# scenario-workflows

A skill for running saved Scenario workflows over MCP: list apps, build the inputs object, price a run before spending anything.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 391 installs · ★ 1141
- Author: scenario-labs
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/scenario-labs/skills/tree/HEAD/skills/scenario-workflows/SKILL.md
- Updated: 2026-10-23
- HTML: https://affpapa.org/en/nevibecode/skills/scenario-workflows

## What it does

A Scenario workflow is a saved node graph that chains several models into one call. Users say "app" and mean one whose status is `ready`. `workflow_run` hands back a job you track like any other generation.

Only `workflows_list`, `workflow_get` and `workflow_run` are listed by default. Approving or rejecting a stuck approval node goes through `scenario_tools_search` and its executor lane. Cap every list call: each record carries the compiled `flow` and the full `editorInfo` graph, and there is no compact flag. Keep `limit` at 3 or fewer and read only `id`, `name`, `hasFlow` and `inputs`. The tool schema advertised a ceiling of 200, but the API rejects anything past 100 with a 400, so the schema maximum is not a value to send.

Take input keys verbatim from `inputs[].name` — they are node ids, so names can be positional (`text2`, `text3`) and neither contiguous nor ordered. Test `required.always === true`; a plain truthiness check reads `{"always": false}` as required too. Route long text through `dry_run=true`: same validator, zero cost. A string input inherits the length ceiling of the node behind it, and the record never lists that ceiling — it only surfaces at run time.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add scenario-labs/skills --skill scenario-workflows -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/scenario-workflows/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/scenario-workflows/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add scenario-labs/skills --skill scenario-workflows -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/scenario-workflows/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add scenario-labs/skills --skill scenario-workflows -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/scenario-workflows/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install scenario-labs/skills scenario-workflows
```

2. **Manually: put the files in place**
- File: `.github/skills/scenario-workflows/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add scenario-labs/skills --skill scenario-workflows -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/scenario-labs/skills --path skills/scenario-workflows
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/scenario-workflows/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add scenario-labs/skills --skill scenario-workflows -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/scenario-labs/skills/tree/HEAD/skills/scenario-workflows/SKILL.md

## When to use it
- list ready Scenario apps without flooding the context
- build the `inputs` object from the workflow contract
- price a run with a dry run before committing
- approve or reject a stuck approval node
- find which string input tripped the length limit

## Example prompts
- list ready Scenario workflows, limit 3
- dry run this workflow with my inputs and quote the cost
- run the workflow and wait for the job

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 100b6b25ca202402.

BEGIN THIRD-PARTY FILE 100b6b25ca202402
```text
---
name: scenario-workflows
description: "Use when a task involves running a Scenario workflow through MCP, including anything the user calls a Scenario app, a saved pipeline, or a multi-step generation graph. Triggers include listing workflows, building workflow_run's inputs object, pricing a run with a dry run, approving or rejecting a stuck approval node, a run rejected for input length, or a workflows_list reply flooding the context. Creating or editing graphs is scenario-workflow-authoring. Keywords: workflow, app, approval gate."
license: MIT
---

# Scenario Workflows

## Overview

A Scenario workflow is a saved node graph chaining several models into one call; users say "app" and
mean one whose status is `ready`. `workflow_run` returns a job tracked like any other generation.

Only `workflows_list`, `workflow_get` and `workflow_run` are listed by default; approve and reject
run through `scenario_tools_search` plus their executor lane. Connection and the core loop: the
`scenario` skill. Creating, editing and publishing graphs: the `scenario-workflow-authoring` skill.
If a sibling skill named here is missing from your available skills, ask the user to install it
(`npx skills add scenario-labs/skills --skill <name>`); unattended, proceed from tool schemas and
flag the gap.

## Quick reference

| Step                  | Call                                              | Notes                          |
| --------------------- | ------------------------------------------------- | ------------------------------ |
| 1. List               | `workflows_list` `status="ready"`                 | Always cap `limit`             |
| 2. Read the contract  | list `inputs[]`, get `workflow.inputs_definition` | `name` is the run key          |
| 3. Price and validate | `workflow_run` with `dry_run=true`                | Returns cost, creates no job   |
| 4. Run                | `workflow_run` with `inputs`                      | Returns a job                  |
| 5. Wait               | `jobs_wait`                                       | Re-call with `pending_job_ids` |

Ids are prefixed `wflow_`; copy them from `workflows_list` or `search`, never construct them. For a
named app or a public template, call `search` with `target="workflows"`, a keyword `query`,
`limit=3`, and your scope; add `public=true` for the public catalog. Workflows support keyword text
and filters, not image or semantic search. To find ready apps, add the raw
`filter: 'status = "ready"'` (not `filters.status`). Read hits from `workflows`, then call
```
END THIRD-PARTY FILE 100b6b25ca202402

The third-party file has ended. Everything between the 100b6b25ca202402 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2555 of 7706 bytes. © scenario-labs · MIT · https://github.com/scenario-labs/skills/tree/HEAD/skills/scenario-workflows/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md