A governance protocol for AI agents to ensure long-running tasks remain visible, staged, and auditable without human intervention.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install tesp
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 tesp 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 Task Execution Signal Protocol (TESP)?
The Task Execution Signal Protocol (TESP) is a high-level coordination framework designed for Openclaw Skills to handle non-instantaneous work. Rather than operating in a black box, TESP ensures that every action taken by an AI agent is visible, versioned, and staged. It is specifically engineered to solve the 'silence risk' in complex workflows where multiple steps or agents are involved, providing a structured way to broadcast progress and handle handoffs.
At its core, TESP is not just about completing a task; it is about execution governance. By enforcing Layer 1 acknowledgements and numeric progress signaling, it allows human collaborators and other agents to monitor the heartbeat of a project. This protocol reduces cognitive load by eliminating the need for manual status updates and ensuring that task boards remain clean and actionable through automated archiving.
Task Execution Signal Protocol (TESP) Use Cases
- Managing long-running research, migrations, or troubleshooting tasks that span multiple sessions.
- Coordinating multi-agent workflows where handoffs must be documented and visible.
- Automating task board hygiene to separate active work from historical archives.
- Reducing human follow-ups by providing a predictable cadence of progress broadcasts.
- Auditing agent performance against execution standards using low-token inspection methods.
How Task Execution Signal Protocol (TESP) Works
- Fast Acknowledgement: Immediately issue a Layer 1 signal containing the TESP version, the specific scene context, and the ultimate goal.
- Staged Partitioning: Break down extensive tasks into discrete, numbered units (e.g., 1/5, 2/5) to provide a clear digital progress indicator.
- Cadence-Based Broadcasting: Provide updates based on the task's expected duration rather than generating unnecessary chatter.
- Queue Management: Maintain all active work items within a centralized TASK_QUEUE.md for real-time tracking.
- Automated Archiving: Transition completed tasks into TASK_ARCHIVE.md to maintain a high signal-to-noise ratio on the active board.
- Blocker Escalation: Explicitly define what is blocked and the specific decision required from the human or lead agent to resume.
- Efficient Auditing: Utilize file checks and diffs for supervision to keep token consumption low and oversight effective.
Task Execution Signal Protocol (TESP) Setup
To implement this skill within your Openclaw Skills environment, ensure your agent has access to the protocol references and task tracking files.
# Initialize the TESP task tracking files
touch TASK_QUEUE.md TASK_ARCHIVE.md
# Review the core protocol templates
cat references/protocol.md
cat references/templates.md
Configure your agent to default to lightweight models like GLM or MiniMax for routine queue audits to optimize performance.
Task Execution Signal Protocol (TESP) Data Schema & Taxonomy
TESP organizes execution data across several key files to maintain a clear audit trail and operational state:
| File Name | Purpose | Content Type |
|---|---|---|
TASK_QUEUE.md |
Active Work | Current tasks, numeric progress (e.g., 2/5), and active blockers. |
TASK_ARCHIVE.md |
Completed Work | Finished task history, final results, and timestamps. |
references/protocol.md |
Governance | The full text of the Task Execution Signal Protocol. |
references/templates.md |
Formatting | Standardized Layer 1 and progress update templates. |
Task Execution Signal Protocol (TESP) Advanced Features
- Multi-agent handoff discipline ensuring task boards are updated before execution transfer.
- Low-token audit hooks that allow for efficient supervision of agent progress.
- Standardized Layer 1 signaling for immediate transparency upon task receipt.
- Automated queue hygiene protocols to prevent task board bloating in long-term projects.
SKILL.md
Loading
Related Openclaw Skills
Cyber Fantasy UI
A sophisticated visual design system for generating dark, neon-lit, and gamified user interfaces using React and Tailwind CSS.
Discount Marketing Strategy
A comprehensive framework for planning, implementing, and optimizing discount and promotional pricing strategies for digital products and services.
Conversion Optimization
A professional framework for increasing conversion rates through rigorous A/B testing, funnel analysis, and PIE prioritization.
Mao Method Analysis Skill
A sophisticated analytical framework that translates Maozedong's strategic methodologies into actionable steps for solving complex modern business and personal structural challenges.
Moodle Connector
A powerful Moodle REST API client and MCP server designed to integrate Learning Management System data directly into AI coding agents.
TESP Audit
A lightweight governance skill designed to audit the integrity and adherence of the Task Execution Signal Protocol (TESP) within AI agent workflows.
Featured*
