Run any Skill in Manus with one click

deepagents-harness

Stars3

Forks0

UpdatedFebruary 9, 2026 at 23:12

Use this skill when the user asks about deepagents harness capabilities, tool names, task delegation, filesystem access, or sandbox execution. It provides a concise operational cheat sheet.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

dkarasiewicz

dkarasiewicz/launchline

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

SKILL.md

readonly

name	deepagents-harness
description	Use this skill when the user asks about deepagents harness capabilities, tool names, task delegation, filesystem access, or sandbox execution. It provides a concise operational cheat sheet.

DeepAgents Harness Skill

Core Capabilities

Task delegation: Use task to spawn subagents for isolated work.
Planning: Use write_todos for multi-step tasks and update statuses.
Filesystem tools: ls, read_file, write_file, edit_file, glob, grep.
Human-in-the-loop: interrupt_on gates sensitive tools.
Summarization: History auto-compresses at high token usage.

Operational Guidance

Delegate early when work can be parallelized (research + analysis + drafting).
Keep tasks small, with explicit output format.
Use file tools for structured artifacts and breadcrumbs.
Prefer short, actionable plans with 3-6 steps.

Common Patterns

Research: plan → task subagents → synthesize with citations.
Automation: plan → run sandbox workflow → verify → summarize.
Comms: draft → confirm → send.

More from this repository

same repository

blocker-detection

dkarasiewicz/launchline

Use this skill when investigating blockers, stalled work, or anything preventing progress.

2026-02-093

delegation-orchestration

dkarasiewicz/launchline

Use this skill for multi-track tasks that benefit from delegation, parallel research, or structured planning. It guides the main agent to use the task tool, subagents, and write_todos for coordination.

2026-02-093

linear-integration

dkarasiewicz/launchline

Use this skill for requests related to Linear issues, projects, sprints, and team workload. This skill provides guidance on how to effectively query and interact with Linear data.

2026-02-093

project-status

dkarasiewicz/launchline

Use this skill when generating project updates, status reports, or stakeholder communications.

2026-02-093

sandbox-automation

dkarasiewicz/launchline

Use this skill for tasks that require running commands or scripts in the sandbox. It provides a plan-first workflow for using run_sandbox_workflow, dependency setup, verification, and iterative loops.

2026-02-093

skill-creator

dkarasiewicz/launchline

Guide for creating or updating skills. Covers naming, required frontmatter, store-backed paths, and publishing.

2026-02-093

name	deepagents-harness
description	Use this skill when the user asks about deepagents harness capabilities, tool names, task delegation, filesystem access, or sandbox execution. It provides a concise operational cheat sheet.

DeepAgents Harness Skill

Core Capabilities

Task delegation: Use task to spawn subagents for isolated work.
Planning: Use write_todos for multi-step tasks and update statuses.
Filesystem tools: ls, read_file, write_file, edit_file, glob, grep.
Human-in-the-loop: interrupt_on gates sensitive tools.
Summarization: History auto-compresses at high token usage.

Operational Guidance

Delegate early when work can be parallelized (research + analysis + drafting).
Keep tasks small, with explicit output format.
Use file tools for structured artifacts and breadcrumbs.
Prefer short, actionable plans with 3-6 steps.

Common Patterns

Research: plan → task subagents → synthesize with citations.
Automation: plan → run sandbox workflow → verify → summarize.
Comms: draft → confirm → send.