Token导航 LogoToken导航

Agent Skill · 研究检索

pocket-ai(口袋艾)

pocket-ai 用于查找、检索和筛选相关信息,适合在 OpenClaw 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。

pocket-ai 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为接触敏感数据;许可证为 MIT-0,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 5,494。

总安装 25,759周安装 1,032GitHub Stars 公开资料未说明下载 8,339核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.1

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:pocket-ai(口袋艾)
来源仓库:https://github.com/asabovetech/pocket-ai
安装命令:
openclaw skills install pocket-ai
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 OpenClaw 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。

ClawHubOpenClaw
openclaw skills install pocket-ai

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

对所有录音进行转录、索引和语义搜索,提取操作项目和会议见解,以实现全面的对话智能。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install pocket-ai;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

pocket-ai 怎么安装?

在终端执行 openclaw skills install pocket-ai。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

pocket-ai 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

pocket-ai 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

pocket-ai 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

pocket-ai 用的人多吗?

公开数据是累计安装 25,759 次,近一周安装 1,032 次,下载 8,339 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

pocket-ai 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
pocket-ai

口袋艾 · 本页

25,759—接触敏感数据MIT-0有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Pocket AI Skill

Voice recording transcription, semantic search, and meeting intelligence across all conversations.

Pocket AI captures your meetings, calls, and thoughts via a wearable device, then transcribes and indexes everything for semantic search.

Quick Reference

WhatValue
API Basehttps://public.heypocketai.com/api/v1
API Key~/.config/pocket-ai/api_key
AuthBearer token
Docshttps://docs.heypocketai.com/docs/api

Core Capabilities

1. Semantic Search (Most Powerful)

Search across ALL recordings by meaning, not just keywords.

curl -s -X POST \
  -H "Authorization: Bearer $(cat ~/.config/pocket-ai/api_key)" \
  -H "Content-Type: application/json" \
  -d '{"query": "your company manufacturing decisions"}' \
  "https://public.heypocketai.com/api/v1/public/search"

Returns:

  • userProfile.dynamicContext[] — AI-built insights from all recordings
  • relevantMemories[] — Matching transcripts, action items, meeting sections
  • Speaker identification, timestamps, relevance scores

2. Action Item Extraction

Pocket AI auto-extracts action items from meetings. Search for them:

curl -s -X POST \
  -H "Authorization: Bearer $(cat ~/.config/pocket-ai/api_key)" \
  -H "Content-Type: application/json" \
  -d '{"query": "action items tasks follow up"}' \
  "https://public.heypocketai.com/api/v1/public/search"

3. List Tags

curl -s -H "Authorization: Bearer $(cat ~/.config/pocket-ai/api_key)" \
  "https://public.heypocketai.com/api/v1/public/tags"

4. List Recordings

curl -s -H "Authorization: Bearer $(cat ~/.config/pocket-ai/api_key)" \
  "https://public.heypocketai.com/api/v1/public/recordings"

5. Get Recording Details

curl -s -H "Authorization: Bearer $(cat ~/.config/pocket-ai/api_key)" \
  "https://public.heypocketai.com/api/v1/public/recordings/{recording_id}"

6. Download Audio

curl -s -H "Authorization: Bearer $(cat ~/.config/pocket-ai/api_key)" \
  "https://public.heypocketai.com/api/v1/public/recordings/{recording_id}/audio"

High-Value Query Patterns

Contact Context

*"What has been discussed with [person]?"*

{"query": "conversations with Dylan Acquisition.com"}
{"query": "Adrienne intercompany invoices discussion"}
{"query": "meetings with Charlene"}

Business Decisions

*"What decisions were made about [topic]?"*

{"query": "your company manufacturing team restructuring decisions"}
{"query": "entity streamlining strategy"}
{"query": "trading system rules discussed"}

Action Items & Follow-ups

*"What needs to be done?"*

{"query": "action items tasks todo follow up"}
{"query": "scheduled meetings upcoming"}
{"query": "things to review or approve"}

Personal Insights

*"What have I said about [topic]?"*

{"query": "trading psychology patience discipline"}
{"query": "family financial planning kids college"}
{"query": "team performance frustrations"}

Meeting Summaries

*"What happened in [meeting type]?"*

{"query": "your company staff meeting summary"}
{"query": "financial review discussion"}
{"query": "geopolitical analysis conversation"}

Response Structure

Search Response

{
  "success": true,
  "data": {
    "userProfile": {
      "dynamicContext": [
        "AI-built insight from recordings...",
        "Another pattern detected..."
      ],
      "staticFacts": []
    },
    "relevantMemories": [
      {
        "content": "Transcript segment or action item...",
        "metadata": {"source": "turbopuffer", "sources": ["transcript_segment", "action_item"]},
        "recordingDate": "2026-01-28 01:16:14",
        "recordingId": "uuid",
        "recordingTitle": "Untitled Recording",
        "relevanceScore": 8.19,
        "speakers": "SPEAKER_00, SPEAKER_01",
        "transcriptionId": "uuid"
      }
    ],
    "total": 8,
    "timing": 490
  }
}

Memory Content Types

  • Transcript segment: [timestamp] SPEAKER_XX: actual words spoken
  • Action item: Action item: Do the thing
  • Meeting section: (start-end) Section Title - Summary of what was discussed

Integration Points

Athena (Family Agent)

  • Query meeting context to understand your bandwidth
  • "Am I free?" → Check if recent recordings show heavy commitments
  • Feed meeting insights into scheduling decisions

Daily Briefings

  • Pull action items from yesterday's meetings
  • Summarize key decisions made
  • Flag urgent follow-ups

Task Management

  • Auto-surface action items as potential tasks
  • Cross-reference with existing todo lists
  • Track what's been mentioned but not yet acted on

Operations Channel

  • Post important decisions to #operations
  • Alert on critical discussions (team changes, financial decisions)

Tags (Your Categories)

Current tags: ai, business, call, economy, finance, game, geopolitics, hockey, outlook, personal, sales, summary, test, victory, weather, work

Use tags to filter or categorize queries.


Heartbeat Integration

During heartbeats, optionally check for new action items:

# Check for recent action items (last 24h)
query = "action items from today"
# Parse response for new follow-ups
# Surface anything urgent

Privacy & Security

  • All recordings encrypted end-to-end
  • Stored on US servers
  • API key should remain in ~/.config/pocket-ai/api_key
  • Never log full transcripts to public channels

Troubleshooting

Empty recordings list?

  • Recordings may need device sync before API access
  • Use search endpoint instead (works with synced transcripts)

Auth errors?

  • Check Bearer token format: Authorization: Bearer pk_xxx
  • Verify key in ~/.config/pocket-ai/api_key

Search returns nothing?

  • Try broader query terms
  • Check if recordings have been synced recently

Helper Scripts

search.sh

#!/bin/bash
# Usage: ./search.sh "your query"
API_KEY=$(cat ~/.config/pocket-ai/api_key)
curl -s -X POST \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d "{\"query\": \"$1\"}" \
  "https://public.heypocketai.com/api/v1/public/search"

Python Helper

See pocket_api.py for full Python integration.

平台分布

OpenClaw

97.49%
按下载量换算8,130

安全审计

VirusTotal

可疑

ClawScan

可疑

Static analysis

未展示

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills