/dramaclaw-workflows

name: dramaclaw-workflows
description: Create, revise, confirm, run, or resume multi-node DramaClaw Freezone canvas workflows. Use for requests involving a workflow, several connected nodes, grouped production stages, storyboards, or text/image/video/audio pipelines; do not use for one standalone canvas operation or for 预演台/previz scene blocking (edit a previzNode instead).

DramaClaw Workflows

Build one coherent workflow transaction, not a sequence of standalone canvas edits.

Required behavior

• For interactive short dramas, branching stories, choices or multiple endings, route story structure to the `interactive-story` Skill and its dedicated tools first. This workflow Skill applies only to the requested media production. For new character, product, scene or storyboard reference images in an approved production plan, use the existing `text-to-image-video` catalog Skill with `general-image` in one image-only WorkflowPlan; keep existing story video nodes outside that Plan and connect images after its run finishes. Never replace an unavailable story tool with ordinary canvas commands or a WorkflowPlan.
• Planning authors topology, Recipe selection, dependencies, confirmed parameters, and short

node task briefs. Each node prompt should state its task, scope, upstream outputs, and reference roles in one or two concise sentences. Preserve user-provided story facts and source material. In a compact Intent, keep every user-confirmed quantity, named object, exclusion, and visual continuity anchor in `user_goal`; `planner.units` may distribute steps but must not replace those shared facts with a short summary. Do not invent details the user did not provide. Carry a confirmed visual style into each image/video task brief, or supply it through an actual consumed upstream text output; a Skill title or an unrelated node does not carry that style into a media node by itself. When a video consumes upstream images through `media_input_for`, select a reference-capable generation mode supported by its chosen Catalog model and reference count. Do not leave the mode unset or use `textToVideo`; an edge alone cannot make a text-only mode consume images. If no compatible mode is available, stop on the catalog/preflight blocker instead of dropping the media input or silently changing an explicit user choice. Do not invent finished scripts, detailed shot-by-shot storyboards, dialogue, camera choreography, sound cues, or final media prompts before upstream stages execute. A concrete action brief explicitly required by the selected Skill for Draft review is a planning constraint: author it now, with enough short sentences to specify the actions; do not defer it as a future instruction. Execution-time Recipe compilation uses actual upstream outputs to produce executable prompts.

• Read this Skill and its references only through the exact locator advertised by the current host.

Never invent `project://` paths. Use a canvas summary already supplied by the host; if current canvas data must be refreshed, call `freezone_get_canvas_ontology` instead of inventing a `canvas://` resource. MCP clients must use only resource URIs returned by `resources/list` or `resources/templates/list`. The Workflow MCP intentionally returns an empty static `resources/list`; this is supported and does not mean the catalog is unavailable. Discover accessible Skill/Recipe IDs with `workflow_catalog_search`, then use the advertised templates for resource reads. Do not enumerate or guess another user's private catalog IDs.

• The Skill package/server display name does not determine a host's MCP registration key. Use the

exact `server` returned by the host. In DramaClaw's Codex adapter, filesystem-backed Skill files are read from `dramaclaw`; workflow catalog resources use `dramaclaw_workflows` (underscore). Never call `resources/read` with an inferred `dramaclaw-workflows` server key.

• Use the portable `dramaclaw-workflows` MCP server for catalog discovery and deterministic

compilation when it is available. Use the authorized DramaClaw MCP server for draft persistence, approval, canvas commit, and execution. Tool names are host-neutral; call them through the MCP mechanism supported by the current agent.

• `dramaclaw-workflows` is this Agent Skill package/server name, not a Workflow catalog `skill_id`.

Never pass it to `workflow_skill_get`, `freezone_get_workflow_skill`, or an intent's `skill_id`. Select the matching production Workflow Skill returned by the catalog instead.

• Route an ordinary pure-image workflow to `text-to-image`. Use `text-to-image-video` only when

the user asks for a video stage, and use `social-content-campaign` only for an explicit social platform image-set request. Do not report a Skill conflict or ask the user to accept video merely because the older general video Skill also contains an image stage.

• Never implement a multi-node request by repeatedly calling `freezone_create_node`,

`freezone_create_edge`, `freezone_group_nodes`, or other single-operation tools.

• Never fall back to repeated single-operation writes after a workflow validation or schema error.

Correct the workflow intent/plan or report the blocking error.

• Follow the selected Skill's current planning contract. A request for a finished result does not authorize collapsing required stages or marking prerequisites complete. When the requested operation cannot run yet, explain the missing prerequisite in creation terms and guide the user to the next supported step. Agent-authored schema/topology errors are the Agent's responsibility to correct, not user mistakes; never ask the user to design internal nodes or links.
• Never offer direct canvas commands or standalone node writes as a clarification choice for

bypassing WorkflowPlan validation. A user selection cannot authorize that bypass. When a Skill's required stage conflicts with an exact node-only constrai