skills / rules
Cursor rule82 starsChanged 8 months agoMITView on GitHub
When editing this repository, preserve skill-tree integrity, relative links, and packaging layout.
We split this zoom-skills-repo.mdc into the rules it gives an agent
5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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 19
Keep skill content under skills/
- Distinctive: line 20
Keep packaging manifests at repo root:
- Distinctive: line 24
Use repository-relative markdown links only
- Distinctive: line 25
Do not commit machine-local absolute paths
- Very specific: line 26
Keep skills/SKILL.md as the skill-bundle entrypoint
≈ “Common” is an estimate: at least 1 in 5 of the 6,350 Cursor rule 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
--- description: When editing this repository, preserve skill-tree integrity, relative links, and packaging layout. alwaysApply: false globs: - "README.md" - "ARCHITECTURE.md" - "CONTRIBUTING.md" - "RUNBOOK.md" - "skills/**/*.md" --- # Zoom Skills Repository This repository uses a packaging root plus an installable skill tree: - packaging/docs at repo root - installable skills under `skills/` ## Rules - Keep skill content under `skills/` - Keep packaging manifests at repo root: - `.claude-plugin/` - `.cursor-plugin/` - `.mcp.json` - Use repository-relative markdown links only - Do not commit machine-local absolute paths - Keep `skills/SKILL.md` as the skill-bundle entrypoint ## After structural edits Run: ```bash python3 tools/md-audit/md_audit.py --root . --exclude raw-docs --exclude md-graph --exclude tools/zoom-crawler node md-graph/build-graph.mjs . md-graph/data.json ``` Copy the refreshed graph to the hosted viewer when applicable.
Where files are headingNew Cursor rule files have more rules about planning and tracking tasks, and fewer about code style.
Of the Cursor rule files we read, the 3,978 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository58 other files it gives its agents.
- .cursor/rules/zoom-platform.mdcCursor rule
- .cursor/rules/zoom-security.mdcCursor rule
- zoom-cobrowse-sdkSkill
- contact-center/androidSkill
- contact-center/iosSkill
- contact-centerSkill
- contact-center/webSkill
- zoom-generalSkill
- zoom-meeting-sdk-androidSkill
- zoom-meeting-sdk-electronSkill
- zoom-meeting-sdk-iosSkill
- meeting-sdk/linuxSkill
- zoom-meeting-sdk-macosSkill
- zoom-meeting-sdk-react-nativeSkill
- zoom-meeting-sdkSkill
- zoom-meeting-sdk-unrealSkill
- zoom-meeting-sdk-webSkill
- zoom-meeting-sdk-windowsSkill
- zoom-oauthSkill
- phoneSkill
- zoom-plugin-sdk-macosSkill
- zoom-plugin-sdkSkill
- zoom-plugin-sdk-windowsSkill
- probe-sdkSkill
- zoom-rest-apiSkill
- rivet-sdkSkill
- zoom-rtmsSkill
- scribeSkill
- zoom-skillsSkill
- summarizerSkill
- zoom-team-chatSkill
- translatorSkill
- ui-toolkit-webSkill
- zoom-video-sdk-androidSkill
- zoom-video-sdk-flutterSkill
- zoom-video-sdk-iosSkill
- video-sdk/linuxSkill
- zoom-video-sdk-macosSkill
- zoom-video-sdk-react-nativeSkill
- zoom-video-sdkSkill
- zoom-video-sdk-unitySkill
- video-sdk-webSkill
- video-sdk/windowsSkill
- virtual-agent/androidSkill
- virtual-agent/iosSkill
- virtual-agentSkill
- virtual-agent/webSkill
- zoom-webhooksSkill
- zoom-websocketsSkill
- zoom-apps-sdkSkill
- zoom-mcp/canvasSkill
- zoom-mcp/docsSkill
- zoom-mcp/meetingsSkill
- zoom-mcp/revenue-acceleratorSkill
- zoom-mcpSkill
- zoom-mcp/tasksSkill
- zoom-mcp/team-chatSkill
- zoom-mcp/whiteboardSkill
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.

