How do I install the Long Task skill?

Run npx skillmds add majiayu000/long-task in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Long Task safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: reads secrets. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Long Task?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Long Task free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Long Task?

majiayu000 (@majiayu000) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Long Task by majiayu000 — Agent Skill

Name: Long Task
Rating: 4.666666666666667 (3 reviews)
Author: majiayu000

Long Task

Initialize or resume a long-running task session. Use when starting a complex multi-session task, resuming work from a previous session, or when the user mentions claude-progress.json or long-running work.

majiayu000 77205e0 2 files · 3.7 KB Updated Sep 9, 2026 567 repo stars

File contents

Long Task Management

Mind-powered persistence for tasks that span multiple sessions.

Quick Commands

/long-task - Show active task or start new one
/long-task status - Show current task status
/long-task complete - Mark task as completed

Starting a Task

When starting a long-running task:

Use long_task_start with:
- task_id: unique identifier (e.g., "implement-feature-x")
- goal: clear description of what you're trying to achieve
- hard_checks: deterministic completion criteria (optional)
- soft_checks: semantic completion criteria (optional)

How It Works

SessionStart: If active task exists, context auto-injects
During work: Log significant events with long_task_event
Stop hook: Automatically logs checkpoint and increments iteration
Completion: Mark with [TASK_COMPLETE] or call long_task_complete

MCP Tools

Tool	Purpose
`long_task_start`	Start a new long-running task
`long_task_get`	Get task details by ID
`long_task_active`	Get active task for realm
`long_task_update`	Update progress (completed_summary, work_items, blockers)
`long_task_complete`	Mark task as completed
`long_task_event`	Log event (decision, error, checkpoint)
`long_task_snapshot`	Get synthesized context
`long_task_evaluate`	Check completion criteria

Process

If no arguments (show status or start)

Check for active task with long_task_active
If found: show snapshot with long_task_snapshot
If not found: ask user for task goal and start new task

If "status" argument

Get active task with long_task_active
Show detailed snapshot with mode="debug"

If "complete" argument

Get active task
Ask for outcome summary
Call long_task_complete

Example Usage

Start a task:

/long-task
> No active task. What's your goal?
> Implement the authentication system

Starting task: implement-auth
Goal: Implement the authentication system

Check status:

/long-task status
[LONG_TASK:implement-auth] Implement the authentication system
Iteration: 3 | Status: active
Done: Added login form, API endpoints
Pending: Add password reset; Add OAuth

Complete task:

/long-task complete
Outcome: Authentication system fully implemented with login, logout, and OAuth

Completed task: implement-auth

Completion Markers

The Stop hook detects these markers to auto-complete:

[TASK_COMPLETE]
[DONE]
<promise>COMPLETE</promise>

Multi-Agent Support

Tasks support lease-based coordination:

task_claim: Claim task with lease
task_heartbeat: Extend lease
Expired leases allow other agents to take over

---name: long-taskdescription: Initialize or resume a long-running task session. Use when starting a complex multi-session task, resuming work from a previous session, or when the user mentions claude-progress.json or long-running work.--- # Long Task Management Mind-powered persistence for tasks that span multiple sessions. ## Quick Commands - `/long-task` - Show active task or start new one - `/long-task status` - Show current task status - `/long-task complete` - Mark task as completed ## Starting a Task When starting a long-running task: ``` Use long_task_start with: - task_id: unique identifier (e.g., "implement-feature-x") - goal: clear description of what you're trying to achieve - hard_checks: deterministic completion criteria (optional) - soft_checks: semantic completion criteria (optional) ``` ## How It Works 1. **SessionStart**: If active task exists, context auto-injects 2. **During work**: Log significant events with `long_task_event` 3. **Stop hook**: Automatically logs checkpoint and increments iteration 4. **Completion**: Mark with `[TASK_COMPLETE]` or call `long_task_complete` ## MCP Tools | Tool | Purpose | |------|---------| | `long_task_start` | Start a new long-running task | | `long_task_get` | Get task details by ID | | `long_task_active` | Get active task for realm | | `long_task_update` | Update progress (completed_summary, work_items, blockers) | | `long_task_complete` | Mark task as completed | | `long_task_event` | Log event (decision, error, checkpoint) | | `long_task_snapshot` | Get synthesized context | | `long_task_evaluate` | Check completion criteria | ## Process ### If no arguments (show status or start) 1. Check for active task with `long_task_active` 2. If found: show snapshot with `long_task_snapshot` 3. If not found: ask user for task goal and start new task ### If "status" argument 1. Get active task with `long_task_active` 2. Show detailed snapshot with mode="debug" ### If "complete" argument 1. Get active task 2. Ask for outcome summary 3. Call `long_task_complete` ## Example Usage **Start a task:** ``` /long-task > No active task. What's your goal? > Implement the authentication system Starting task: implement-auth Goal: Implement the authentication system ``` **Check status:** ``` /long-task status [LONG_TASK:implement-auth] Implement the authentication system Iteration: 3 | Status: active Done: Added login form, API endpoints Pending: Add password reset; Add OAuth ``` **Complete task:** ``` /long-task complete Outcome: Authentication system fully implemented with login, logout, and OAuth Completed task: implement-auth ``` ## Completion Markers The Stop hook detects these markers to auto-complete: - `[TASK_COMPLETE]` - `[DONE]` - `<promise>COMPLETE</promise>` ## Multi-Agent Support Tasks support lease-based coordination: - `task_claim`: Claim task with lease - `task_heartbeat`: Extend lease - Expired leases allow other agents to take over

Frequently asked questions