Skip to content
Back to skills

Work On Task

ASecurity

Turn prompt for an assigned swarm task: find the task, gather context when the message lacks it, use the skill the task names, finish with one of the four endings.

  • 844 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added May 26, 2026
ai-agents

Security analysis

A100/100

Scanned September 21, 2026

npx -y skills add desplega-ai/agent-swarm --skill work-on-task --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Work On Task?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Work On Task
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/desplega-ai-work-on-task/badge)](https://www.skillsdirectory.com/skills/desplega-ai-work-on-task)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: work-on-task
description: "Turn prompt for an assigned swarm task: find the task, gather context when the message lacks it, use the skill the task names, finish with one of the four endings."
---

# Working on a task

The taskId follows the command. Without one, call `get-tasks` with `mineOnly: true` and take your `pending` or `in_progress` task. If there is none, say so and stop.

This message carries the task text, its attachments, its output format, and memories from past sessions. If it does not (you invoked this command yourself, or the context was compacted), run the `task-context-gathering` script with the taskId.

When the task names a skill (`researching`, `planning`, `implementing`), use it. Otherwise work directly.

Finish the task with one of the four endings in your operating contract: `completed`, `defer-task`, `request-human-input`, or `failed`. Then stop.

If the user interrupts, follow their instructions. To resume, call `/work-on-task <taskId>` again.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.