Table From Markdown

text.table_from_markdown

ProductionBounded custom (Class B)Deterministicverifiablefastv1.0.0

No network

Overview

Extracts Markdown pipe tables into structured data: returns header/row arrays, alignment markers, and object rows keyed by unique headers, with optional source offsets. Honors escaped pipes, ignores tables inside fenced code blocks, and never renders HTML or fetches links.

Agents receive tables as Markdown — we turn pipe tables into JSON-ready structures so downstream skills can consume them.

Reliability

VERIFIABLE and deterministic — identical markdown and options always yield the same tables. Tables inside fenced code blocks are ignored, an escaped \| stays part of its cell, and every value comes back as a string — we never guess numbers or dates. Input validation (not retryable): a flavor outside the two listed values; a negative tableIndex; maxTables outside 1 to 100; markdown missing, not a string, or longer than 1,048,576 characters.

Context footprint

Returns compact structured tables. A successful call costs 1 execution credit.

When to use it

When you need tabular data from a Markdown document for ingestion or analysis.

Do not use for HTML rendering, non-pipe table formats, or fetching linked URLs.

Scope

Note

We extract GitHub Flavored Markdown pipe tables from your document into structured headers, rows, alignment markers, and object rows keyed by column name.

Non-goals

Does not render HTML
Does not fetch links
Does not parse non-pipe tables

Properties

IdempotentRetry safeStreaming supportedFile input supportedRequires external service

Capabilities

data-transformationparsing

Cost & billing

Flat rate per invocation

MetercallsBillable onsuccessCost per call1 credit

File handling

Accepts file_refProduces file_refMax input1 MB

How we handle your data

Sensitive output possible

What this means

This skill may receive sensitive content and may return submitted, transformed, extracted, or reformatted content.

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 may contain submitted or transformed 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 pipe tables are extracted.
flavor	string	No	Table grammar label; omit it for gfm.
tableIndex	integer	No	Optional zero-based table index; omit it to return every table.
includeSourceOffsets	boolean	No	Whether source offsets are returned; omit it for true.
trimCells	boolean	No	Whether cell padding is trimmed; omit it for true.
maxTables	integer	No	Table cap; omit it for twenty.

Output schema

Field	Type	Required	Description
tables	array	Yes	Bounded array of table receipts in document order with headers, alignments, rows, objects, and offsets. The item shape is defined by the nested schema and the array contains from 0 through 100 items.
warnings	array	Yes	Bounded array of non-fatal table warnings with code and message properties. The item shape is defined by the nested schema and the array contains from 0 through 101 items.

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.table_from_markdown","input":{"markdown":"| a | b |\n|---|---|\n| 1 | 2 |"}}'

Integrations

TypeScript SDK

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

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

const { output } = await sq.execute("text.table_from_markdown", {"markdown":"| region | revenue |\n|:---|---:|\n| EMEA | 4200 |"});

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 render HTML
Does not fetch links
Does not parse non-pipe tables
Rendering Markdown to HTML

How to call

POST /v1/execute (requires authentication)

Request bodyjson

{
  "skillKey": "text.table_from_markdown",
  "input": {
    "markdown": "| region | revenue |\n|:---|---:|\n| EMEA | 4200 |"
  }
}

Examples

Extract a simple table

Inputjson

{
  "markdown": "| region | revenue |\n|:---|---:|\n| EMEA | 4200 |"
}

Expected outputjson

{
  "warnings": [],
  "tables": [
    {
      "objects": [
        {
          "region": "EMEA",
          "revenue": "4200"
        }
      ],
      "rows": [
        [
          "EMEA",
          "4200"
        ]
      ],
      "sourceEndOffset": 48,
      "alignments": [
        "left",
        "right"
      ],
      "headers": [
        "region",
        "revenue"
      ],
      "sourceStartOffset": 0
    }
  ]
}

Tip

Alignment colons in the delimiter row come back as left, right, or center; every cell stays a string

Extract one table by index