Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Migrate Cron Jobs To Lobster Workflows

ASecurity

Transform OpenClaw cron jobs into Lobster workflows. Analyze, inspect, and validate job migrations. Use when converting automations to deterministic, approval-gated workflows with resume capabilities.

19 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsgoshellbashgitdevops

Works with

cursorcli

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill migrate-cron-jobs-to-lobster-workflows --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Migrate Cron Jobs To Lobster Workflows?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Migrate Cron Jobs To Lobster Workflows
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-migrate-cron-jobs-to-lobster-workflows/badge)](https://www.skillsdirectory.com/skills/rondoflow-migrate-cron-jobs-to-lobster-workflows)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: migrate-cron-jobs-to-lobster-workflows
description: "Transform OpenClaw cron jobs into Lobster workflows. Analyze, inspect, and validate job migrations. Use when converting automations to deterministic, approval-gated workflows with resume capabilities."
category: "DevOps & Infra"
author: community
version: "1.0.0"
icon: server
---

# lobster-jobs

Transform OpenClaw cron jobs into Lobster workflows with approval gates and resumable execution.

## Purpose

OpenClaw cron jobs are either:
- **systemEvent**: Simple shell commands (fully deterministic)
- **agentTurn**: Natural language instructions spawning AI agents (flexible but token-heavy)

Lobster workflows offer:
- **Deterministic execution**: No LLM re-planning each step
- **Approval gates**: Hard stops requiring explicit user approval
- **Stateful execution**: Remembers cursors/checkpoints
- **Resumability**: Pauses and resumes exactly where left off

This skill helps analyze existing cron jobs and transform them into Lobster workflows.

## Commands

### Tier 1 (Available Now)

#### `lobster-jobs list`
List all cron jobs with their Lobster readiness score.

Output categories:
- ✅ **Fully Migratable**: Simple shell commands (systemEvent)
- 🟡 **Partial Migration**: Mixed deterministic + LLM steps (agentTurn)
- ❌ **Not Migratable**: Heavy LLM reasoning required

#### `lobster-jobs inspect <job-id>`
Inspect a specific cron job with detailed migration assessment.

Shows:
- Job metadata (schedule, target, payload type)
- Lobster migration status and reason
- Payload preview
- Migration recommendation

#### `lobster-jobs validate <workflow-file>`
Validate a Lobster workflow YAML file against schema.

Checks:
- Required fields (name, steps)
- Step structure (id, command)
- Approval gate syntax
- Condition syntax

### Tier 2 (Available Now)

#### `lobster-jobs convert <job-id>`
Transform a cron job into a Lobster workflow.

```bash
lobster-jobs convert 17fe68ca
lobster-jobs convert 17fe68ca --output-dir ~/workflows
lobster-jobs convert 17fe68ca --force  # Overwrite existing
```

Generates:
- `.lobster` workflow file in `~/.lobster/workflows/`
- Extracts commands from systemEvent or agentTurn payloads
- Auto-validates generated workflow

Options:
- `--output-dir, -o`: Custom output directory
- `--force, -f`: Overwrite existing workflow
- `--keep-on-error`: Keep file even if validation fails

#### `lobster-jobs new <name>`
Create a new Lobster workflow from scratch using templates.

```bash
lobster-jobs new my-workflow
lobster-jobs new my-workflow --template with-approval
lobster-jobs new my-workflow --template stateful
```

Templates:
- `simple-shell`: Basic command execution
- `with-approval`: Approval gate workflow
- `stateful`: Workflow with cursor/state tracking

## Installation

```bash
# Add to PATH
export PATH="$PATH:/home/art/niemand/skills/lobster-jobs/bin"

# Or create symlink
ln -s /home/art/niemand/skills/lobster-jobs/bin/lobster-jobs ~/.local/bin/
```

## Quick Start

```bash
# See all your cron jobs and their migration status
lobster-jobs list

# Inspect a specific job
lobster-jobs inspect 17fe68ca

# Convert a job to Lobster workflow
lobster-jobs convert 17fe68ca

# Create a new workflow from template
lobster-jobs new my-workflow --template with-approval

# Validate a workflow file
lobster-jobs validate ~/.lobster/workflows/my-workflow.lobster
```

## Workflow File Format

```yaml
name: my-workflow
description: Optional description

steps:
  - id: fetch_data
    command: some-cli fetch --json
    
  - id: process
    command: some-cli process
    stdin: $fetch_data.stdout
    
  - id: approve_send
    command: approve --prompt "Send notification?"
    approval: required
    
  - id: send
    command: message.send --channel telegram --text "Done!"
    condition: $approve_send.approved
```

## Migration Strategy

### Wrapper Approach (Recommended)
Keep cron as scheduler, change payload to call Lobster:

```json
{
  "payload": {
    "kind": "systemEvent",
    "text": "lobster run ~/.lobster/workflows/my-workflow.lobster"
  }
}
```

Benefits:
- Rollback is trivial (revert payload)
- Incremental migration
- Cron scheduling already works

## Handling LLM Judgment

For jobs needing both deterministic steps and LLM reasoning:

```yaml
steps:
  - id: gather
    command: gh issue list --json title,body
    
  - id: triage
    command: clawd.invoke
    prompt: "Classify these issues by urgency"
    
  - id: notify
    command: telegram-send
```

The workflow is deterministic; the LLM is a black-box step.

## Edge Cases

| Issue | Handling |
|-------|----------|
| **Idempotency** | Workflows track step completion; restart-safe |
| **Approval timeouts** | Configurable timeout with default action |
| **Secret handling** | Environment variables or 1Password refs |
| **Partial failures** | `convert` validates before writing |

## References

- Lobster: https://github.com/openclaw/lobster
- Lobster VISION: https://github.com/openclaw/lobster/blob/main/VISION.md

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693621 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →