Systems Lab

Agent skill

brand-review

Review a rendered graphic or visual system for message clarity, identity consistency and export quality; make fixes when requested.

activeSelf-containedInstructions only225 words

From timscheuerai/gtm-architecture-template · 51 skill entries · 13 · pushed 2026-09-17

What it does when it runs

Review a rendered graphic or visual system for message clarity, identity consistency and export quality; make fixes when requested.

Automated analysis of the skill and the 0 files bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.

Keys and connectors you must supply
None found.
Hosts it reaches
No third-party host appears in the skill or its bundled files.
Tool permissions it declares
No allowed-tools in the frontmatter. It only issues instructions, so there is nothing to bound.
Actions present in the files
None. Instructions only.

Ask about brand-review

Opens your assistant with this page's verified links already in the prompt.

Is this safe to install?ClaudeChatGPT
Adapt it to my stackClaudeChatGPT
What else do I need for it to workClaudeChatGPT
Rather ask a human? Talk to Cheetah

Install it

View source on GitHub ↗
git clone --depth 1 --filter=blob:none --sparse https://github.com/timscheuerai/gtm-architecture-template.git /tmp/gtm-architecture-template
git -C /tmp/gtm-architecture-template sparse-checkout set ".agents/skills/brand-review"
mkdir -p ~/.claude/skills/brand-review
cp -R "/tmp/gtm-architecture-template/.agents/skills/brand-review/." ~/.claude/skills/brand-review/

Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗

The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.

The skill

Source on GitHub ↗

Reproduced in full from timscheuerai/gtm-architecture-template/blob/2c312c9398064ad3730c786647293458cb89632c/.agents/skills/brand-review/SKILL.md, which is licensed MIT (repository). 225 words, 1 heading.

Workspace: all context paths below (identity, audience, strategy, voice, brand, raw, output, index, log, workspace preferences and context scripts) resolve from context/ in the kit root. Read both the root AGENTS.md and context/AGENTS.md. Skill-local references/ and flowchart scripts/ resolve from this skill directory.

Review the visual

Read brand/BRAND.md, the asset brief and only the supporting context needed to assess the work. If the brand guide is blank, review clarity and execution; do not invent brand-compliance failures.

Inspect the actual rendered artifact at the intended size and a small viewing size. With only a screenshot, distinguish visible findings from checks requiring editable source.

Assess:

  • Meaning: the takeaway, reading order, truthful relationships and evidence.
  • Identity: consistency with approved rules, where rules exist.
  • Craft: text size, line breaks, alignment, spacing, contrast, clipping and connector collisions.
  • Delivery: dimensions, loaded fonts, linked assets and editable/export files when supplied.

Give the few highest-impact findings with a location, effect on the reader and concrete correction. Separate functional defects, conflicts with adopted rules and subjective preferences. Avoid numerical quality scores without a defined rubric.

Review is report-only unless fixes were requested. For fixes, stay within the asset's scope, preserve user edits, rerender and inspect the result. Reviewing a single asset does not authorize global brand changes, Notion edits or publication.

Lead with the assessment and state inspection limits.

Other skills for the same job

Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.

Need help setting it up?

This page tells you what brand-review does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.

Book a call →

The directory stays free. There is nothing gated behind this.