← Back to Skills Marketplace
trackoverflow

Requirement Agent

by TrackOverflow . · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
175
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install requirement-agent
Description
需求澄清与执行确认。用于日常代码任务(修改、重构、优化、添加注释等)。当用户提出需求时,先通过快速追问(3-5 轮)完善需求,执行前根据规则判断是否需要确认。与 brainstorming(复杂系统设计)互补。
Usage Guidance
This skill appears coherent and low-risk, but it assumes the agent has permission to read and modify your codebase. Before installing: (1) ensure you want an agent that can edit repository files and that proper backups/version control are in place, (2) review and, if needed, tighten config/rules.yaml (for example require confirmation for multi-file changes, deletions, or logic changes), (3) be cautious about the 'explicit_safe' or broad 'safe_operations' that enable auto-execution, and (4) restrict the agent's file access scope in your platform so it only operates on intended projects. If you need higher assurance, request logs or a dry-run mode before allowing actual edits.
Capability Analysis
Type: OpenClaw Skill Name: requirement-agent Version: 1.0.0 The 'requirement-agent' skill is a helper tool designed to improve AI agent interactions by enforcing a requirement clarification process and execution confirmation safety checks. The logic is entirely focused on structured questioning and rule-based confirmation (e.g., requiring user approval for deletions or multi-file changes) as defined in 'SKILL.md' and 'config/rules.yaml'. There are no indicators of data exfiltration, malicious execution, or unauthorized access.
Capability Assessment
Purpose & Capability
Name/description (clarify requirements and confirm before code edits) match the provided SKILL.md and the two configuration/reference documents. The files only define question/confirmation workflows and rules; there are no unrelated credential requests, binaries, or external dependencies.
Instruction Scope
The instructions describe asking clarifying questions (3–5 rounds) and deciding whether to auto-execute or request confirmation based on config/rules.yaml. This implicitly assumes the agent can read and modify project files (to locate files and perform edits) — which is expected for a code-modification helper, but users should be aware that the skill's behavior presumes file-system/repository access by the agent.
Install Mechanism
Instruction-only skill with no install spec and no code files that execute. Lowest installation risk: nothing is written to disk or downloaded by the skill itself.
Credentials
No required environment variables, credentials, or config paths are declared. The config files only control questioning and confirmation behavior; no sensitive tokens or unrelated service access are requested.
Persistence & Privilege
Skill flags: always=false (not force-included). disable-model-invocation=false is the platform default and appropriate here. The skill does not request persistent system-wide changes or access to other skills' configs.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install requirement-agent
  3. After installation, invoke the skill by name or use /requirement-agent
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Requirement Agent v1.0.0 - Introduces a lightweight agent for daily code tasks such as modifications, refactoring, optimizations, and adding comments. - Implements a structured 3–5 round questioning process to clarify user requirements before execution. - Includes pre-execution confirmation based on configurable rules (e.g., multi-file edits, deletions). - Differentiates use cases from brainstorming; designed for routine code changes, not complex system design. - Provides documentation and guides for setup, questioning, and configuration.
Metadata
Slug requirement-agent
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Requirement Agent?

需求澄清与执行确认。用于日常代码任务(修改、重构、优化、添加注释等)。当用户提出需求时,先通过快速追问(3-5 轮)完善需求,执行前根据规则判断是否需要确认。与 brainstorming(复杂系统设计)互补。 It is an AI Agent Skill for Claude Code / OpenClaw, with 175 downloads so far.

How do I install Requirement Agent?

Run "/install requirement-agent" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Requirement Agent free?

Yes, Requirement Agent is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Requirement Agent support?

Requirement Agent is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Requirement Agent?

It is built and maintained by TrackOverflow . (@trackoverflow); the current version is v1.0.0.

💬 Comments