Agent skill
imsg-ingest
Primary iMessage interface. Full-featured CLI for message export, conversation management, contact resolution, and thread state. Use when user mentions "imessage", "imsg", "text message", "iphone messages", or phone numbers. Triggers: "imessage messages", "export imessage", "text from john", "imessage contacts", "sync imessage". This is STANDALONE - do not defer to unified-messages for iMessage operations.
Install this agent skill to your Project
npx add-skill https://github.com/rohunvora/cool-claude-skills/tree/main/skills/imsg-ingest
SKILL.md
iMessage Export (imsg-ingest)
Primary interface for all iMessage operations. Standalone and full-featured.
Location: /Users/satoshi/data/imsg-ingest
Quick Start
cd /Users/satoshi/data/imsg-ingest
# Check access (MUST have Full Disk Access)
poetry run imsg status
# Sync messages
poetry run imsg sync
# List conversations
poetry run imsg list
# Export specific conversation
poetry run imsg dump "+14155551234" --output john.jsonl
Prerequisites
Full Disk Access required. See references/setup.md for setup.
Core Workflows
Quick Export for AI Context (Recommended)
Get recent messages as markdown, ready to paste into Claude:
# Syncs first, outputs to stdout (last 24h)
python scripts/quick_export.py "+14155551234"
# By contact name
python scripts/quick_export.py "John Doe" --hours 48
# Copy to clipboard
python scripts/quick_export.py "+14155551234" | pbcopy
# Visual copy in browser
python scripts/quick_export.py "+14155551234" | quick-view
# Intentional save
python scripts/quick_export.py "+14155551234" --save
# → exports/14155551234_2026-01-02.md
See references/files.md for file management philosophy.
Export via CLI (Alternative)
# By phone number
poetry run imsg dump "+14155551234" --output john.jsonl
# By email
poetry run imsg dump "john@example.com" --output john.jsonl
# By name (searches contacts)
poetry run imsg dump "John Doe" --output john.jsonl
# Last 7 days only
poetry run imsg dump "+14155551234" --last 7d --output john.jsonl
Sync Operations
# Sync new messages (forward)
poetry run imsg sync
# Backfill older messages
poetry run imsg sync --backfill
List Conversations
# All conversations
poetry run imsg list
# DMs only
poetry run imsg list --no-groups
# Groups only
poetry run imsg list --no-dms
# With minimum message count
poetry run imsg list --min-messages 10
Export All Conversations
# Export all with 10+ messages
poetry run imsg dump-all --min-messages 10
# Limit messages per chat
poetry run imsg dump-all --limit-per-chat 500
Contact Resolution
# Check contact system status
poetry run imsg contacts status
# Lookup a contact
poetry run imsg contacts lookup "+14155551234"
# List all contacts
poetry run imsg contacts list
# Refresh contacts from AddressBook
poetry run imsg contacts sync
# Update exports with contact names
poetry run imsg contacts refresh-exports
See references/contacts.md for resolution backends.
Data Locations
| Path | Purpose |
|---|---|
data/conversations/ |
Exported conversations (*.jsonl) |
data/sync-state.json |
Sync state (rowid tracking) |
data/context/state.json |
Thread states (done/draft/snooze) |
Source Database
~/Library/Messages/chat.db
Read-only SQLite access. Requires Full Disk Access.
Thread ID Format
iMessage threads use format: imsg:dm:identifier or imsg:group:chatID
Examples:
imsg:dm:+14155551234- DM with phone numberimsg:dm:john@example.com- DM with emailimsg:group:chat123456- Group chat
Thread State
State stored in data/context/state.json. Same format as tg-ingest:
{
"imsg:dm:+14155551234": {
"status": "pending",
"draft": null,
"note": "Follow up on project",
"snooze": null
}
}
States: pending, done, archived
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
comment-mode
Granular feedback on drafts without rewriting. Generates highlighted HTML with click-to-reveal inline comments. Use when user says "comment on this", "leave comments on", "give feedback on", or asks for feedback on a draft. Supports multiple lenses—editor feedback, POV simulation ("as brian would react"), or focused angles ("word choice only", "weak arguments"). A granular alternative to rewrites that lets users review feedback incrementally without losing their voice.
ai-loading-ux
Design AI loading, thinking, and progress indicator UX. Use when explicitly asked to improve AI waiting states, add thinking indicators, or design loading UX for AI interfaces. Covers reasoning display (chain-of-thought), progress steps, streaming states, and the "elevator mirror effect" for reducing perceived wait time.
arena-cli
CLI tools for Are.na: export blocks, enrich with vision AI, generate views. Use when: (1) exporting Are.na blocks incrementally, (2) enriching images with AI-generated titles/tags/patterns, (3) generating browsable HTML views, (4) searching blocks by UI patterns or tags, (5) visual search results when terminal output is insufficient. Triggers: "export arena", "enrich arena", "sync arena", "arena view", "search arena for [pattern]", "show me [pattern]".
unified-messages
Cross-platform messaging aggregator. Use as DEFAULT when user does NOT specify a platform (telegram/imessage). Provides unified inbox, search, and triage across both platforms. Triggers: "check messages" (no platform), "inbox", "who messaged me", "all my messages", "triage". NOT for platform- specific requests - use tg-ingest for "telegram X" or imsg-ingest for "imessage X".
html-style
Apply opinionated styling to barebones HTML. Use when user has plain/unstyled HTML and wants to apply consistent visual styling. Triggers: style this HTML, apply styling, make this look good, /html-style, or when user shares HTML that needs CSS. Transforms tables, lists, status indicators, buttons, and layouts into a cohesive design system.
mobbin-ux
Research-driven UI/UX improvement using Mobbin. Use when user explicitly requests design pattern research ("use Mobbin", "research design patterns", "find UX patterns for X"). Requires Mobbin account and browser automation (claude-in-chrome MCP). Searches Mobbin for relevant UI patterns, extracts design principles, generates a spec document for approval, then implements. NOT for general UI work—only when user wants research-backed design.
Didn't find tool you were looking for?