clique-three-surfaces
Skill3 starsChanged 28 days agoMITView on GitHub
CLIque ships as panel/PWA, Windows desktop and Android. Load at the end of any panel feature to decide whether Android needs a port and to record it in clique-android/docs/port-plan.md.
Files
Three surfaces
The panel is the product. Two clients wrap it, and a new feature does not reach them on the same terms:
| What it is | What a new panel feature costs it | |
| PWA | the panel, installed | nothing, it is the same page |
Desktop (clique-desktop) | a Windows window around the panel | nothing, it is a webview of the same page |
Android (clique-android) | a native app with its own terminal | a port, every time |
So the question at the end of a feature is only ever about the phone, and it
gets asked out loud rather than assumed: does Android need this, and if not,
why not? A yes becomes a tiered row in clique-android/docs/port-plan.md, a
no goes in that file's Tier 3, which exists so leaving something out is a
decision on the record instead of an oversight.
Three releases, none implied by another: PyPI for the panel, our own F-Droid repo for the phone, a GitHub release for the desktop exe.
In this repository11 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- animateSkill
- animation-vocabularySkill
- apple-designSkill
- clique-motionSkill
- clique-release-checkSkill
- emil-design-engSkill
- find-animation-opportunitiesSkill
- improve-animationsSkill
- review-animationsSkill
- drive-cliqueSkill
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.