- Home
- Skills
- Branding & Design
- π¨ Brand Consistency Linter
More screenshots
Works with the AI Agents you already use
π¨ Brand Consistency Linter
Use it when updating bios, profile READMEs or footer copy so older names, taglines and handles are easier to spot.
$12
π¨ Brand Consistency Linter
Example session with this skill installed
Run the included synthetic risky-sample fixture against the included example brand spec. Show the scanner output without changing any files.
- Read your context and instructions
- Compiled the brand consistency linter
## Included synthetic fixture run This is a representative local run, not a customer result. ```text FINDINGS: 7 BCL001 medium fixtures/risky-sample/profile.md:1 Brand name uses 'Just Handled Lab' instead of 'JustHandled Labs' BCL002 medium fixtures/risky-sample/profile.md:2 Tagline is not in the approved tagline list BCL003 medium fixtures/risky-sample/profile.md:4 Link is not on the official allowlist: example.com BCL004 medium fixtures/risky-sample/profile.md:5 Placeholder text remains: TODO BCL004 medium fixtures/risky-sample/profile.md:2 Placeholder text remains: your tagline here BCL004 medium fixtures/risky-sample/profile.md:5 Placeholder text remains: [brand] BCL005 low fixtures/risky-sample/profile.md:3 Handle 'justhandledlabs' differs from canonical handle 'justhandled' ``` **Exit status:** 1 (findings). Path separators normalized for display. No files rewritten and no network requests. ## Next step Configure your own brand spec before scanning your text, then review the cited lines and decide which changes to make.
Connects securely to your tools. The creator never sees your data.
About this skill
## Check brand drift in supplied text Brand Consistency Linter compares local Markdown and text files with your configured brand-spec.json. Use it when updating bios, profile READMEs or footer copy so older names, taglines and handles are easier to spot. ## What you get A complete SKILL.md package with a standard-library Python scanner, editable brand specification, synthetic examples and regression tests. Findings include rule IDs, severity, source paths and line numbers. The scanner reads files; it does not rewrite your copy or contact external services. ## Checks covered - Canonical name casing/spacing and explicitly configured variants. - Recognized tagline fields against your approved list. - Text URLs against an exact official-link allowlist. - Configured placeholders and differing handles. ## Before you run it Replace the included JustHandled Labs example specification with your own approved values. You need the complete package, Python 3 and an agent host able to read local files and run Python. Review findings before deciding on edits. ## Boundaries This is a text linter, not a visual brand audit, browser URL parser or phishing detector. It does not detect arbitrary misspellings or prove that a missing brand name should have appeared. Unusual joined links, escaped HTML and punctuation can need manual review. It does not verify that links resolve. Lines exceeding 10,000 characters fail as incomplete rather than being reported clean; pathological long lines can be slow. A clean result covers only the supplied text and configured rules, not every brand surface.
Checks only supplied text against configured rules. Does not detect arbitrary misspellings or audit visual identity, live pages or link availability. Exact link allowlists and unusual markup/punctuation can require manual review. Not a browser URL parser or phishing detector. A line longer than 10,000 characters fails as incomplete; pathological long lines can be slow.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 19 days ago
Requires
Permissions
File Scopes
Loads your canonical name, taglines, official links, handle, and placeholder list from an editable references/brand-spec.json. Reads no environment variables and rewrites nothing.