AGENT SKILL

imessage-signal-analyzer

Analyze iMessage (macOS) and Signal conversation history to reveal relationship dynamics — message volume, initiation patterns, silence gaps, tone samples, and recent exchanges. Use when asked to analyze messages, read message history, check conversation patterns, or evaluate a relationship based on text history. Works on macOS (iMessage + Signal), Linux/Windows (Signal only).

License 许可
MIT
最近更新
2026-06-07
Stars
★ 0
Forks
1

01 前言 Front Matter

name
imessage-signal-analyzer
description
Analyze iMessage (macOS) and Signal conversation history to reveal relationship dynamics — message volume, initiation patterns, silence gaps, tone samples, and recent exchanges. Use when asked to analyze messages, read message history, check conversation patterns, or evaluate a relationship based on text history. Works on macOS (iMessage + Signal), Linux/Windows (Signal only).

03 SKILL.md 正文

iMessage & Signal Analyzer

Analyze iMessage (macOS) and Signal conversations to produce relationship reports.

Prerequisites

macOS (iMessage)

iMessage data is stored locally on macOS. Depending on your security settings, you may need to grant Full Disk Access:

Option 1: Run the script directly with Python (no special permissions needed if you have read access to ~/Library/Messages/chat.db)

Option 2: If you get a permission error, grant Full Disk Access:

  • Open System Settings → Privacy & Security → Full Disk Access
  • Click + and add Python or your terminal app

Linux / Windows (Signal only)

  • iMessage is not available on Linux/Windows
  • Signal analysis works via exported JSON

Signal (All Platforms)

  • Install signal-cli: brew install signal-cli (macOS) or see https://github.com/AsamK/signal-cli
  • Link your device: signal-cli link and scan QR code
  • Export messages: signal-cli export --output ~/signal_export.json

Usage

iMessage Analysis

python3 skills/message-analyzer/scripts/analyze.py imessage <phone_or_handle>

Examples:

python3 skills/message-analyzer/scripts/analyze.py imessage "+15551234567"
python3 skills/message-analyzer/scripts/analyze.py imessage "+15551234567" --limit 500

Signal Analysis

First, export your Signal data (one-time):

signal-cli export --output ~/signal_export.json

Then analyze:

python3 skills/message-analyzer/scripts/analyze.py signal ~/signal_export.json <phone_or_name>

Examples:

python3 skills/message-analyzer/scripts/analyze.py signal ~/signal_export.json "+15551234567"
python3 skills/message-analyzer/scripts/analyze.py signal ~/signal_export.json "+15559876543"

Finding a Contact's Number

iMessage

If you have a name but not a number:

DB=$(ls ~/Library/Application\ Support/AddressBook/Sources/*/AddressBook-v22.abcddb 2>/dev/null | head -1)
sqlite3 "$DB" "SELECT ZFIRSTNAME, ZLASTNAME FROM ZABCDRECORD WHERE ZFIRSTNAME LIKE '%Name%';"

If AddressBook returns no results, ask the user for the number.

Signal

Signal exports include phone numbers in the JSON. Search by name or number.

Key Data Caveats

iMessage

  • Your sent messages may only exist from the current device's setup date — older sent messages are lost when switching devices. This skews initiation stats.
  • Binary messages (attributedBody) are partially decoded — some formatting artifacts like +@ prefixes may appear in samples; these are normal.
  • Multiple handles: One contact may have 2–3 duplicate handles (iMessage + SMS + RCS). The script aggregates them automatically.

Signal

  • Export required: You must export Signal data first using signal-cli export
  • Media: Exported JSON contains message text; media (images, files) is not included
  • Reactions: Emoji reactions are included as separate message entries

Analysis Output

The script produces:

  • Total message count (you vs. them)
  • Date range
  • Messages per year with volume bar
  • Conversation initiation breakdown (new convo = gap > 4 hours)
  • Notable silences (>30 days)
  • Sample messages by year
  • Most recent 10 messages

Interpreting Results

After running the script, synthesize findings conversationally:

  • Volume patterns: When was the friendship most active? Any notable surges or drops?
  • Initiation skew: Who reaches out first? (Note: your sent messages may be missing from old periods)
  • Gaps: Were long silences mutual drift or explainable (device switch, platform change, life event)?
  • Tone/content: What do the sample messages reveal about the relationship's energy?
  • Context from user: Always ask the user to fill in context gaps

Present the analysis conversationally, not just as raw numbers. Offer a genuine take on the relationship dynamic.

04 同仓库更多 Skills

javimosch
javimosch/open-claw-skills

crowd-prompting

A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.

★ 0
javimosch
javimosch/open-claw-skills

ceaser

Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir/UltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).

★ 0
javimosch
javimosch/open-claw-skills

ceaser-send

Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir/UltraHonk zero-knowledge proofs.

★ 0
javimosch
javimosch/open-claw-skills

dilemm-ai

Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).

★ 0
javimosch
javimosch/open-claw-skills

moldium

Post and manage content on the Moldium blog platform. Triggered by "post to Moldium", "write a blog post", "publish an article", etc.

★ 0
javimosch
javimosch/open-claw-skills

arxiv-paper-reviews

Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date/category/interest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http://weakaccept.top:8000/.

★ 0