A structured requirements gathering and planning skill that ensures alignment between developers and AI agents before implementation starts.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install plan-interview
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install plan-interview using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Plan Interview?
The Plan Interview skill is a specialized component of the Openclaw Skills ecosystem designed to eliminate assumptions and technical debt during the initial stages of feature development. By initiating a thematic, four-domain interview process, it bridges the gap between high-level user requests and actionable technical specifications. This tool is specifically engineered for non-trivial tasks like refactoring or new feature implementation where alignment on risk tolerance and success criteria is paramount.
Integrating this into your Openclaw Skills library transforms the way you interact with AI agents by introducing a mandatory draft-then-refine workflow. It encourages a pause for codebase exploration and iterative plan refinement, ensuring that every line of code written later is backed by a solid, peer-reviewed architectural foundation. This process prevents silent scope reduction and ensures that all technical constraints are respected throughout the implementation lifecycle.
Plan Interview Use Cases
- Planning a major refactor of an existing module where technical constraints are high.
- Implementing a new complex feature that requires alignment on multiple integration points.
- Defining success criteria and risk tolerance for high-risk migrations or authentication changes.
- Generating detailed documentation and implementation checklists for team-wide visibility.
How Plan Interview Works
- The user invokes the skill using the
/plan-interviewcommand followed by a task description. - The agent initiates a thematic interview, asking 2-3 questions per batch regarding technical constraints, scope, risks, and success criteria.
- The agent performs a codebase exploration to understand existing patterns, affected files, and architecture boundaries.
- A draft plan is generated and stored in a sequential markdown file within the
docs/plans/directory. - The agent executes an iterative refinement loop with a fresh-eyes approach to identify contradictions or missing edge cases.
- Upon user approval, the agent automatically starts the implementation phase using the generated checklist for tracking.
Plan Interview Setup
To install this skill and add it to your Openclaw Skills collection, run the following command in your terminal:
npx skills add pskoett/pskoett-ai-skills/plan-interview
Plan Interview Data Schema & Taxonomy
The skill organizes planning data into a standardized file structure and uses a consistent internal taxonomy to track implementation progress.
| Attribute | Specification |
|---|---|
| File Location | docs/plans/plan-NNN-<slug>.md |
| Naming Convention | Sequential numbering (NNN) followed by a descriptive slug |
| Plan Components | Success Criteria, Risk Assessment, Affected Files, Test Strategy, Validation, and Implementation Checklist |
| Metadata | Tracks plan depth (Simple, Moderate, or Complex) and refinement pass summaries |
Plan Interview Advanced Features
- Fast Mode: Supports an abbreviated planning workflow for simpler tasks with a single refinement pass.
- Resume Support: Detects existing partial plans and allows users to continue interviews or refinement from where they left off.
- Multi-Plan Synthesis: Capable of merging multiple competing plans into a single canonical document while preserving the best architectural ideas.
- Planning Depth Calibration: Dynamically adjusts the intensity of the planning process based on the detected complexity of the implementation task.
SKILL.md
Loading
Related Openclaw Skills
Intent Framed Agent
A specialized skill for AI agents to capture coding intent, monitor scope drift, and document resolutions during implementation tasks.
DX Data Navigator
A comprehensive engineering intelligence skill for querying Developer Experience (DX) metrics, DORA data, and team performance via PostgreSQL.
Agent Teams: Simplify and Harden
A robust multi-agent orchestration pattern that automates the implementation, security auditing, and refactoring of complex codebases.
Feishu Bot Manager
A comprehensive CRUD utility for managing Feishu bot configurations within the Openclaw ecosystem.
XiaoHongShu Auto-Publish
An all-in-one automation skill that generates AI copywriting, designs Chinese-style covers, and publishes directly to XiaoHongShu.
Article Writer
An expert content engine that transforms raw topics into high-conversion, modular articles using professional copywriting frameworks and real-time research.
Featured*
