New to Claude Skills? Learn how to install them →

Wruvnet on GitHub

Workflow Run

Free

Manage and execute workflows with ease.

by ruvnet67.6k stars on ruvnet/ruflo
Updated Aug 10, 2026
Get this skill

Free · Opens the source repo

What Workflow Run does

The Workflow Run skill provides a robust interface for executing and controlling workflows within the MCP environment. It allows users to manage the lifecycle of workflows, including executing, pausing, resuming, and canceling workflows. This is particularly useful for developers and engineers who need to orchestrate complex processes that require monitoring and control over multiple steps. By leveraging the MCP workflow lifecycle, users can ensure that their workflows run smoothly and efficiently.

In addition to managing MCP workflows, the skill also supports the invocation of native workflows defined in .claude/workflows/*.js files. This allows users to run pre-defined scripts with specified parameters, enabling a deterministic approach to task execution. The ability to pass arguments and resume workflows from specific run IDs adds flexibility, making it easier to integrate workflows into larger systems or applications. Notifications on completion and the ability to monitor live progress further enhance the user experience.

This skill is ideal for developers and designers who are looking to automate processes, manage task execution, and improve workflow efficiency. Whether you are building a complex application that requires multiple workflows or simply need to manage a series of tasks, Workflow Run provides the necessary tools to streamline your operations. Its straightforward commands and structured approach make it accessible for users at various skill levels.

However, it's important to note that while Workflow Run excels at managing workflows, it may not be suitable for simpler tasks that do not require the overhead of a full workflow management system. For straightforward automation or scripting needs, lighter-weight solutions may be more appropriate.

When to use it

Use this skill when you need to execute, monitor, or control complex workflows in your projects.

When not to use it

Avoid this skill for simple tasks that don't require workflow management, as it may introduce unnecessary complexity.

What you can build with it

Automating Deployment Processes

Use Workflow Run to automate the deployment of applications by managing multiple workflows that handle different stages of the deployment process.

Monitoring Long-Running Tasks

Leverage this skill to monitor and control long-running tasks, allowing you to pause for review or resume as needed.

Integrating with Other Systems

Invoke native workflows to integrate with other systems or services, passing necessary parameters for seamless operation.

How to install Workflow Run

View source

1. Install with the skills CLI

npx skills add ruvnet/ruflo/workflow-run --agent claude-code

2. Or install it manually

Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.

Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs

Inside SKILL.md

Written by ruvnet

Workflow Run

Run and manage a workflow on either surface.

A — MCP workflow lifecycle

When you need to run a persisted definition and control its lifecycle (pause/resume/cancel):

  1. Execute — call mcp__plugin_ruflo-core_ruflo__workflow_execute or mcp__plugin_ruflo-core_ruflo__workflow_run with the workflow ID
  2. Monitor — call mcp__plugin_ruflo-core_ruflo__workflow_status to check progress and step outcomes
  3. Pause — call mcp__plugin_ruflo-core_ruflo__workflow_pause to halt at the current step
  4. Resume — call mcp__plugin_ruflo-core_ruflo__workflow_resume to continue from where paused
  5. Cancel — call mcp__plugin_ruflo-core_ruflo__workflow_cancel to abort the workflow

Execution modes: sequential, parallel (independent steps), conditional (branch on outcome), manual gate (pause for human approval).

B — Native .claude/workflows/*.js

When you need a deterministic subagent fan-out, run a named native workflow with the Workflow tool. The named workflows are the meta.name of each .claude/workflows/*.js file (list them with /workflow or ls .claude/workflows/).

Workflow({ name: 'plugin-contract-audit' })                    // run a named workflow
Workflow({ name: 'plugin-contract-audit', args: 'ruflo-agentdb' })  // pass args → the script's `args` global
Workflow({ scriptPath: '.claude/workflows/foo.js' })           // run a script by path
Workflow({ scriptPath, resumeFromRunId: 'wf_…' })              // resume — unchanged agent() calls return cached

Notes:

  • A native workflow runs in the background; you are notified on completion (don't poll). Watch live progress with /workflows.
  • Pause/resume here is journal-based (resumeFromRunId), not the MCP state machine. Stop a run first, then resume from its runId.
  • To author a new native workflow, use the workflow-create skill.

See ADR-0002.

Frequently asked questions about Workflow Run

Similar skills