Token导航 LogoToken导航

Agent Skill · 研究检索

pndr(pndr 搜索)

pndr 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。

pndr 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,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 1,313。

总安装 100,808周安装 4,078GitHub Stars 1下载 31,645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
1.0.20260202

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:pndr(pndr 搜索)
来源仓库:https://github.com/dgershman/pndr
安装命令:
openclaw skills install pndr
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 pndr

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。

pndr 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。适用于个人生产力管理、任务跟踪和习惯养成的信息整合场景。通过 openclaw skills install pndr 安装,具体用法请参考 GitHub 仓库文档。

安装前需确认权限范围和维护状态,注意可能触发联网、命令执行或文件读写操作。pndr 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

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 pndr;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

pndr 怎么安装?

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

pndr 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。

pndr 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。

pndr 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。

pndr 用的人多吗?

公开数据是累计安装 100,808 次,近一周安装 4,078 次,下载 31,645 次,GitHub 1 星。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。

pndr 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

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。
  • 第三方扫描已通过,常见的高风险行为没有命中。

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。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

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
pndr

pndr 搜索 · 本页

100,8081接触敏感数据MIT-0通过

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

name
pndr
description
Personal productivity app with Ideas/Tasks, Journal, Habits, Package tracking, Lists, and more via MCP
homepage
https://pndr.io
metadata
{"openclaw":{"emoji":"📝","requires":{"bins":["mcporter"]}}}

Pndr

Pndr is your personal productivity command center, now accessible to AI agents via MCP (Model Context Protocol).

What You Can Do

With Pndr's MCP integration, AI assistants like Claude can:

  • Manage your tasks - Add, edit, complete, and organize ideas with tags and priorities
  • Track your habits - Create daily habits and mark them complete automatically
  • Journal - Record thoughts and retrieve them with fuzzy search
  • Track packages - Monitor deliveries with tracking numbers and carriers
  • Manage lists - Create checklists, shopping lists, or any collection of items
  • Get insights - View today's focus items, kanban boards, accomplishments, and patterns

All of this happens in your own private Pndr account - the AI just provides a natural language interface to your data.

How It Works

Pndr exposes your personal productivity data through the Model Context Protocol (MCP), allowing AI assistants to interact with your tasks, habits, and journal on your behalf.

Example conversations:

  • "Add a task to call mom tomorrow with high priority"
  • "What's on my plate today?"
  • "Mark my exercise habit as complete"
  • "Show me my accomplishments this week"
  • "Add a journal entry about today's meeting"

The AI uses Pndr's MCP tools behind the scenes to read and write your data securely.

Who Is This For?

This integration is perfect if you:

  • Use an AI assistant (Claude, OpenClaw, etc.) and want it to manage your tasks
  • Want natural language access to your productivity data
  • Like the idea of saying "add this to my todo list" instead of opening an app
  • Already use Pndr and want to access it through AI conversations

Prerequisites

  • A Pndr account (sign up at https://pndr.io)
  • An AI assistant that supports MCP (like Claude Desktop or OpenClaw)
  • For manual setup: mcporter CLI tool

Setup

For OpenClaw Users

OpenClaw can set this up automatically! Just ask your assistant:

"Connect to my Pndr account"

Then provide your Pndr OAuth credentials when prompted.

Manual Setup

  1. Get Pndr API credentials:

- Log in to https://pndr.io - Go to Settings → API → Create OAuth Client - Give it a name (e.g., "My AI Assistant") - Copy your client_id and client_secret

  1. Get an access token:
   curl -X POST https://pndr.io/oauth/token \
     -H "Content-Type: application/json" \
     -d '{
       "grant_type": "client_credentials",
       "client_id": "pndr_client_YOUR_CLIENT_ID",
       "client_secret": "YOUR_CLIENT_SECRET"
     }'

This returns a JSON response with an access_token. Copy it.

  1. Add to your MCP client config:

For mcporter (config/mcporter.json):

   {
     "mcpServers": {
       "pndr": {
         "baseUrl": "https://pndr.io/mcp",
         "headers": {
           "Authorization": "Bearer YOUR_ACCESS_TOKEN"
         }
       }
     }
   }

For Claude Desktop (claude_desktop_config.json):

   {
     "mcpServers": {
       "pndr": {
         "url": "https://pndr.io/mcp",
         "headers": {
           "Authorization": "Bearer YOUR_ACCESS_TOKEN"
         }
       }
     }
   }
  1. Test the connection:
   mcporter list pndr --schema

You should see 47 available tools!

