$ loading_
Break large, long-running tasks into manageable chunks and preserve context.
This appears to be a prompt-oriented skill for breaking large tasks into smaller chunks, with no required secrets and no declared remote endpoints, so overall risk is low. The README contains strongly prescriptive workflow instructions, but the provided material does not show extra privileges, data exfiltration, or closed-source red flags.
The material explicitly states there are no required keys or environment variables. No API keys, tokens, or other sensitive credentials are requested, so credential exposure and abuse risk appears low.
No remote endpoints are declared, and the checks do not indicate network connectivity. Based on the documentation, this is a prompt-only skill with no stated behavior of sending user data to external services.
The README explicitly instructs use of tools like TodoWrite and Task and to 'start subagents,' which is a strong workflow directive that may indirectly trigger task orchestration or execution paths in the host agent. The material does not show bundled executable code or extra system privileges, so this is caution rather than high risk.
No file I/O, database access, or other resource scopes are declared. As a prompt-only skill, the material provides no factual basis that it grants or requests local data access permissions.
A positive factor is that it is labeled open source and hosted on GitHub, which improves auditability. However, the stated repository does not clearly match the skill name/use case, community adoption is 0 stars, the license is undeclared, and maintenance status is unknown, so supply-chain trust should still be manually verified.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "handle-large-tasks" skill from askskill: 1. Download https://raw.githubusercontent.com/microsoft/FluidFramework/main/.agency/plugins/nori/skills/handle-large-tasks/SKILL.md 2. Save it as ~/.claude/skills/handle-large-tasks/SKILL.md 3. Reload skills and tell me it's ready
Break down “refactor our user authentication system” into executable phases. For each phase, list goals, inputs, outputs, risks, dependencies, and completion criteria, and explain how to control context length at each step.
A phased execution plan with clear subtasks, dependencies, and context-management guidance.
I need to complete a “market research report on AI customer service tools.” Split the work into research modules, each with research questions, sources, output format, estimated time, and checkpoints before moving on.
A modular research roadmap that enables steady progress and prevents overload from oversized tasks.
Split “write a 5,000-word industry white paper” into writing stages, including outline, research, chapter drafts, review, and final version. For each stage, provide a reusable context summary template for continuing the conversation.
A staged writing workflow with reusable context summary templates for each phase.
Use subagents to manage your context. Each subagent has its own limited context window. Subagents perform best when they have clear implementation guidelines. Each subagent should be given a small and precise task. Create tests for each subagent and explicitly tell the subagent that it is responsible for making sure that test passes. The tests should test behavior. You are responsible for the final output. That means you MUST ensure that everything runs as expected. You should create high level tests that validate overall behavior.
Explains how to use abilities effectively before starting any conversation.
Turn rough ideas into actionable designs through structured questioning and validation.
Draft and review Fluid Framework PR titles and descriptions consistently.
Review code or branches for correctness, compatibility, architecture, tests, performance, and security.
Build, debug, and validate features in web app frontends.
Generate Fluid-style PR content, push branches, and open GitHub pull requests.
Create, refine, and evaluate AI skills for better performance and triggering accuracy.
Create, refine, validate, and restructure AgentSkills and SKILL.md files.
Turn a repeated workflow into a reusable skill file from the current session.
Create or update skills that extend Codex with knowledge, workflows, and tools.
Convert skills from other AI coding assistants into Amplifier-native SKILL.md files.
Write precise prompts for any AI tool with full context retention.