Frontmatter Extractor

text.extract_frontmatter

ProductionBounded custom (Class B)Deterministicstrictfastv1.0.0

No network

Overview

Detects and parses frontmatter at the start of a Markdown document (YAML '---', TOML '+++', or a leading JSON object). Returns parsed metadata, format, offsets, and the remaining body. Parsers run in safe mode with a bounded frontmatter size.

Markdown metadata lives in frontmatter blocks. We parse the leading fence safely so you get structured fields without hallucinated structure.

Reliability

STRICT and deterministic — identical markdown and options always produce the same result. Parsers run in safe mode with a 256 KB frontmatter cap, and TOML support covers the frontmatter subset — top-level pairs, single-level [table] headers, and scalar arrays — reporting anything else in warnings. An opening fence with no matching close is treated as ordinary Markdown, so you get found: false rather than an error. Input validation (not retryable): a formats array with none of yaml, toml, json; frontmatter we cannot parse; frontmatter over 256 KB; markdown over 2,000,000 characters.

Context footprint

Bounded input (2 MB) and frontmatter (256 KB); parses only the leading block at the document start. A successful call costs 1 execution credit.

When to use it

When you need the metadata block at the top of a Markdown document, with optional raw block and body separation.

Do not use when metadata is embedded in the body or you need full Markdown AST parsing.

Scope

Note

Extracts and parses YAML, TOML, or JSON frontmatter at the start of your Markdown document, returning parsed metadata, format, character offsets, and body.

Non-goals

Does not parse Markdown body structure (headings, lists, links)
Does not detect frontmatter after headings or mid-document blocks
Does not resolve custom YAML tags into Java types

Properties

IdempotentRetry safeStreaming supportedFile input supportedRequires external service

Capabilities

parsingtext-processing

Cost & billing

Flat rate per invocation

MetercallsBillable onsuccessCost per call1 credit

File handling

Accepts file_refProduces file_refMax input1.9 MB

How we handle your data

Sensitive input, safe output

What this means

This skill may receive sensitive content, but it does not target sensitive data and returns only a structured non-sensitive result.

Squillify guarantees

Runs inside Squillify
This skill runs inside Squillify.
Payloads are not sent to an external service by this skill.
Squillify does not permanently store submitted payloads.
Telemetry records metadata only, not submitted content.
Submitted payloads are not used for training.
Submitted payloads are not reviewed by humans.
This skill does not target sensitive data.
The response does not contain submitted content.

Your responsibility

Squillify does not determine whether submitted content is sensitive. Your application is responsible for deciding what data it is allowed to submit. Your application is responsible for securing the response.

Read the Microskill Data Handling Policy

Input schema

Field	Type	Required	Description
markdown	string	Yes	Markdown document whose leading metadata block is inspected.
formats	array	No	Bounded optional format array; omit it to try JSON, YAML, and TOML in the documented order. The item shape is defined by the nested schema and the array contains from 0 through 3 items.
includeBody	boolean	No	Whether the body is returned; omit it for true.
includeRaw	boolean	No	Whether the raw block is returned; omit it for false.
parseValues	boolean	No	Whether metadata values are parsed; omit it for true.

Output schema

Field	Type	Required	Description
found	boolean	Yes	Whether a leading metadata block was found.
format	string	No	Detected frontmatter format.
data	object	No	Purpose-bound parsed frontmatter object; keys and JSON-compatible values come from the document. Its purpose-bound receipt properties are bounded to 64 entries — unconstrained RFC 8259 JSON items.
raw	string	No	Exact frontmatter source block including fences.
body	string	No	Unmodified Markdown body after the metadata block.
startChar	integer	No	Zero-based metadata start offset.
endChar	integer	No	Zero-based body start offset.
warnings	array	Yes	Bounded warning array containing from 0 through 10000 items, where each item is one non-fatal advisory string.

API contract

POST /v1/execute

curl

curl -sS -X POST "$BASE/v1/execute" -H "Authorization: Bearer $KEY" -H 'Content-Type: application/json' -d '{"skillKey":"text.extract_frontmatter","input":{"markdown":"---\ntitle: Hello\n---\n# Body"}}'

Integrations

TypeScript SDK

import { Squillify } from "@squillify/sdk";

const sq = new Squillify({ apiKey: process.env.SQUILLIFY_API_KEY });

const { output } = await sq.execute("text.extract_frontmatter", {"markdown":"---\ntitle: Hello\n---\n# Body\n"});

Errors

Code	HTTP	Retryable	Description
VALIDATION_ERROR	400	No	The request payload failed schema validation.
UNAUTHORIZED	401	No	Missing or invalid API key.
SKILL_NOT_ACCESSIBLE	403	No	The API key is not granted access to this skill.
SKILL_NOT_AVAILABLE_FOR_PLAN	403	No	This skill is not included in your current plan.
PLAN_ELIGIBILITY_UNAVAILABLE	503	Yes	Plan eligibility could not be decided. Retry after backoff.
SKILL_NOT_FOUND	404	No	The requested skill or version does not exist.
TENANT_RATE_LIMITED	429	Yes	Request rate limit exceeded. Retry after backoff.
QUOTA_EXCEEDED	429	Yes	Plan quota exhausted. Retryable once the quota period resets.
EXECUTION_TIMEOUT	504	Yes	Execution exceeded the allowed time budget.

Other limits

Limit	Value
Recommended inline bytes	32 KiB

Limitations

Does not parse Markdown body structure (headings, lists, links)
Does not detect frontmatter after headings or mid-document blocks
Does not resolve custom YAML tags into Java types
Full Markdown AST parsing
Metadata blocks not at the document start
Inline metadata in the body rather than a leading frontmatter fence

How to call

POST /v1/execute (requires authentication)

Request bodyjson

{
  "skillKey": "text.extract_frontmatter",
  "input": {
    "markdown": "---\ntitle: Hello\n---\n# Body\n"
  }
}

Examples

YAML frontmatter with body

Inputjson

{
  "markdown": "---\ntitle: Hello\n---\n# Body\n"
}

Expected outputjson

{
  "startChar": 0,
  "warnings": [],
  "endChar": 21,
  "data": {
    "title": "Hello"
  },
  "found": true,
  "format": "yaml",
  "body": "# Body\n"
}

Document without frontmatter