Official Verified productivity Safety 3/5

agent-step-sequencer

Multi-step scheduler for in-depth agent requests. Detects when user needs multiple steps, suggests plan and waits for confirmation, persists state, and runs heartbeat-aware flow. Use when requests have 3+ actions, sequential dependencies, output dependencies, or high scope/risk.

Why use this skill?

Automate multi-step agent tasks with the Agent Step Sequencer. Ensure high-reliability, persistent progress tracking, and autonomous recovery for your AI agent.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/gostlightai/agent-step-sequencer

Download Source Code (.zip)

What This Skill Does

The Agent Step Sequencer is an advanced orchestration framework for OpenClaw that enables agents to break down complex, multi-stage requests into granular, verifiable tasks. Designed for high-scope workflows, this skill manages the entire lifecycle of a request, including planning, persistence, execution monitoring, and autonomous recovery. Unlike standard agent interactions that may timeout or lose context during long-running tasks, the Step Sequencer utilizes a state-driven approach where progress is saved in a JSON configuration. This ensures that even if a gateway reset or network interruption occurs, the agent can resume exactly where it left off upon the next heartbeat cycle. By enforcing a structured plan and validating required outputs for each step, the sequencer drastically reduces the probability of hallucinated task completion and improves overall system reliability.

Installation

You can install the Agent Step Sequencer via the ClawHub repository using the following command: clawhub install openclaw/skills/skills/gostlightai/agent-step-sequencer

Use Cases

This skill is ideal for projects requiring sequential dependencies or high-risk execution. Examples include:

Automated Research Pipelines: Downloading multiple data sources, cleaning them, and synthesizing a final report.
Content Development: Iterative writing processes where outline generation, draft creation, and proofreading must occur in strict sequence.
Complex Data Extraction: Performing API-heavy data fetching where rate-limiting requires intentional delays between calls.
System Migration Tasks: Operations that involve multi-step configuration, verification, and validation of file structures.

Example Prompts

"I need to generate a full market research report on the current state of decentralized finance, starting with data aggregation and ending with a final PDF summary. Please create a plan for this."
"Please conduct a technical audit of the files in my workspace. First, identify any security vulnerabilities in the source code, then write a remediation plan, and finally apply the recommended patches."
"Can you set up a multi-step sequence to scrape trending articles from three different news sites, summarize them, and save each summary as a separate markdown file in the /reports directory?"

Tips & Limitations

Rate Limiting: Always enable the 2-minute step delay if your target APIs are sensitive to high-frequency requests.
State Management: Do not manually modify the state.json file while the sequencer is running to avoid corruption.
Validation: Leverage the requiredOutputs field for every critical step to ensure the runner acts as a gatekeeper against incomplete work.
Resilience: The sequencer is designed for autonomous recovery; if a step fails, allow the system's internal retry mechanism to attempt a secondary endpoint or approach before manual intervention.

Read Full Documentation on GitHub

Metadata

Author@gostlightai

Stars2387

Updated2026-03-09

View Author Profile

AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill

Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-gostlightai-agent-step-sequencer": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#automation#scheduler#workflow#persistence#resilience

Safety Score: 3/5

Flags: file-write, file-read, code-execution, external-api

Related Skills

casual-cron

Create Clawdbot cron jobs from natural language with strict run-guard rules. Use when: users ask to schedule reminders or messages (recurring or one-shot), especially via Telegram, or when they use /at or /every. Examples: 'Create a daily reminder at 8am', 'Remind me in 20 minutes', 'Send me a Telegram message at 3pm', '/every 2h'.

gostlightai 2387

cdp-browser

CDP browser control at localhost:9222. Use when you need to inspect tabs, take screenshots, navigate, scroll, post to X, or run JS in a persistent browser session (e.g. logged into X, Gmail).

gostlightai 2387