confidence score.
Type story — heading class and body class derived from the archetype pairing-filter; note that concrete tokens come from typography-system, not from this skill.
Logo direction — mark style, form language, vector requirement (editable SVG/AI where needed), and any explicit exclusions.
Imagery direction — subject matter, mood, composition style, colour treatment, and anti-patterns to avoid.
Confidence + evidence_gap — verbatim from all corpus calls; flag any domain where evidence_gap is high before the human confirmation step.
Handoff note — which constraints go to brand-to-tokens (colour + type) and which go to the generation skills in pack-ai-image (logo direction + imagery direction).

Do NOT

Generate the actual marks here — that is logo-generation and brand-asset-generation.
Invert the dependency direction — generation lives in pack-ai-image (A), not in pack-brand (B).
Ship a raster as a final logo where the consumer needs an editable vector mark.
Override an existing set of brand tokens on a live project without explicit user confirmation.

Gotcha

Identity DEFINES constraints; generation CONSUMES them. Keep the B->A direction in every handoff note.
A type story is a pairing-filter plus heading/body class labels — the concrete type tokens (scale, weight, line-height) come from typography-system, not from this skill.
Vector-vs-raster is a real decision for any mark: confirm with the user before recording the logo direction, because raster is irreversible for downstream editing needs.

What ships with it: 1 file

1.5 KB alongside SKILL.md

evals/

triggers.json1.5 KB