agentleFS
Sign inStart free
michelgroletmichelgrolet/people-memory-mcp/skills/import-contacts/SKILL.md

import-contacts

Skill1 starsChanged 3 months agoMITView on GitHub

Import people into People Memory with built-in LinkedIn Connections CSV, Google Contacts CSV, and WhatsApp export support, or an agent-reviewed mapping for vCards and arbitrary CSV/JSON; preview fields, normalize identifiers, deduplicate, surface ambiguous identities and conflicting values, and report results. Use when the user says import, migrate, seed, sync, deduplicate, merge contacts, LinkedIn, Google Contacts, WhatsApp export, address book, vCard, or contact CSV.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. nitrosend/claude★ 3same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository8 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 7 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    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
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Import official exports conservatively.

    line 8
  2. Distinctive:

    Read references/formats.md for that source only.

    line 14
  3. Distinctive:

    Ask the user whether to proceed when the export includes sensitive fields they did not request.

    line 16
  4. Very specific:

    Run the matching people-memory import command.

    line 17
  5. Very specific:

    Run the duplicate and orphan checks from maintain-people-memory.

    line 20
  6. Distinctive:

    Do not auto-merge two people because their names are similar.

    line 32
  7. Distinctive:

    Keep an existing value when the import conflicts.

    line 38
  8. Distinctive:

    Keep raw export files outside Git and delete them when the user no longer needs them.

    line 41
  9. Distinctive:

    Never upload contact exports to an external model or service without explicit approval.

    line 42

≈ “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

Import contacts

Import official exports conservatively. Preserve source, keep existing stated values, and stop on identity ambiguity.

Workflow

  1. Identify the source and inspect headers or a small sample. Never print private rows in full.
  2. Read references/formats.md for that source only.
  3. Preview the record count, fields found, identifiers available, and fields that will be ignored.
  4. Ask the user whether to proceed when the export includes sensitive fields they did not request.
  5. Run the matching people-memory import command. For other formats, show the mapping and use remember_person only after approval.
  6. Report created, updated, ambiguous, conflicting, and skipped counts.
  7. Run the duplicate and orphan checks from maintain-people-memory.

Identity order

Resolve in this order:

  1. normalized email;
  2. normalized phone;
  3. LinkedIn URL or source-native stable identifier;
  4. exact normalized full name;
  5. similar name only as a candidate requiring the user's decision.

Do not auto-merge two people because their names are similar. Do not auto-create a similar name when the source lacks an identifier. Ask whether it is the existing person or someone new.

Write rules

  • Fill empty fields from imports.
  • Keep an existing value when the import conflicts.
  • Surface the conflict with existing and incoming values.
  • Save source-specific dates as observed facts or interactions.
  • Keep raw export files outside Git and delete them when the user no longer needs them.
  • Never upload contact exports to an external model or service without explicit approval.

For an unfamiliar CSV, infer a proposed mapping, show it, and ask before writing. Prefer a reusable mapping file or importer change when the format will recur.

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