New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Output Workflow Run

by growthxai in growthxai/output

Execute an Output SDK workflow synchronously and wait for the result.

Apache-2.0Auto-check: notes

Install Output Workflow Run

skills CLI
$ npx skills add growthxai/output --skill output-workflow-run -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install growthxai/output output-workflow-run --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/growthxai/output.git skills-src && mkdir -p .claude/skills && cp -r skills-src/coding_assistants/claude/plugins/outputai/skills/output-workflow-run .claude/skills/output-workflow-run && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
output-workflow-run
GitHub stars
442
Token cost
~1.6k tokens
SKILL.md length
468 words
Files
1
Skills in repo
50
Repo updated
First seen
Licence
Apache-2.0

At a glance

Execute an Output SDK workflow synchronously and wait for the result.

  • Works in 2 steps: Inline JSON → File Path (Recommended)
  • Running a workflow and needing immediate results
  • SKILL.md covers Overview, When to Use This Skill, When to Use Async Instead and Instructions, plus 5 more sections
  • Calls npx and jq

What it does

Output Workflow Run is an agent skill from growthxai/output. Execute an Output SDK workflow synchronously and wait for the result. Use when running a workflow and needing immediate results, testing workflow execution, or getting the output directly in the terminal.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: The open-source TypeScript framework for building AI workflows and agents. Designed for Claude Code describe what you want, Claude builds it, with all the best practices already… The licence is Apache-2.0.

When your agent uses it

  • Running a workflow and needing immediate results
  • Testing workflow execution
  • Getting the output directly in the terminal

Example prompts

  • “/output-workflow-run”

Requirements

  • Node.js
  • Pre-approved tools (allowed-tools): Bash, Read, Write

Workflow steps

2 steps, taken from the step headings in SKILL.md.

  1. Inline JSON
  2. File Path (Recommended)

What it can do on your machine

Read from SKILL.md and the folder at commit 99ee298. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash
    • Read
    • Write

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npx
    • jq

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Output Workflow Run loads about 1.6k tokens when it runs. Until then it costs about 56 tokens; SKILL.md has 468 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~56
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Read, Write

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from growthxai/output at commit 99ee298, republished under its Apache-2.0 licence (© growthxai). 468 words, ~1,612 tokens.

Download SKILL.mdSave it as .claude/skills/output-workflow-run/SKILL.md (or your agent's skills folder).
name
output-workflow-run
description
Execute an Output SDK workflow synchronously and wait for the result. Use when running a workflow and needing immediate results, testing workflow execution, or getting the output directly in the terminal.
allowed-tools
Bash, Read, Write

Run Workflow Synchronously

Overview

This skill executes a workflow synchronously, meaning the command waits for the workflow to complete and returns the result directly. This is ideal for testing, quick executions, and when you need immediate feedback.

When to Use This Skill

  • Testing a workflow during development
  • Running a workflow and needing the result immediately
  • Quick one-off workflow executions
  • Debugging by re-running a workflow with different inputs
  • When you don't need to monitor the workflow separately

When to Use Async Instead

Consider using npx output workflow start (async) when:

  • The workflow takes a long time (minutes to hours)
  • You need to run multiple workflows in parallel
  • You want to disconnect and check results later
  • You need to monitor progress separately

Instructions

Basic Syntax
bash
npx output workflow run <workflowName> --input '<json-input>'
npx output workflow run <workflowName> --input <path-to-json-file>

The --input flag is required when the workflow expects input data.

Input Methods
1. Inline JSON

Pass JSON directly on the command line:

bash
npx output workflow run example --input '{"question": "who really is ada lovelace?"}'

Reference a JSON file containing the input:

bash
npx output workflow run simple --input src/simple/scenarios/question_ada_lovelace.json

This is the recommended approach because:

  • Input is version controlled and reproducible
  • Complex inputs are easier to read and edit
  • Scenarios can be shared and reused
Scenario Folder Pattern (Best Practice)

Workflows typically have a scenarios/ folder containing test inputs:

src/
  my_workflow/
    workflow.ts
    steps.ts
    scenarios/
      basic_test.json
      edge_case_empty.json
      large_payload.json

Best practice workflow:

  1. Create a scenario file with your input:

    bash
    # Create scenarios folder if it doesn't exist
mkdir -p src/my_workflow/scenarios

  2. Write your input to a scenario file:

    json
    // src/my_workflow/scenarios/test_user.json
{
  "userId": "123",
  "options": {
    "verbose": true
  }
}

  3. Run the workflow referencing the scenario:

    bash
    npx output workflow run my_workflow --input src/my_workflow/scenarios/test_user.json
Input Examples
bash
# Inline JSON - simple object
npx output workflow run my-workflow --input '{"userId": "123"}'

# Inline JSON - complex nested input
npx output workflow run data-pipeline --input '{"source": "api", "options": {"limit": 100}}'

# File path - reference a scenario file
npx output workflow run simple --input src/simple/scenarios/basic.json

# File path - relative to current directory
npx output workflow run batch-processor --input ./test_inputs/batch1.json

# No input (only if workflow doesn't require it)
npx output workflow run health-check

Understanding the Output

The command returns the workflow result directly to stdout.

