Organize Google Contacts

What it does

When your agent uses it

• The user wants to: search people they know
• Find someones email
• Update a contact
• Add meeting notes

Example prompts

• “/organize-google-contacts”

Requirements

• Node.js
• A credential in RAREFRIEND_CLIENT_SECRET
• Compatibility (from SKILL.md): Requires Rarefriend MCP (@rarefriend-ai/mcp). Works with Claude Code, Cursor, Codex, OpenClaw, Gemini CLI, and other Agent Skills-compatible clients.

Workflow steps

2 steps, taken from the first numbered list in SKILL.md.

1. 1search_contacts("Sequoia", searchMode="company")
2. 2Loop add_tag(contactId, "investor") for each result

What it can do on your machine

Read from SKILL.md and the folder at commit 44923f3. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • claude

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • rarefriend.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • RAREFRIEND_CLIENT_SECRET

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Requires Rarefriend MCP (@rarefriend-ai/mcp). Works with Claude Code, Cursor, Codex, OpenClaw, Gemini CLI, and other Agent Skills-compatible clients.

  From compatibility in the SKILL.md frontmatter.

Context cost

Organize Google Contacts loads about 2.2k tokens when it runs, and up to ~2.6k if it reads all its reference files. Until then it costs about 171 tokens; SKILL.md has 574 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~171

When it runs · the whole SKILL.md, loaded when a task matches

~2.2k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~2.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from aiskillstore/marketplace at commit 44923f3, republished under its MIT-0 licence (© aiskillstore). 574 words, ~2,223 tokens.

name

organize-google-contacts

description

Your Google Contacts — supercharged with notes, tags, and relationship memory via Rarefriend. Find anyone instantly, remember every conversation, and never lose context on a person again. Use when the user wants to: search people they know, find someone's email or phone, create or update a contact, add meeting notes or call summaries, tag contacts, bulk import a list of people, connect Google Contacts, or check what they know about someone. Triggers on: contact, contacts, Google Contacts, who do I know, find someone, person, people, notes about, meeting notes, tag, import contacts, network, what do I know about, who is, remember this about, add a note.

compatibility

Requires Rarefriend MCP (@rarefriend-ai/mcp). Works with Claude Code, Cursor, Codex, OpenClaw, Gemini CLI, and other Agent Skills-compatible clients.

license

MIT-0

user-invocable

true

argument-hint

[setup|search|create|notes|tags|import|connect]

metadata.category

productivity

metadata.author

Rarefriend

metadata.homepage

https://rarefriend.com

metadata.repository

https://github.com/Whitefield-Labs/rarefriend-skills

search_contacts(query, searchMode?, tag?, source?, limit?, offset?)
  searchMode: 'all' | 'name' | 'company' | 'role' | 'email' | 'exact'
  tag:        filter to contacts with this exact tag (e.g. "investor")
  source:     filter by origin — 'google_contacts' | 'manual' | 'mcp' | 'linkedin_csv' | ...

get_contact(contactId)   — full profile; call only when user needs details on one person

create_contact(displayName*, firstName?, lastName?, emails?, phones?,
               company?, role?, location?, bio?)

update_contact(contactId, ...same optional fields...)

create_note(contactId, content, isPinned?)
update_note(noteId, content?, isPinned?)
delete_note(noteId)
list_notes(contactId, limit?, offset?)
get_note(noteId)
pin_note(noteId, pinned)
search_notes(query, limit?)     — full-text across ALL contacts
get_recent_notes(limit?)        — most recent notes, any contact

list_tags()
add_tag(contactId, tag)         — lowercase kebab-case
remove_tag(contactId, tag)
rename_tag(oldTag, newTag)      — renames across all contacts

bulk_create_contacts(contacts[])
  Each: { displayName*, firstName?, lastName?, emails?, phones?,
          company?, role?, location?, bio? }
  Max 50 per call — split larger lists and call sequentially.

connect_integration("google_contacts")

get_integration_sync_status("google_contacts")

© aiskillstore, MIT-0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in skills/whitefield-labs/organize-google-contacts of aiskillstore/marketplace.

• SKILL.md
• references/SETUP.md
• skill-report.json

Open the folder on GitHubat commit 44923f3