scenario-workflow-authoring
Original:🇺🇸 English
Translated
1 scriptsChecked / no sensitive code detected
Use when a task involves creating or editing a Scenario workflow graph through MCP: building an app from a brief, adding or rewiring nodes (models, prompts, approval gates, loops), authoring editor_info, publishing, unpublishing or renaming, importing an exported workflow JSON, migrating a graph built in Weavy, ComfyUI, or another node tool, copying a workflow, or turning a prompt chain into an app. Running or pricing a workflow is scenario-workflows. Keywords: node graph, editor_info, CEL.
27installs
Sourcescenario-labs/skills
Added on
NPX Install
npx skill4agent add scenario-labs/skills scenario-workflow-authoringTags
Translated version includes tags in frontmatterSKILL.md Content
View Translation Comparison →Scenario Workflow Authoring
Overview
A workflow has two representations: (the editable node graph: , , ) and (the compiled runnable form). Authoring through MCP means writing the whole document: there are no per-node editing tools; every change is a read, modify, write of the full graph through or . Never hand-write : compiles into it and flips status to . Editing a ready workflow's leaves the stale running until you publish again.
editor_infonodesedgesinputKeysfloweditor_infoworkflow_createworkflow_updateflowworkflow_publisheditor_inforeadyeditor_infoflowRead references/editor-info.md before writing any graph: it holds the node type vocabulary, the node choice doctrine (when an node is legitimate), the edge direction rule, per-node data contracts, and a validated minimal example. Create, update, publish, copy and delete live in the tool catalog ( plus the matching executor, see the skill). , and are direct tools: scope and go in their top-level arguments, never an executor wrapper. Running and pricing: the skill. If a sibling skill named here is missing from your available skills, ask the user to install it (); unattended, proceed from tool schemas and flag the gap.
llmscenario_tools_searchscenarioworkflows_listworkflow_getworkflow_rundry_runscenario-workflowsnpx skills add scenario-labs/skills --skill <name>Quick reference
| Step | Call | Notes |
|---|---|---|
| 1. Study a graph | | Copy the shape, never ids |
| 2. Model contract | | Handle names and required inputs |
| 3. Author | | Per the reference file |
| 4. Create | | Non-atomic, see below |
| 5. Publish | | Compiles |
| 6. Validate | | Prices and runs the real validator |
workflow_createworkflow_updateworkflow_getworkflows_listsearchtarget="workflows"public=truequerylimit=3query="image"filter: 'status = "ready"'workflowsworkflow_getworkflows_listWorked example: a text-to-image app
- with
recommendand the user's brief ascapability: "txt2img", following thepromptskill'sscenariodiscipline, thennext_step: its input names become the model node's handle names, and itsmodel_schema_getflag marks what must be wired. Userequiredinstead when the user names a model.search - Author :
editor_infowithtext1,data.isInput: truewithmodel1,type: "model"anddata.modelId, one edge fromdata.isOutput: true's input tomodel1's output (edges name the downstream node astext1, see the reference),source.inputKeys: ["text1"] - with
workflow_create,name, andeditor_infonaminginputs_definitionas a string input. The published input key is the node id, which is why run inputs have names liketext1.text1 - , then
workflow_publishwithworkflow_runto validate and price. Fix the graph and re-publish if validation fails.dry_run=true
Migrating a graph from another node tool
A pipeline exported by Weavy, ComfyUI, or another node editor does not import: only Scenario's own export round-trips. It is translated node by node, then created, published, and dry-run as above. The mapping table, member resolution, and the report the user gets are in references/foreign-graph-import.md; read it before touching such an export, since its first rule is to reduce the file to a table locally rather than paste it into the conversation.
Common mistakes
- Writing UI palette names as node types: persisted types are the camelCase vocabulary in the reference, and every generator is .
type: "model" - Wiring edges producer to consumer: persisted edges point the other way.
- Expecting an update to change a live app without re-publishing.
editor_info - Retrying a failed with a second create instead of
workflow_createon the id from the error.workflow_update - Publishing with no pins: at least one node listed in
data.isInputand oneinputKeysnode.data.isOutput - Gating a text node in front of a builder or model: a branch skips only the node wired to its handle, so the consumer stays pending and the job never completes. Gate the node that does the work, or use a CEL ternary for conditional prompt text, per the reference's section.
ifElse - Double-quoted CEL literals: they evaluate but corrupt the canvas editor, single quotes only.
- Sending to
workflow_id: get, update, publish, run and delete takeworkflow_copy, but copy takesworkflow_id; the copy inherits everything verbatim and needs its own publish.source_workflow_id