A standardized communication protocol that ensures AI agents provide consistent status updates and concise two-line summaries after every action.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install interaction-pipeline
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 interaction-pipeline 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 Interaction Pipeline?
The Interaction Pipeline skill is designed to bring operational discipline to AI agent communications. It establishes a rigorous status flow and summary format that ensures users are never left guessing about an agent's progress or intent. By implementing this skill, developers can enforce a predictable lifecycle for every tool execution within the ecosystem of Openclaw Skills, making autonomous agents more reliable and easier to monitor.
This skill acts as a middleware layer that intercepts tool outputs to provide a structured STARTED, IN_PROGRESS, and DONE/BLOCKED state machine. It prioritizes clarity by overriding default LLM verbosity with high-signal, actionable feedback, which is essential for maintaining trust in automated workflows.
Interaction Pipeline Use Cases
- Standardizing reporting for complex, multi-step developer workflows
- Providing clear debugging paths when an agent encounter a BLOCKED state
- Maintaining visibility during long-running background tasks or data processing
- Ensuring consistent feedback loops in human-in-the-loop automation scenarios
How Interaction Pipeline Works
- The skill hooks into the agent execution lifecycle immediately after any tool or action is triggered.
- It transitions the internal state from STARTED to IN_PROGRESS as the action executes.
- If a user queries the agent mid-task, the skill provides the current step and an estimated completion time.
- Upon completion, it validates the result and transitions to either DONE or BLOCKED.
- It generates a mandatory two-line summary: the first line describes the achievement in past tense, and the second line provides the immediate next step or a command to repeat the action.
Interaction Pipeline Setup
To integrate the Interaction Pipeline into your agent configuration, add the skill key to your active manifest. This skill is designed to function as a post-execution hook for all other Openclaw Skills.
# Add the skill to your local environment
openclaw install interaction-pipeline
Interaction Pipeline Data Schema & Taxonomy
The Interaction Pipeline follows a strict state transition model and output schema to ensure compatibility across different interfaces.
| State | Definition | Requirement |
|---|---|---|
| STARTED | Task initialization | Immediate log |
| IN_PROGRESS | Execution phase | Mid-task updates allowed |
| DONE | Successful completion | Mandatory 2-line summary |
| BLOCKED | Execution failure | Error cause + concrete fix |
Output Format:
- Line 1: Past-tense description of the accomplishment.
- Line 2: Short, actionable instruction for what to do next or how to repeat.
Interaction Pipeline Advanced Features
- Global override capability that prevents other skills from suppressing status updates
- Per-step summarization for multi-stage tasks to maintain granular visibility
- Automatic injection of concrete fixes when encountering known error patterns
- Native integration with guided-conversation for pre-action requirement gathering
SKILL.md
Loading
Related Openclaw Skills
FlowForge Workflow Runner
A structured state machine engine for AI agents to execute complex, multi-step workflows without skipping critical steps.
OpenClaw SaaS Builder
A comprehensive orchestration skill for building SaaS projects end-to-end using OpenClaw as the driver and Gemini CLI as a planning copilot.
PowerShell Sandbox
A restricted execution environment for PowerShell scripts that enforces command whitelisting, resource limits, and timeout protection.
React Orchestrator
A sophisticated reasoning framework that orchestrates AI agents using a dual-system approach for both rapid execution and deep strategic planning.
Skill Interview Builder
A structured interview agent that automates the creation of ready-to-use AI skill packages by guiding users through a three-round requirement gathering process.
Guided Conversation
A smart interaction protocol that minimizes user friction by asking up to four clarifying questions before executing high-impact or ambiguous tasks.
Featured*
