A specialized skill for AI agents to capture coding intent, monitor scope drift, and document resolutions during implementation tasks.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install intent-framed-agent
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 intent-framed-agent 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 Intent Framed Agent?
The Intent Framed Agent skill provides a robust framework for managing the transition from planning to execution in AI-driven development. It functions by creating an explicit intent contract that defines the desired outcome, approach, and constraints before any code is modified. As part of the Openclaw Skills ecosystem, it ensures that high-level goals are translated into actionable and trackable implementation steps.
By establishing these boundaries, the skill protects projects from accidental scope creep and ensures that the agent remains focused on the specific problem at hand. It is particularly valuable for complex refactoring, new feature development, and bug fixes where the logical path might otherwise deviate from the original requirements.
Intent Framed Agent Use Cases
- Managing the transition from a Q&A or planning session to active code implementation.
- Preventing scope drift during multi-step execution tasks involving multiple files.
- Documenting architectural pivots and decisions made mid-session.
- Establishing clear success criteria for non-trivial coding assignments.
How Intent Framed Agent Works
- Intent Capture: Upon entering execution mode, the skill generates a structured Intent Frame containing the outcome, approach, constraints, and success criteria, requiring user confirmation before proceeding.
- Intent Monitoring: The agent periodically evaluates the current action against the stated intent at natural work boundaries to detect and flag potential drift.
- Intent Resolution: When the task is completed or abandoned, the skill generates a resolution record detailing what was delivered and documenting any pivots or remaining open items.
Intent Framed Agent Setup
To install this skill using the Openclaw Skills CLI, run the following command:
npx skills add pskoett/pskoett-ai-skills/intent-framed-agent
If you use the Entire CLI for session management, the skill will automatically attempt to detect it using:
entire status 2>/dev/null
Intent Framed Agent Data Schema & Taxonomy
The skill organizes session data into sequential frames. Each frame follows a specific markdown structure for parseability:
| Component | Fields Included |
|---|---|
| Intent Frame | Outcome, Approach, Constraints, Success Criteria, Estimated Complexity |
| Intent Check | Stated Outcome, Current Action, Pivot vs. Creep Question |
| Intent Resolution | Status (Fulfilled/Pivoted/Abandoned), Delivered Output, Pivots, Open Items |
Intent Framed Agent Advanced Features
- Support for multi-intent sessions where frames are numbered and resolved sequentially.
- Automatic integration with Entire CLI to capture intent records on checkpoint branches.
- Intelligent drift detection that prompts for deliberate pivots rather than blocking progress.
- Seamless interoperability with other Openclaw Skills like plan-interview and simplify-and-harden.
SKILL.md
Loading
Related Openclaw Skills
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.
Zhipu Web Search
Integrate Zhipu AI's powerful web search API to provide AI agents with real-time, structured internet information and multi-engine capabilities.
Plan Interview
A structured requirements gathering and planning skill that ensures alignment between developers and AI agents before implementation starts.
XiaoHongShu Auto-Publish
An all-in-one automation skill that generates AI copywriting, designs Chinese-style covers, and publishes directly to XiaoHongShu.
Featured*
