Skip to content
cccskills
FreePublished on GitHub

workflow-creator

Create or update saved Dynamic Workflows, JavaScript scripts that organize repeatable agent tasks. Capture task order, dependencies, and final results in a reusable file, with a slash command for running the workflow.

OriginalShow the original description

Create or update reusable Dynamic Workflow JavaScript files under .qwen/workflows. Use when the user asks to create, save, edit, or reuse a Dynamic Workflow, including requests started from the Web Shell Workflows page.

See how to install

Good for

  • Saving a repeated task as a reusable workflow
  • Updating the steps in an existing workflow
  • Organizing parallel tasks and dependent steps
  • Creating a workflow shared across projects

Files included (2)

  • SKILL.md3.4 KB
  • SKILL.test.ts1.5 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Workflow Creator

Create and maintain saved Dynamic Workflows for the current workspace.

Boundary

  • This skill manages .qwen/workflows/<name>.js files used by the workflow tool and exposed as /<name> slash commands.
  • Do not create or edit qwen-workflow-design/*.yaml; those Task Flow definitions are a different feature.
  • Use project scope by default. Write to ~/.qwen/workflows only when the user explicitly asks for a workflow shared across projects.

Workflow

  1. Inspect the current task and any existing workflow with the requested name. Ask a question only when the goal, ordering, or write scope is materially ambiguous.
  2. Choose a lower-case name containing only letters, digits, and hyphens. It must start with a letter and be at most 41 characters.
  3. Create the smallest script that captures the requested phases, dependencies, and final result. Do not add speculative branches, retries, or agents.
  4. Read the saved file back and verify its name, metadata, phase order, dependency flow, and final return value. Do not execute it unless the user also asks to run it.
  5. Report the saved path and slash command. In the interactive TUI's ink renderer, the slash command runs in the foreground: progress stays in the tool card, and completion displays the result and notifies the model. The OpenTUI renderer does not yet run client-scheduled tools; there, ask the model to call Workflow({ name: '<name>' }) instead. /workflows <runId> shows the run after it settles. In Web Shell, tell the user to return to Workflows and refresh the Saved tab if it is already open.

Script contract

  • Start with a literal metadata declaration:
export const meta = {
  name: 'Release readiness',
  description: 'Inspect, validate, and summarize a release candidate',
};
  • Use the sandbox globals phase(title), log(message), agent(prompt, options?), parallel(thunks), pipeline(items, ...stages), workflow(nameOrRef, args?), args, and budget. The workflow-authoring skill is the full reference for them — load it before writing anything beyond a trivial script.
  • Scripts cannot import modules or access the filesystem, shell, environment, or network directly. Put required reads and actions in explicit agent prompts.
  • Give every agent a complete, scoped prompt and a concise label. State whether it may edit files.
  • Express real concurrency as parallel([() => agent(...), () => agent(...)]). Do not pass already-started promises to parallel.
  • Keep dependent work sequential and pass prior results explicitly.
  • Put variable user input in args instead of hard-coding one-off values.
  • End every successful path with an explicit return of the final result. A trailing expression is not a return value.
  • Do not use node --check for validation: valid workflow scripts may contain top-level await and return because the runtime wraps them in an async function.

Updates

  • Preserve unrelated behavior and metadata when editing an existing workflow.
  • Do not overwrite an existing workflow with a different design unless the user requested that update.
  • Do not delete or rename a workflow unless the user explicitly asks.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

agent-delegation

FreeSummary

Write clear briefs for subagents and conversation forks, agents that inherit conversation history. Specify purpose, known findings, scope, and expected output while respecting each agent's existing role and separating research requests from implementation.

  • Writing a focused research brief for a subagent
  • Specifying files and constraints for implementation
  • Defining scope for an agent inheriting conversation history
QwenLM/qwen-code28.6KUpdated Oct 18, 2026

Compare a feature implemented in Qwen Code with Codex or Claude Code under the same scenario. Capture communication and terminal records, inspect tool definitions and outputs, and guide fixes toward matching observable behavior.

  • Checking a reproduced feature against its reference agent
  • Comparing tool definitions and required arguments
  • Investigating differences in terminal output
QwenLM/qwen-code28.6KUpdated Oct 18, 2026

Reproduce a Codex or Claude Code feature in Qwen Code or another command-line agent. Capture requests, terminal output, and state changes, then use that evidence to implement focused behavior and add a verification path.

  • Reproduce an existing agent's slash command
  • Inspect request formats and tool definitions
  • Compare terminal output and saved state
QwenLM/qwen-code28.6KUpdated Oct 18, 2026

autofix

FreeSummary

Review local uncommitted changes, verify findings, and repeat focused repairs until the review converges or a blocker remains. Also supports Qwen Code issue fixes and review responses within workflows run through GitHub Actions.

  • Review and repair local uncommitted changes
  • Develop a focused fix for a selected issue
  • Verify and address pull request feedback
QwenLM/qwen-code28.6KUpdated Oct 18, 2026

batch

FreeSummary

Apply the same operation across multiple files using parallel worker agents. The skill finds matching files, divides the work, and reports successes, failures, and skipped files, with a preview option before edits.

  • Add license headers across source files
  • Convert JavaScript files to TypeScript
  • Fix the same lint issue in multiple files
QwenLM/qwen-code28.6KUpdated Oct 18, 2026

batch-api

FreeSummary

Prepare shared instructions for translating, rewriting, or extracting information from many independent files, then submit a plan through the DashScope Batch API. Processing runs asynchronously at half the realtime list price and delivers new files later.

  • Translate many documents using shared terminology
  • Rewrite independent files into a consistent format
  • Extract structured data from a collection of files
QwenLM/qwen-code28.6KUpdated Oct 18, 2026

See all skills by QwenLM

Report a problem with this skill