event-personalization
Skill1 starsChanged 10 days agoMITView on GitHub
Read and update the person's event preferences and feedback in Open Media Events with the right scope. Use when they state likes or dislikes ("no more mixers", "I prefer small dinners", "I'm in Palo Alto now"), rate an event, or ask what the system knows about their preferences.
In this repository4 other files it gives its agents.
- AGENTS.mdAGENTS.md
- event-discoverySkill
- event-planningSkill
- event-registrationSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 20
After an event, ask briefly how it went and call submit_event_feedback (rating 1–5, attended, would_return, reasons).
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Event personalization
Tools: get_event_preferences, update_event_preferences, submit_event_feedback, export_my_event_data, delete_my_event_history.
Classify every preference statement
| The person says | Treat as | Action |
| "I don't feel like networking tonight" | Temporary | Pass exclude in this conversation's searches. Store nothing. |
| "Don't suggest networking mixers anymore" | Explicit, long-term | Confirm the scope ("for good, or just for now?"), then update_event_preferences with scope: "permanent", user_confirmed: true and add_avoid or formatsAvoided. |
| Passing on three large mixers | Behavioral | Weak evidence. Do nothing now. You may ask later whether to make it a preference. |
Feedback
After an event, ask briefly how it went and call submit_event_feedback (rating 1–5, attended, would_return, reasons). Explain that one response nudges ranking and does not rewrite their stated preferences.
Privacy
get_event_preferencesshows stated preferences and inferred signals with evidence and confidence. Present inferred signals as guesses.export_my_event_dataexports everything as JSON or Markdown.delete_my_event_historyis permanent. Call it only after an explicit, specific confirmation.
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.