upgrade-scan
Skill311 starsChanged 18 days agoMITView on GitHub
Review project changes and suggest adoption steps after a superlite upgrade
In this repository18 other files it gives its agents.
- AGENTS.mdAGENTS.md
- commands/agents.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/feature-worktrees.mdcCursor rule
- .cursor/rules/no-cursor-commit-notes.mdcCursor rule
- diagnosisSkill
- draftingSkill
- feature-prototypeSkill
- inventingSkill
- mergedSkill
- mvp-prototypeSkill
- proofSkill
- researchSkill
- shippingSkill
- swarmSkill
- testingSkill
- using-superliteSkill
- writing-specsSkill
The file
Files
Review this repository against the changes in superlite since the previously installed version. Use the current version in .claude-plugin/plugin.json and any other .git/info/superlite-upgrade-scan-* markers to identify the previous version. Read the release notes and relevant commit messages between those versions when available. If no previous version is known, review the current release notes and recent superlite changes.
Suggest relevant improvements only:
- Find legacy prototype worktrees or branches ending in
-proto, including worktrees directly under.superlite/sandboxes/<topic>-proto/. - Find worktrees under the old
.superlite/worktrees/home. - Suggest any settings, plans, or habits this version handles better.
For each legacy layout, explain how the user could move wanted changes into the current layout or remove the old worktree/branch. Report findings and suggestions only. Do not move, edit, or delete anything; wait for the user's yes before making any change.
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.