Messages and reusable prompts
For questions about message variants, reusable prompts, variable substitution, or channel behavior
that this skill does not answer, follow the
docs MCP workflow before answering
or implementing. For every new Voiceflow troubleshooting issue, consult it even
when this skill suggests a fix. Include package/skill/stage context in why as
described there. Reuse guidance for the same issue; consult it whenever unsure.
Read the operation contract. Distinguish literal message content, a reusable prompt resource, an agent's instructions, and a workflow step that references one of these.
Read the resource and its consumers before replacing it. Shared text changes can affect multiple paths. Preserve variants, variable bindings, channel-specific content, and unrelated fields.
Use current message/prompt operation schemas. Do not guess whether a step expects raw text, a message ID, or a prompt ID. Create dependencies first and attach the returned ID. For a local edit, prefer a supported targeted update.
Keep generated-answer instructions separate from exact text the agent should say. Check variable references and behavior when values are missing. Voice text should sound natural aloud; chat may include formatting inappropriate for speech.
Read back the referenced resource and owning step/tool after changes. Verify the intended path uses the edited resource, rather than creating an unused duplicate and claiming the user-facing text changed.
Source: Instructions.
Skill metadata
--- name: voiceflow-messages description: Create or edit reusable Voiceflow messages, prompts, and text referenced by workflow steps or tool messages. license: MIT ---