Token导航 LogoToken导航TokenDH.com
研究检索执行命令github未标认证来源可访问clear审计未展示

signal-history-search信号历史搜索

Agent Skill

signal-history-search 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

428

周安装

18

GitHub Stars

公开资料未说明

下载量

150
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:signal-history-search(信号历史搜索)
来源仓库:https://github.com/nicolaischmid/agent-inbox-tools
仓库路径:skills/signal-history-search
安装命令:
npx skills add nicolaischmid/agent-inbox-tools --skill "signal-history-search"
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

AgentSkills.tonpx skills
npx skills add nicolaischmid/agent-inbox-tools --skill "signal-history-search"

简介

用于搜索 Signal 消息历史记录中的相关信息。

  • 适用于需要根据关键词或场景在 Codex、Claude、Cursor、Gemini CLI 中快速筛选通信内容的任务。
  • 通过 npx 命令从 GitHub 仓库安装,支持灵活集成。
  • 安装前建议检查维护状态及是否涉及敏感数据访问权限。
  • signal-history-search 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

name
signal-history-search
description
Search Signal Desktop message history on macOS with sub-second query times. Queries the encrypted SQLite database directly without export overhead.
license
MIT
metadata
author
Nicolai Schmid
version
1.0.0
requires
scripts
search
./scripts/signal-search

Signal History Search

Direct SQL search against Signal Desktop's encrypted database. Queries complete in under 1 second against live data.

When to use

  • You need to quote or summarize prior Signal conversations.
  • You already have Signal Desktop installed on macOS.
  • You want fast, instant search without export delays.

How it works

  1. Retrieves the encryption key from macOS Keychain (Signal Safe Storage)
  2. Decrypts the key using PBKDF2 (same as Signal Desktop)
  3. Opens the SQLite database directly with SQLCipher
  4. Runs SQL queries against messages and conversations tables
  5. No files are written; searches happen in memory

First run caches the Python environment path (~5-10s setup), subsequent runs are sub-second.

Usage

# List all available chats
signal-search list

# Dump all messages from a specific day
signal-search dump --date "2026-01-25"

# Dump a specific day's chat with one person
signal-search dump --date "2026-01-25" --chat "Dariush"

# Search within a specific chat
signal-search search --query "istanbul" --chat "Monika"

# Search with context (messages before/after matches)
signal-search search --query "flight" --chat "Monika" --context 3

# Regex search across all chats
signal-search search --query "invoice.*\d{4}"

# Literal string search (not regex)
signal-search search --query "100$" --literal

# Case-sensitive search
signal-search search --query "API" --case-sensitive

# Limit number of results
signal-search search --query "meeting" --max-count 10

Commands

CommandDescription
listList all available chats (name and type)
dumpDump all messages from a specific day
searchSearch messages

Dump Flags

FlagShortDescription
--date <YYYY-MM-DD>-dDate to dump (required)
--chat <name>-cFilter to chats containing this string

Search Flags

FlagShortDescription
--query <pattern>-qSearch pattern (regex by default)
--chat <name>-cFilter to chats containing this string
--context <n>-CShow N messages before and after matches
--max-count <n>-mStop after N matches
--case-sensitive-sCase-sensitive search (default: smart-case)
--literal-FTreat query as literal string, not regex

Output Format

> [2026-01-15 12:01:11] Monika Schmid | Monika Schmid: Habe Fluge gebucht!
  [2026-01-15 12:40:53] Monika Schmid | Me: Schon!
  • Lines starting with > are matches
  • Format: [timestamp] Chat Name | Sender: Message
  • Context lines (if requested) don't have the > prefix

Performance

OperationTime
First run (env setup)~5-10s
Subsequent searches<0.5s
Full chat search (1000s of messages)<1s

Security considerations

  • The database key is retrieved from macOS Keychain using security find-generic-password
  • No data is written to disk; all searches happen in memory
  • The cached Python path is stored in ~/.cache/signal-search/
  • Searches happen locally; nothing leaves your machine

Legacy: Export-based search

The old export-based script (signal-history-search) is still available but deprecated. It uses sigexport to create a temporary export, then searches with ripgrep. This is slower (~15-30s) but may be useful if the direct DB access fails.

# Old method (slower, requires full export)
signal-history-search search --chat "Name" --query "pattern"

Troubleshooting

  • "Failed to get keychain password": Ensure Signal Desktop has been opened at least once and you've granted keychain access
  • "Signal Desktop not found": Check that ~/Library/Application Support/Signal exists
  • First run slow: This is normal; nix-shell is setting up the Python environment with SQLCipher bindings
  • "nix-shell: command not found": Install Nix package manager

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

04

需要参考平台分布和安装热度时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenCode

47.65%
按下载量换算71

Cursor

33.79%
按下载量换算51

Claude Code

14.8%
按下载量换算22

安全审计

暂无安全审计结果可展示。

权限和风险

执行命令

安装流程涉及命令执行,可能通过 npx skills add nicolaischmid/agent-inbox-tools --skill "signal-history-search" 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills