pickup — install pickup skill for AI agents pickup, On-Device-LMM-Reasoning-Acceleration, community, install pickup skill for AI agents, ide skills, tmux task management with pickup, PROGRESS.md format for pickup, pickup skill for efficient conversation handoffs, Claude Code, Cursor, Windsurf

v1.0.0
GitHub

About this Skill

Essential for Development and Task-Oriented Agents requiring persistent state management across conversation breaks. pickup is a skill that allows AI agents to resume conversations by reading PROGRESS.md and utilizing tmux for task management

Features

Reads PROGRESS.md to understand current conversation state
Utilizes tmux to check and manage background tasks
Supports BLUF format for concise status reporting
Executes tasks based on '立即执行事项' in PROGRESS.md
Compatible with /handoff prompts for precise conversation handoffs
Automatically captures and reports on task progress using tmux capture-pane

# Core Topics

install pickup skill for AI agents tmux task management with pickup PROGRESS.md format for pickup pickup skill for efficient conversation handoffs
holEeast979 holEeast979
[1]
[0]
Updated: 3/2/2026

Agent Capability Analysis

The pickup skill by holEeast979 is an open-source community AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance. Optimized for install pickup skill for AI agents, tmux task management with pickup, PROGRESS.md format for pickup.

Ideal Agent Persona

Essential for Development and Task-Oriented Agents requiring persistent state management across conversation breaks.

Core Value

Enables seamless continuation of complex workflows by reading the PROGRESS.md file to understand the current state and immediate next actions. It checks for active tmux sessions to monitor background tasks and report progress using BLUF (Bottom Line Up Front) formatting for clarity.

↓ Capabilities Granted for pickup

Resuming interrupted development workflows
Monitoring long-running tmux-based experiments
Parsing PROGRESS.md for immediate action items

! Prerequisites & Limits

  • Requires PROGRESS.md file in /root/scripts/ directory
  • Depends on tmux for session monitoring
  • Relies on specific handoff prompt structure for optimal performance
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

pickup

Install pickup, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command setup.

SKILL.md
Readonly

新对话接续（/pickup）

当用户在新对话开始时说"接续"、"继续上次"、"读进度"时执行此流程。

最佳方式：用户直接粘贴上次 /handoff 生成的交接 Prompt（更精准）。 兜底方式：没有 Prompt 时用 /pickup，Agent 自己读 PROGRESS.md 理解状态。

步骤

  1. 读取 PROGRESS.md

    读取 /root/scripts/PROGRESS.md 全文（重点关注"当前状态"和"⬇️ 新对话 Agent 立即执行事项"）

  2. 检查后台任务

    bash
    1# 检查是否有 tmux 实验在跑
2tmux list-sessions 2>/dev/null || echo "no sessions"
3# 如果有，查看进度
4tmux capture-pane -t eval -p | tail -20

  3. 汇报当前状态（BLUF 格式）

    • 一句话总结当前状态
    • 列出"立即执行事项"
    • 如果有后台实验，报告进度

  4. 确认优先级

    • 如果用户粘贴了交接 Prompt：按 Prompt 中的"立即执行"直接开始
    • 如果用户只说了 /pickup：问用户"按 PROGRESS.md 的计划继续，还是有新的优先级？"

  5. 开始工作

    • 按"⬇️ 新对话 Agent 立即执行事项"的第一条开始执行
    • 如果实验已完成，优先分析结果
    • 如果实验未完成，做其他待办事项

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is pickup?

Essential for Development and Task-Oriented Agents requiring persistent state management across conversation breaks. pickup is a skill that allows AI agents to resume conversations by reading PROGRESS.md and utilizing tmux for task management

How do I install pickup?

Run the command: npx killer-skills add holEeast979/On-Device-LMM-Reasoning-Acceleration/pickup. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for pickup?

Key use cases include: Resuming interrupted development workflows, Monitoring long-running tmux-based experiments, Parsing PROGRESS.md for immediate action items.

Which IDEs are compatible with pickup?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for pickup?

Requires PROGRESS.md file in /root/scripts/ directory. Depends on tmux for session monitoring. Relies on specific handoff prompt structure for optimal performance.

↓ How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add holEeast979/On-Device-LMM-Reasoning-Acceleration/pickup. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use pickup immediately in the current project.

Related Skills

Looking for an alternative to pickup or another community skill for your workflow? Explore these related open-source skills.

View All

widget-generator

Logo of f
f

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

★ 149.6k
⑂ 0
AI

flags

Logo of vercel
vercel

flags is a Next.js feature management skill that enables developers to efficiently add or modify framework feature flags, streamlining React application development.

★ 138.4k
⑂ 0
Browser

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

★ 72.8k
⑂ 0
AI

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

★ 72.8k
⑂ 0
AI