Available Tools

Ideas & Tasks

  • add_idea - Create a new idea/task
  • list_ideas - List and filter ideas
  • edit_idea - Edit an existing idea
  • complete_idea - Mark an idea as completed
  • delete_idea - Delete an idea
  • categorize_idea - Update tags on an idea
  • set_work_status - Set work status (not started, in progress, blocked)
  • get_kanban - Get kanban board view
  • get_today - Get today's focus items

Journal & Thoughts

  • add_thought - Record a journal/diary entry
  • get_thoughts - Retrieve thoughts with fuzzy search
  • delete_thought - Delete a thought

Habits

  • add_habit - Create a new daily habit
  • list_habits - List all habits with completion status
  • complete_habit - Mark a habit as completed for today
  • uncomplete_habit - Undo a habit completion
  • update_habit - Update habit text or resources
  • archive_habit - Archive (delete) a habit

Checklists

  • add_checklist_item - Add a checklist item to an idea
  • complete_checklist_item - Mark checklist item as completed
  • uncomplete_checklist_item - Mark checklist item as not completed
  • get_checklist - Get all checklist items for an idea
  • edit_checklist_item - Edit checklist item text
  • delete_checklist_item - Delete a checklist item

Lists

  • add_list - Create a new list
  • list_lists - Get all lists with optional filtering
  • get_list - Get a single list with items
  • update_list - Update list name, description, or tags
  • delete_list - Delete a list and all its items
  • add_list_item - Add an item to a list
  • update_list_item - Update list item text, notes, or completion
  • toggle_list_item - Toggle list item completion
  • delete_list_item - Remove an item from a list
  • reorder_list_items - Change item order in a list

Packages

  • add_package - Track a new package delivery
  • list_packages - List tracked packages
  • update_package - Update package information
  • mark_package_delivered - Mark a package as delivered
  • delete_package - Delete a package from tracking

Tags

  • list_tags - List all available tags
  • create_tag - Create a new tag
  • delete_tag - Delete a tag

Comments

  • add_comment - Add a comment to an idea
  • list_comments - List comments on an idea
  • delete_comment - Delete a comment

Attachments

  • list_attachments - List attachments for an idea
  • get_attachment - Get attachment metadata
  • download_attachment - Download attachment with base64 data

Analytics

  • get_accomplishments - Get summary of completed tasks and habits
  • get_patterns - Analyze patterns in ideas and thoughts over time

Usage Examples

Once connected, you can interact with Pndr naturally through your AI assistant:

Task Management:

  • "Add a high-priority task to finish the presentation by Friday"
  • "Show me all my work tasks that are in progress"
  • "Mark task [ID] as complete"
  • "What should I focus on today?"

Habits:

  • "Did I complete my exercise habit today?"
  • "Mark my reading habit as done"
  • "What's my current streak for meditation?"

Journaling:

  • "Add a journal entry: Had a breakthrough on the project today"
  • "What was I thinking about last week around this topic?"
  • "Show me my thoughts from January"

Package Tracking:

  • "Track a package from Amazon, tracking number 1Z999..."
  • "What packages am I expecting?"
  • "Mark my laptop package as delivered"

Lists:

  • "Create a grocery list"
  • "Add milk and eggs to my shopping list"
  • "Show me my reading list"

Direct CLI Usage (Advanced)

If you're using mcporter directly:

# Add a task
mcporter call pndr.add_idea text="Build a new feature" tags:work,coding priority:P1

# Check today's focus
mcporter call pndr.get_today

# Complete a habit
mcporter call pndr.complete_habit habit-id:abc123

# Add journal entry
mcporter call pndr.add_thought content="Had a great day working on the project"

# View kanban board
mcporter call pndr.get_kanban tags:work

Authentication

Pndr uses OAuth 2.0 client credentials flow. Access tokens expire after 1 year (365 days).

To refresh your token, repeat the curl command from step 2 and update your mcporter config with the new Bearer token.

Source Code

Open source at https://github.com/Dgershman/pndr

Pricing

  • Free tier: Read-only access
  • Pro ($5/mo or $48/year): Full read/write access

Support

  • Documentation: https://pndr.io/docs
  • Issues: https://github.com/Dgershman/pndr/issues

平台分布

OpenClaw

86.19%
按下载量换算27,275

安全审计

VirusTotal

通过

ClawScan

通过

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。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