Markilo brand audit — evaluate an existing logo or identity (small-size legibility, balance, monochrome, contrast, genericity, similarity to competitors, name confusion) and recommend keep, refresh or redesign with evidence. Use when the user asks for feedback on, or an assessment of, an existing logo or brand.
Installs into .claude/skills of the current project.
Are you the author of Audit?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/cihantopac-audit-markilo)
---
name: audit
description: Markilo brand audit — evaluate an existing logo or identity (small-size legibility, balance, monochrome, contrast, genericity, similarity to competitors, name confusion) and recommend keep, refresh or redesign with evidence. Use when the user asks for feedback on, or an assessment of, an existing logo or brand.
argument-hint: "[logo file, URL, repo path or brand slug]"
allowed-tools: Bash(node "${CLAUDE_PLUGIN_ROOT}/dist/markilo.mjs" *) Bash(node ${CLAUDE_PLUGIN_ROOT}/dist/markilo.mjs *) Read Write Edit Glob Grep
---
# Markilo · Audit
Request: $ARGUMENTS
Toolchain: `node "${CLAUDE_PLUGIN_ROOT}/dist/markilo.mjs" <command>` (written `markilo`). Run every toolchain command as its own Bash call, written out in full (`node "${CLAUDE_PLUGIN_ROOT}/dist/markilo.mjs" <command> …`). Do not wrap it in shell variables, `cd`, `&&` chains or pipes: the plugin pre-approves exactly that form, so anything else triggers permission prompts. Read `${CLAUDE_PLUGIN_ROOT}/skills/design/references/design-principles.md` (refresh vs. redesign).
1. Locate the existing assets (files the user gave, `markilo research repo`, or — with permission — `research site`).
`Read` them.
2. Measure: `markilo score <file> --role symbol|wordmark|lockup`, `markilo analyze <file>`,
`markilo render <file> -o <tmp>.png --sheet` and `Read` the sheet.
3. Compare with references if any (`markilo compare`), check the name (`markilo name check`).
4. Report: what works (equity worth keeping), measured problems, judgment-based problems (labeled), and a
recommendation — keep, refresh or redesign — with the evidence. Do not redesign during an audit; offer it.
5. Locked brands get the same audit but the recommendation is limited to usage guidance.