Handle Large Tasks

by microsoft

Handle Large Tasks is an AI Engineering skill for Claude Code, published by microsoft in FluidFramework.

4.9K stars583 forkson microsoft/FluidFrameworkAdded 2026/07/19Repository updated 2026/08/06

View source on GitHub Download repo ZIP

collaborationcrdtdatastructuredistributedfluidfluid-frameworkmicrosoftrealtime

Install in seconds

Install Handle Large Tasks

Copy Handle Large Tasks into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/microsoft/FluidFramework/tree/main/.agency/plugins/nori/skills/handle-large-tasks ~/.claude/skills/handle-large-tasks

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/microsoft/FluidFramework.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: .agency/plugins/nori/skills/handle-large-tasks/SKILL.md in microsoft/FluidFramework
Installs to: ~/.claude/skills/handle-large-tasks
Collection: One of 31 skills cataloged from this repository
Category: AI Engineering — 3670 skills

What Handle Large Tasks does

Splits large tasks into smaller chunks managed by subagents to prevent context window overflow. Use when long-running tasks cause context issues, ensuring coherent final output through iterative testing.

Handle Large Tasks is cataloged under AI Engineering on DirSkills. Handle Large Tasks comes from a repository tagged collaboration, crdt, datastructure, distributed and fluid.

Documentation

README

Excerpt

Announce that you are creating subagents.
Construct a plan for each subagent.
Write a test for each subagent based on what you expect the subagent to do.
Start each subagent using the Task tool with instructions to make the test pass.
- Subagents may come back and ask questions or present plans. Review and provide feedback.
- You may have to restart subagents. If that happens, simply pass in the previous produced plan.
Evaluate the code the subagent produces. Give feedback. Iterate until tests pass AND the code fits.
When all subagents complete, make sure all tests pass and all of the code fits together coherently.

Guidelines

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Handle Large Tasks

What else does microsoft publish alongside Handle Large Tasks?
Handle Large Tasks is one of 31 skills that DirSkills catalogs from microsoft/FluidFramework, the repository it ships in. Its siblings there include API Changes Review, Brainstorming and Building UI/UX. Each one is a separate skill with its own page in this directory, installs the same way Handle Large Tasks does, and is maintained by microsoft in that same repository. The rest of the collection is listed on the microsoft/FluidFramework page.
How does Handle Large Tasks compare to other AI Engineering skills?
Handle Large Tasks ranks #508 by stars among the 3670 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Handle Large Tasks against them. Open each page to compare what they document and how they install.