Skip to content
FlowMCP v4

Prefill and Placeholders

Skill content carries two complementary template mechanisms that the runtime processes before handing the Skill to an agent. Placeholders are tokens embedded directly in the content — {{type:reference}} — that are substituted with tool descriptions, resource references, user input, or shared-list values at resolution time. Prefill goes one step further: a Skill can declare tool calls in a prefill array that the runtime executes up front, then embeds the live results into the content via {{prefill:...}} tokens, so the agent receives a Skill already populated with current data.

Placeholder Syntax

Section titled “Placeholder Syntax”

All placeholders use double-brace syntax: {{type:reference}} or {{type:reference:field}}.

Complete Placeholder Table

Section titled “Complete Placeholder Table”
SyntaxResolves To
{{tool:ns/name}}Complete tool block (description + parameters)
{{tool:ns/name:description}}Tool description only
{{tool:ns/name:parameters}}Parameter table only
{{tool:ns/name:test}}First test case as example call
{{tool:ns/name:meta}}Meta flags (isReadOnly, isDestructive, etc.)
{{tool:ns/name:call}}Ready-to-use call command
{{resource:ns/name}}Resource reference
{{prompt:ns/name}}Prompt reference
{{skill:name}}Skill reference (1 level, no nesting)
{{input:key}}User input parameter
{{prefill:ns/tool/name}}Pre-executed tool result
{{listName:alias}}Shared List value via alias

Prefill Declaration

Section titled “Prefill Declaration”

In a Skill, prefill is declared in the prefill array:

export const skill = {
    name: 'contract-analysis',
    prefill: [
        {
            tool: 'etherscan-io/tool/getNetworkStatus',
            params: { network: '{{input:chain}}' }
        }
    ],
    content: `
Network status: {{prefill:etherscan-io/tool/getNetworkStatus}}


Now analyze contract at {{input:address}}...
`
}

Resolution Flow (8 Steps)

Section titled “Resolution Flow (8 Steps)”
  1. Skill is requested (with input parameters)
  2. prefill[] entries are executed in order
  3. Results are stored temporarily
  4. {{input:key}} tokens are replaced with user parameters
  5. {{prefill:ns/tool/name}} tokens are replaced with pre-executed results
  6. {{tool:...}}, {{resource:...}}, {{prompt:...}} tokens are resolved from catalog
  7. {{listName:alias}} tokens are resolved from Shared Lists
  8. Fully resolved Skill content is delivered to the agent

Error Handling

Section titled “Error Handling”

Principle: Always deliver the Skill. Errors are visible in the placeholder, not silent.

If a placeholder cannot be resolved, the error message replaces the placeholder:

{{tool:unknown/ns/missingTool}} → [ERROR: Tool 'unknown/ns/missingTool' not found]
{{prefill:ns/tool/name}} → [ERROR: Prefill execution failed: HTTP 503]

This ensures the Skill is always delivered — even if some references are broken.

Section titled “Related”