workflowBuild automated pipelines with reusable components, data flow between nodes, and state management.
Install via ClawdBot CLI:
clawdbot install ivangdavila/workflowRequires:
Workflows live in workflows/ with components and flows:
workflows/
āāā index.md # Inventory with tags
āāā components/
ā āāā connections/ # Auth configs
ā āāā nodes/ # Reusable operations
ā āāā triggers/ # Event sources
āāā flows/{name}/
āāā flow.md # Definition
āāā config.yaml # Parameters
āāā run.sh # Executable
āāā state/ # Persistent between runs
āāā logs/| Topic | File |
|-------|------|
| Directory layout, naming, formats | structure.md |
| Data passing between nodes | data-flow.md |
| Cursor, seen set, checkpoint | state.md |
| Retry, rollback, idempotency | errors.md |
| Connections, nodes, triggers | components.md |
| Create, test, update, archive | lifecycle.md |
security find-generic-password)workflows/ in workspace rootflows/{name}/state/ ā cursor.json, seen.json, checkpoint.jsonflows/{name}/logs/ ā JSONL per runflows/{name}/data/ ā intermediate files between nodesEach node writes output to data/{NN}-{name}.json. Next node reads it.
curl ... > data/01-fetch.json
jq '...' data/01-fetch.json > data/02-filter.jsonBreaking this pattern = nodes can't communicate.
Every node in flow.md MUST declare:
Undefined behavior = unpredictable workflow.
Prevent concurrent runs:
LOCKFILE="/tmp/workflow-${NAME}.lock"
exec 200>"$LOCKFILE"
flock -n 200 || exit 0| File | Purpose |
|------|---------|
| cursor.json | "Where did I leave off?" |
| seen.json | "What have I processed?" |
| checkpoint.json | "Multi-step recovery" |
Before creating new connections/nodes/triggers:
ls workflows/components/connections/
ls workflows/components/nodes/Use existing. Update "Workflows Using This" when adding.
Related: For LLM-driven multi-phase processes, see the cycle skill.
Generated Mar 1, 2026
An e-commerce platform uses the Workflow skill to automate daily product data ingestion from supplier APIs, transform the data with filtering and enrichment nodes, and load it into a database. It handles retries for API failures, manages state with cursor.json to track last processed items, and logs each run for auditing.
A media company sets up a workflow to scrape news websites, social media feeds, and RSS sources using trigger nodes for scheduled runs. Nodes process and deduplicate content based on seen.json, generate summaries, and push alerts to a Slack channel, with error handling to skip empty results.
An accounting firm automates monthly financial report generation by fetching transaction data from banking APIs, validating entries with jq-based nodes, and compiling reports into PDFs. It uses checkpoint.json for multi-step recovery during long runs and flock to prevent concurrent executions during peak periods.
A manufacturing plant implements a workflow to collect sensor data from IoT devices via HTTP requests, analyze trends with custom nodes, and trigger maintenance alerts. State files like cursor.json track data timestamps, and components are reused across multiple production lines for efficiency.
A SaaS company uses the Workflow skill to automate incoming support ticket processing: nodes fetch tickets from a helpdesk API, categorize them based on keywords, assign priority, and route to appropriate teams. It manages seen.json to avoid reprocessing and logs each step for compliance.
Offer the Workflow skill as a managed service where clients pay a monthly fee for custom automated pipelines, including setup, maintenance, and support. Revenue comes from tiered plans based on workflow complexity and data volume, with upsells for additional components or integrations.
Provide consulting services to help businesses design and deploy workflows tailored to their needs, such as data migration or process automation. Revenue is generated through project-based fees or hourly rates, with ongoing retainer contracts for updates and troubleshooting.
Create a marketplace where users can buy and sell pre-built nodes, triggers, and connections for the Workflow skill. Revenue is earned via transaction fees or subscriptions for premium components, encouraging community contributions and accelerating workflow development.
š¬ Integration Tip
Integrate with existing CI/CD pipelines by adding workflow runs as automated steps, and use environment variables for secrets instead of hardcoding to enhance security.
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.
Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications.
Advanced desktop automation with mouse, keyboard, and screen control
Manage n8n workflows and automations via API. Use when working with n8n workflows, executions, or automation tasks - listing workflows, activating/deactivating, checking execution status, manually triggering workflows, or debugging automation issues.
Design and implement automation workflows to save time and scale operations as a solopreneur. Use when identifying repetitive tasks to automate, building workflows across tools, setting up triggers and actions, or optimizing existing automations. Covers automation opportunity identification, workflow design, tool selection (Zapier, Make, n8n), testing, and maintenance. Trigger on "automate", "automation", "workflow automation", "save time", "reduce manual work", "automate my business", "no-code automation".
Browser automation via Playwright MCP server. Navigate websites, click elements, fill forms, extract data, take screenshots, and perform full browser automation workflows.