Markdown Inspector

markdown.inspect

ProductionBounded custom (Class B)Deterministicstrictfastv1.0.0

File inputNo network

Overview

You select structural sections and receive deterministic headings, canonical IDs, links, images, code, tables, tasks, footnotes, math, frontmatter, callouts, statistics, and parser dependencies. The skill parses once, reports exact total and returned counts, and never fetches or renders remote content. Accepts file input via file_ref — no need to extract file content first.

Agents need bounded machine-readable structure without parsing HTML or combining several unrelated focused skills.

Reliability

STRICT at a fixed profile version. MARKDOWN_PROFILE_UNSUPPORTED means the profile name is unknown and requires choosing commonmark, gfm, or squillify-safe; MARKDOWN_INVALID_ENCODING means a file is not strict UTF-8 and requires re-encoding before retrying; MARKDOWN_COMPLEXITY_LIMIT means the fixed node, depth, or math-expression cap was exceeded and requires splitting or simplifying the document. Collection sections always report exact total and returned counts.

Context footprint

Input uses the shared Markdown file, node, and depth caps. Collection sections default to 1000 retained items and cap at 5000; together they also share a 1500000-byte pessimistic JSON budget. Metadata titles cap at 8192 UTF-8 bytes. A successful call costs 1 execution credit.

When to use it

When you need a deterministic whole-document inventory or statistics.

When one focused extraction or rendered output is sufficient.

Scope

Note

Reports selected structure and statistics from one Markdown document.

Non-goals

Does not render or rewrite Markdown
Does not test remote availability
Does not semantically validate TeX
Does not replace focused extraction skills

Properties

IdempotentRetry safeStreaming supportedFile input supportedRequires external service

Capabilities

analysisdocument-processingparsing

Cost & billing

Flat rate per invocation

MetercallsBillable onsuccessCost per call1 credit

File handling

Accepts file_refProduces file_refMax input2 MBMax file size2 MB

File limits

Constraints this skill applies to your input and generated files. The “Limited by” column shows the static source of each cap; none of these can be raised by upgrading your plan.

Limit	Value	Limited by
Maximum size per input file	2 MiB	Skill maximum

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 using a self-contained open-source component
This skill runs inside Squillify.
Payloads are not sent to an external service by this skill.
Self contained open source component
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.
Output may reveal sensitive derived information

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	No	Inline Markdown up to 1048576 characters. Omit only when file_ref is present. If both are present, file_ref wins and _meta._input_conflict_resolved reports it.
file_ref	string	No	Tenant-scoped strict-UTF-8 Markdown file up to 2097152 bytes. When omitted, the inline markdown field is used.
profile	string	No	commonmark, gfm, or squillify-safe; defaults to squillify-safe.
include	array	No	Unique closed selectors in any order: [metadata, headings, links, images, code, tables, tasks, footnotes, math, diagrams, frontmatter, callouts, statistics, dependencies]. The response always uses canonical section order. When omitted, defaults to metadata, headings, links, images, and statistics.
limits	object	No	Optional timeoutMs and maxItemsPerSection (1..5000). Defaults are timeoutMs=5000 and maxItemsPerSection=1000. Unknown properties are rejected.

Output schema

Field	Type	Required	Description
metadata	object	No	Optional bounded title, titleTruncated flag, profile and first-seen feature list; omit it when metadata was not requested.
headings	object	No	When requested: closed {total, returned, items} where each item is {level, text, id, range}.
links	object	No	When requested: closed {total, returned, items} where each item is {text, destination, title, range}.
images	object	No	When requested: closed {total, returned, items} where each item is {alt, destination, title, range}.
code	object	No	When requested: closed {total, returned, items} where each item is {kind, language, text, range}.
tables	object	No	When requested: closed {total, returned, items} where each item is {columns, rows, range}.
tasks	object	No	When requested: closed {total, returned, items} where each item is {checked, text, range}.
footnotes	object	No	When requested: closed {total, returned, items} where each item is {kind, label, text, range}.
math	object	No	When requested: closed {total, returned, items} where each item is {kind, tex, range}.
diagrams	object	No	When requested: closed {total, returned, items} where each item is {language, source, range}.
frontmatter	object	No	When requested: closed {total, returned, items} where each item is {key, values, range}.
callouts	object	No	When requested: closed {total, returned, items} where each item is {kind, title, text, range}.
statistics	object	No	When requested: closed whole-document counts for codePoints, utf8Bytes, lines, words, nodes and maxDepth covering the complete normalized document.
dependencies	object	No	When requested: closed {total, returned, items} where each item is {name, version} in parser-then-extension order.
_meta	object	Yes	Closed parser identity, normalized input facts and exact truncation sections for this inspection.

API contract

POST /v1/execute

curl

curl -sS -X POST "$BASE/v1/execute" -H "Authorization: Bearer $KEY" -H 'Content-Type: application/json' -d '{"skillKey":"markdown.inspect","input":{"markdown":"# Plan\n\n- [ ] Ship","include":["headings","tasks","statistics"]}}'

Integrations

TypeScript SDK

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

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

const { output } = await sq.execute("markdown.inspect", {"markdown":"# Plan\n\n- [ ] Ship","include":["headings","tasks","statistics"]});

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.
MARKDOWN_PROFILE_UNSUPPORTED	400	No	The request payload failed this skill's input validation.
MARKDOWN_INVALID_ENCODING	400	No	The request payload failed this skill's input validation.
MARKDOWN_COMPLEXITY_LIMIT	429	No	A size, quota, rate, or time limit was exceeded.

Other limits

Limit	Value
Recommended inline bytes	32 KiB

Limitations

Does not render or rewrite Markdown
Does not test remote availability
Does not semantically validate TeX
Does not replace focused extraction skills
Remote link checking
HTML rendering
Content repair
Open-ended summarization

How to call

POST /v1/execute (requires authentication)

Request bodyjson

{
  "skillKey": "markdown.inspect",
  "input": {
    "markdown": "# Plan\n\n- [ ] Ship",
    "include": [
      "headings",
      "tasks",
      "statistics"
    ]
  }
}

Examples

Inspect a heading and task

Inputjson

{
  "markdown": "# Plan\n\n- [ ] Ship",
  "include": [
    "headings",
    "tasks",
    "statistics"
  ]
}

Expected outputjson

{
  "_meta": {
    "profileVersion": "1",
    "inputChars": 18,
    "parserVersion": "0.24.0",
    "truncated": false,
    "truncatedSections": [],
    "nodeCount": 7,
    "bomStripped": false,
    "lineEndingsNormalized": false,
    "profile": "squillify-safe",
    "inputBytes": 18,
    "parser": "commonmark"
  },
  "tasks": {
    "items": [
      {
        "checked": false,
        "text": "Ship",
        "range": {
          "start": {
            "line": 3,
            "offset": 8,
            "column": 1
          },
          "end": {
            "line": 3,
            "offset": 18,
            "column": 11
          }
        }
      }
    ],
    "returned": 1,
    "total": 1
  },
  "headings": {
    "items": [
      {
        "level": 1,
        "text": "Plan",
        "range": {
          "start": {
            "line": 1,
            "offset": 0,
            "column": 1
          },
          "end": {
            "line": 1,
            "offset": 6,
            "column": 7
          }
        },
        "id": "plan"
      }
    ],
    "returned": 1,
    "total": 1
  },
  "statistics": {
    "utf8Bytes": 18,
    "codePoints": 18,
    "nodes": 7,
    "lines": 3,
    "words": 2,
    "maxDepth": 4
  }
}

Inspect only parser dependencies