rebrand
Skill0 starsChanged 47 days agoMITView on GitHub
Rebrand Sorted for another council (name, colours, case prefix and an optional crest), then check every page at desktop and phone sizes. Use when asked to rebrand or re-skin it, or to make it look like another council's.
4 other projects use a version of this.
Adopted by
Most recently taken up by
- davision0102/fabriktheir own version, first seen Nov 15, 2026
- A70III/ateliertheir own version, first seen Sep 22, 2026
- ahpxex/open-dashboardtheir own version, first seen Jun 18, 2026
- platformplatform/PlatformPlatformtheir own version, first seen May 15, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- platformplatform/PlatformPlatform★ 439same name
- ahpxex/open-dashboard★ 136same name
- davision0102/fabrik★ 3same name
- A70III/atelier★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository11 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- content/CLAUDE.mdCLAUDE.md
- evals/CLAUDE.mdCLAUDE.md
- scripts/CLAUDE.mdCLAUDE.md
- seed/CLAUDE.mdCLAUDE.md
- static/CLAUDE.mdCLAUDE.md
- checkSkill
- evalSkill
- resetSkill
- screenshotsSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 9
If a crest is wanted, draw it as static/shared/marks/<short-name>.svg: viewBox="0 0 64 64", drawn in currentColor so it takes the header's …
- Very specific: line 10
Make sure the app is running on 8800 (curl -s http://localhost:8800/api/health).
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Rebrand to: $ARGUMENTS
- Read
content/brand.json, including its_aboutnote: it sets the rules.colouris the header and button colour and must take white text at 4.5:1 or better;accenthighlights the Demo badge and focus rings;placeis the short name used in sentences;case_prefixstarts every case reference. Never reuse "Mersey Vale" or "MVCC" inside the new name. - If a crest is wanted, draw it as
static/shared/marks/<short-name>.svg:viewBox="0 0 64 64", drawn incurrentColorso it takes the header's text colour.humpington-pirate.svgis a worked example. Put its file name inmark, or leavemarkempty for the standard gull and waves. - Make sure the app is running on 8800 (
curl -s http://localhost:8800/api/health). If it isn't, start it withscripts/start_server.sh, withoutFT_RESET. - Save
content/brand.json. Both sites change on the next page load, and screens opened with?live=1reload by themselves. To preview a brand without saving it, write it to a temporary file and pass that file to the check below with--try. - Run
uv run --with playwright python scripts/brand_check.py. It uses the installed Google Chrome, in its own profile. If any view fails (the old name still showing, a broken logo, low contrast, a page wider than the screen, a console error), fix the cause and run it again until every view passes. - Report the new brand, the contact sheet at http://localhost:8800/dev/brand-check/, and how to undo it:
git restore content/brand.json, and delete the crest file if you made one.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

