get-started
Skill2 starsChanged 4 months agoMITView on GitHub
First run with Rams. Connect the Rams design reviewer, run a quick check on one UI file, then a full scored review, then confirm the fixes landed. Use when someone has just installed Rams or asks how to start.
23 other projects use a version of this.
Adopted by
Most recently taken up by
- blovett80/synero-mcptheir own version, first seen Nov 8, 2026
- Protoduct-AI/ledgie-plugintheir own version, first seen Nov 8, 2026
- chatmaxima-com/chatmaxima-skillstheir own version, first seen Nov 8, 2026
- pschlieker/getbacklanetheir own version, first seen Nov 8, 2026
- anotb/forward-deployedtheir own version, first seen Nov 8, 2026
- LeadMagic/leadmagic-claude-plugintheir own version, first seen Nov 3, 2026
Other versions23 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 23
- glifxyz/glif-mcp-server★ 213same name
- different-ai/openwork-hub★ 35same name
- gomarble-ai/marketing-agent★ 15same name
- katalon-labs/true-skills★ 10same name
- PicsArt/gen-ai-skills★ 6same name
- Marky-Team/marky-skills★ 5same name
- multiples-hq/business-state-machine-mcp★ 2same name
- anotb/forward-deployed★ 1same name
- asimokat/imzala-eklenti★ 1same name
- freigent/freigent-plugin★ 1same name
13 more not listed
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 repositoryOne other file it gives its agents.
- ramsSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 0 are distinctive, and 5 are very specific to this project.
0
Common
Most of the 22 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 25
Ask for one UI file the user is working on, or a component they can paste.
- Very specific: line 26
Call quick_review with the file path and its full content.
- Very specific: line 33
When the user wants a score or ready-made fixes, call review_files once on the same files.
- Very specific: line 43
After fixes are applied, call verify_fixes with the updated files and the issues from step 3.
- Very specific: line 49
If the user asks how many reviews they have left, call usage and relay the answer as written.
“Common” is measured: kept by at least 6 in 10 of the 22 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Get started with Rams
Rams reviews UI code (React, Vue, Svelte, CSS, SwiftUI) for visual design and accessibility. It reads the files you send it and returns findings with severity, category and file:line. It does not edit files, run code, open pull requests or touch any repository. Applying a fix is always your step.
Walk the user through these four steps in order. Keep each step short and show the real tool output.
1. Connect
The first Rams tool call asks the user to sign in at rams.ai with Google or GitHub and approve access. There is no key to paste. If a tool call fails with an authorization error, ask the user to connect Rams from the plugin settings and try again.
2. Run a quick check
Ask for one UI file the user is working on, or a component they can paste.
Call quick_review with the file path and its full content. It answers in
about ten seconds with the top issues. It returns no score and no patch.
Show the issues as a short list: severity, what is wrong, and file:line.
3. Run a full review
When the user wants a score or ready-made fixes, call review_files once on
the same files. It returns a 0-100 score, a one-line summary, and issues with
fixes. Many issues include a unified diff in patch that applies with
git apply.
Show the score first, then the issues from most to least severe. Offer to apply the patches. Only apply one after the user agrees.
4. Verify the fixes
After fixes are applied, call verify_fixes with the updated files and the
issues from step 3. It reports which issues are fixed and which are still
present.
Usage
If the user asks how many reviews they have left, call usage and relay the
answer as written.
Limits
- Rams judges UI code only. For backend code, configs or tests, say Rams has nothing to review there.
- Rams only sees the content sent in the call. It cannot read a repository on its own.
- Rams cannot deploy, merge, change billing or act on anyone's account.
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.