design-task — Skills — getagentictools

What it does

Format — bullet points, paragraphs, JSON, table

Structure — sections, headings, order

Length — approximate word count or number of items

Quality markers — citations required, confidence levels, specific fields

researchtask

The task needs tools the agent doesn't normally have

You want to restrict an agent to specific tools for this task

Requirements & configuration

Every task needs two things: a description (what to do and how) and an expectedoutput (what the result looks like).

In sequential process: Each task auto-receives all prior task outputs. Use context only when you need non-linear dependencies.

Use outputpydantic or outputjson when downstream code needs to parse the result:

When enabled, the agent presents its result and waits for human feedback before marking the task complete. Use for critical outputs that need human approval.

You don't need context= in sequential — it's implicit. Use it only to create non-linear dependencies:

design task

Source

Repository: https://github.com/crewaiinc/skills

design-task FAQ

What does the design-task skill do?

CrewAI task design and configuration. Use when creating, configuring, or debugging crewAI tasks — writing descriptions and expected_output, setting up task dependencies with context, configuring output formats (output_pydantic, output_json, output_file), using guardrails for validation, enabling human_input, async execution, markdown formatting, or debugging task execution issues. Format — bullet points, paragraphs, JSON, table Structure — sections, headings, order

What does design-task require?

Every task needs two things: a description (what to do and how) and an expectedoutput (what the result looks like). In sequential process: Each task auto-receives all prior task outputs. Use context only when you need non-linear dependencies. Use outputpydantic or outputjson when downstream code needs to parse the result: When enabled, the agent presents its result and waits for human feedback before marking the task complete. Use for critical outputs that need human approval. You don't need context= in sequential — it's implicit. Use it only to create non-linear dependencies:

How do I install design-task?

Run: npx -y skills add https://github.com/crewaiinc/skills --skill design-task --agent claude-code — the source lives at github.com/crewaiinc/skills.

Maintain design-task?

Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.

[design-task on getagentictools](https://getagentictools.com/skills/crewaiinc-skills-design-task?ref=badge)

npx agentictools info skills/crewaiinc-skills-design-task

The second line is the CLI lookup for this page — handy in READMEs and docs.