Success Output

The workflow's return value is displayed, typically as JSON.

Error Output

If the workflow fails, you'll see:

  • Error message
  • The workflow ID (for further debugging)
  • Suggestion to use npx output workflow debug for details
Show full SKILL.md (195 more words)Show less

Examples

Scenario: Test a workflow with a scenario file

bash
# First, look for existing scenarios
ls src/simple/scenarios/

# Run using a scenario file
npx output workflow run simple --input src/simple/scenarios/basic_sum.json

# Output:
# { "sum": 6, "count": 3 }

Scenario: Create and run a new test scenario

bash
# Create a scenario file
cat > src/my_workflow/scenarios/test_case_1.json << 'EOF'
{
  "question": "What is the capital of France?",
  "context": "geography"
}
EOF

# Run the workflow
npx output workflow run my_workflow --input src/my_workflow/scenarios/test_case_1.json

Scenario: Quick inline test during development

bash
npx output workflow run example --input '{"question": "explain quantum computing"}'

Scenario: Re-run a workflow with different input for debugging

bash
# First attempt with scenario file
npx output workflow run process-data --input src/process_data/scenarios/user_abc.json
# Error occurs

# Create a new scenario to isolate the issue
cat > src/process_data/scenarios/debug_minimal.json << 'EOF'
{"id": "test", "debug": true}
EOF

npx output workflow run process-data --input src/process_data/scenarios/debug_minimal.json

Scenario: Capture output for further processing

bash
# Save result to a file
npx output workflow run generate-report --input src/generate_report/scenarios/jan_2024.json > report.json

# Pipe to jq for processing
npx output workflow run get-users --input src/get_users/scenarios/active.json | jq '.users[].name'

Error Handling

Common Errors
ErrorCauseSolution
"Workflow not found"Workflow name is incorrectCheck with npx output workflow list
"Invalid input"JSON doesn't match schemaVerify input matches workflow's inputSchema
"Parse error"Malformed JSON or file not foundCheck JSON syntax or file path
"Timeout"Workflow took too longUse async execution for long workflows
Getting More Details on Failures

When a workflow fails, the output includes the workflow ID. Use it to get the full trace:

bash
npx output workflow run my-workflow --input src/my_workflow/scenarios/test.json
# Output: Workflow failed. ID: abc123xyz

npx output workflow debug abc123xyz --json

Input Schema Tips

  1. Check the schema first: Look at the workflow's inputSchema in the code
  2. Use scenario files: Create reusable test inputs in the workflow's scenarios/ folder
  3. Use proper types: Strings in quotes, numbers without quotes, booleans as true/false
  4. Include required fields: All non-optional schema fields must be provided
  • npx output workflow start <name> --input - Start asynchronously
  • npx output workflow list - See available workflows
  • npx output workflow debug <id> - Debug a failed run

© growthxai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in coding_assistants/claude/plugins/outputai/skills/output-workflow-run of growthxai/output.

Open the folder on GitHubat commit 99ee298

Compare with similar skills

Output Workflow Run next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Output Workflow Run compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Output Workflow Run this skillgrowthxai/output442—~1.6kAutomated safety check: NotesApache-2.0
Executealirezarezvani/claude-skills28k—~831Automated safety check: PassMIT
Debugging Executionsn8n-io/n8n207k—~2.6kAutomated safety check: PassCustom licence
Agent Crdt Synchronizerruvnet/ruflo74k2 repos~6.3kAutomated safety check: PassMIT
Ulw Executecode-yeongyu/oh-my-openagent70k—~6.3kAutomated safety check: PassCustom licence
Executebrycewang-stanford/Auto-Empirical-Research-Skills4.6k—~370Automated safety check: NotesCustom licence

Similar skills

  • Execute

    alirezarezvani/claude-skills

    /cs:execute <decision — Generate a 90-day execution plan with weekly milestones, DRIs, and check-in cadence from an approved decision.

    28k GitHub stars~831 tokensUpdated 1 mo ago
    Product & Project ManagementAuto-check passed

  • Debugging Executions

    n8n-io/n8n

    Official

    Debug failed or wrong-output workflow executions using executions tools.

