ClearTask Requirement Confirmation
Paste the following prompt into your AI chat to install this skill:
Install @user_331cdc55/clear-task into your AI assistant by following https://skillhub.cn/install/skillhub.md.
About this skill
Problem
When a request is vague, an agent may start too early and miss scope, inputs, deliverables, defaults, or external constraints. ClearTask is not meant to “start immediately”; it turns ambiguous intent into a confirmable, traceable task brief before execution.
How It Works
It follows a staged flow:
- Stage 1 – Understand the request: structure the ask into
request_summary,business_goal,scope,inputs,outputs,workflow_graph,assumptions, andopen_questions, keeping assumptions separate from facts. - Stage 2 – Clarify critical gaps: ask only questions that would materially change execution, or record
accepted_defaultsinstead of producing a long questionnaire. - Confirmation gate: present “requirement summary / details / your confirmation” in plain language and proceed only after the user explicitly agrees.
- Stage 3 – Build the internal execution package: generate an
AgentTaskGuidancePackagewith expert guidance, execution advice, and checkable acceptance criteria; the full internal structure is not shown by default.
After execution, it reports what was completed, key defaults used, files or artifacts changed, self-check results, and remaining non-blocking issues.
Boundaries
It fits coding, documentation, planning, analysis, or product tasks that require a clear deliverable. It should pause when the requirement is unconfirmed, blocking questions remain, or the work touches many files, external systems, credentials, paid services, network access, or destructive operations. It is less suitable for quick exploratory analysis or workflows where the user expects output without confirmation.
Use Cases
- Turn a vague backend request into scope, inputs, deliverables, and defaults, then let the user confirm before interface changes
- Confirm readers, length, tone, and required API examples before drafting documentation that meets explicit acceptance criteria
- Clarify characters, levels, asset inputs, and acceptance checks before generating game prototype code and scenes
- Confirm metric definitions, time range, data source, and output format before producing a verifiable report
Best For
- Engineers who need to write down scope and deliverables from informal product requests
- Tech leads who want agents to confirm requirements before changing code
- Data analysts who need fixed metric definitions and output formats before reporting
- Developers who need to confirm readers, length, and API examples before documentation
Related Skills
Provides Claw with character-library selection, switching, saving, and global SOUL.md style sync for role-based conversation.
An AIONE Agentic AI Infrastructure SDK wrapper for building production AI agents with memory, skills, workflows, and hooks.
A Python/TypeScript SDK wrapper for the DeepSeek-Reasonix native AI coding agent, with prefix-cache support.
A browser automation tool for analysts, operators, and developers that locates elements, fills forms, extracts structured content, and supports no-code scheduling and export.