agentleFS
Sign inStart free
connectmachineconnectmachine/claude-plugin/skills/connectmachine/SKILL.md

connectmachine

Skill0 starsChanged 26 days agoMITView on GitHub

Work with the user's ConnectMachine network of professional contacts, networks, events and digital business cards. Use when the user asks who they know, mentions meeting someone, wants to save or update a contact, or wants to follow up with people.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Search by anything the user remembers, not only names.

    line 11
  2. Very specific:

    Use get_contact for full details before drafting anything about a person.

    line 13
  3. Distinctive:

    When the user mentions meeting someone, offer to save them.

    line 17
  4. Very specific:

    Before updating, tagging or deleting a contact by name, call find_contact first.

    line 18

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

ConnectMachine

ConnectMachine holds the user's professional network: contacts with where and when they met, networks (groups such as "Investors"), events, and the user's digital business cards. Use the ConnectMachine MCP tools for anything about people the user knows. Never invent contact details.

Finding people

  • Search by anything the user remembers, not only names. search_contacts and list_contacts (search) match company, job title, notes, location and event names, so "founders in fintech" or "people from WebSummit" work directly.
  • Filter with list_contacts: network_name, country, city, industry_ids (see list_industries).
  • Use get_contact for full details before drafting anything about a person.

Saving and updating

  • When the user mentions meeting someone, offer to save them. Collect what they said: name, company, role, email or phone, where and when they met, and any note.
  • Before updating, tagging or deleting a contact by name, call find_contact first. If it returns status=ambiguous, ask the user which person they mean. Never guess between same-named contacts.
  • Attach where they met with add_events_to_contact. Event names are created if they don't exist.
  • Group contacts with assign_contacts_to_network. Use list_networks to see existing networks before creating a new one.

Follow-ups

Base follow-ups on what ConnectMachine stores: where and when they met, notes, company and role. Keep them short and personal, and show drafts to the user rather than sending anything.

Messages from ConnectMachine

A tool result can include message_for_user. Show it to the user exactly as written, placed where message_for_user_display says, then continue with the answer.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free