    207k GitHub stars~2.6k tokensUpdated today
    DevelopmentAuto-check passed

  • Agent Crdt Synchronizer

    ruvnet/ruflo

    Agent skill for crdt-synchronizer - invoke with $agent-crdt-synchronizer

    74k GitHub starsUsed in 2 repos~6.3k tokens
    Auto-check passed

  • Ulw Execute

    code-yeongyu/oh-my-openagent

    Executes a written ulw-plan work plan with Boulder state, evidence ledger, worktree discipline, and parallel subagents.

    70k GitHub stars~6.3k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Execute

    brycewang-stanford/Auto-Empirical-Research-Skills

    Executes all registered notebooks, strips noisy cell metadata, and syncs Jupytext pairs.

    4.6k GitHub stars~370 tokensUpdated 5 days ago
    Data & AnalyticsAuto-check: notes

  • Safe SQL Execution

    supabase/supabase

    Official

    A skill your agent uses whenever code will build, return, fetch, or execute SQL that runs against a user's real Postgres database — even when the request reads like an ordinary feature or bug fix…

    111k GitHub stars~4.2k tokensUpdated today
    DatabasesAuto-check passed

More from growthxai/output

All 50 skills in this repo

  • Output Build Workflow

    growthxai/output

    Implement an Output SDK workflow from a plan document. An agent skill from growthxai/output.

    442 GitHub stars~2.2k tokensUpdated today
    Auto-check passed

  • Output Credentials Edit

    growthxai/output

    View, edit, and set encrypted credentials in an Output.ai project.

    442 GitHub stars~1.1k tokensUpdated today
    Auto-check: notes

  • Output Credentials Env Vars

    growthxai/output

    Wire encrypted credentials to environment variables using the credential: convention.

    442 GitHub stars~930 tokensUpdated today
    Auto-check: notes

  • Output Credentials Init

    growthxai/output

    Initialize encrypted credentials for an Output.ai project. An agent skill from growthxai/output.

    442 GitHub stars~803 tokensUpdated today
    Auto-check: notes

  • Output Debug Workflow

    growthxai/output

    Debug Output SDK workflow issues. An agent skill from growthxai/output.

    442 GitHub stars~1.5k tokensUpdated today
    Auto-check passed

  • Output Dev Agent Class

    growthxai/output

    Use the Agent class for multi-step tool loops, conversation history, streaming progress, and reusable LLM agents.

    442 GitHub stars~2.6k tokensUpdated today
    Auto-check passed

Questions about Output Workflow Run

What does Output Workflow Run do?

Execute an Output SDK workflow synchronously and wait for the result. Output Workflow Run is an agent skill from growthxai/output. Execute an Output SDK workflow synchronously and wait for the result.

When should I use Output Workflow Run?

Output Workflow Run fits situations like: running a workflow and needing immediate results; testing workflow execution; getting the output directly in the terminal.

How do I install Output Workflow Run in Claude Code?

Run `npx skills add growthxai/output --skill output-workflow-run -a claude-code`. Or copy the skill folder (coding_assistants/claude/plugins/outputai/skills/output-workflow-run in growthxai/output) into .claude/skills/output-workflow-run in your project. Claude Code loads it when a task matches its description.

How do I install Output Workflow Run in Codex?

Run `npx skills add growthxai/output --skill output-workflow-run -a codex`. Or copy the skill folder (coding_assistants/claude/plugins/outputai/skills/output-workflow-run in growthxai/output) into .agents/skills/output-workflow-run in your project. Codex loads it when a task matches its description.

Can I use Output Workflow Run in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add growthxai/output --skill output-workflow-run -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/output-workflow-run, .gemini/skills/output-workflow-run, .github/skills/output-workflow-run and .opencode/skills/output-workflow-run in your project.

What does Output Workflow Run need to run?

Going by SKILL.md and its folder, Output Workflow Run needs the command-line tools its instructions call (npx and jq). Our summary lists: Node.js. Its frontmatter pre-approves these tools: Bash, Read, Write.

Does Output Workflow Run access the network?

SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Output Workflow Run safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Output Workflow Run use?

Output Workflow Run is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Output Workflow Run use?

About 1.6k tokens (SKILL.md is roughly 6.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Output Workflow Run?

Skills that share tags, products or a category with Output Workflow Run: Execute (alirezarezvani/claude-skills, 28k stars), Debugging Executions (n8n-io/n8n, 207k stars), Agent Crdt Synchronizer (ruvnet/ruflo, 74k stars) and Ulw Execute (code-yeongyu/oh-my-openagent, 70k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Output Workflow Run?

growthxai (a GitHub organization) maintains it in growthxai/output, which has 442 GitHub stars. The repository holds 50 skills in this directory. The repository was last updated on October 9, 2026.

Source: growthxai/output on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.