Markdown Citation Renderer
markdown.render_citations
Overview
You send Markdown plus canonical CSL-JSON items. The skill recognizes a documented citation subset, formats it with a closed six-style catalog, sanitizes all generated HTML, and returns unresolved keys without fetching anything. It does not accept custom styles, BibTeX, RIS, DOI lookup, or arbitrary URLs. Accepts file input via file_ref — no need to extract file content first.
Citation formatting and bibliography ordering are easy to get subtly wrong; this skill gives agents one bounded, versioned contract.
Reliability
STRICT for the pinned parser, citeproc-java 3.5.0, closed style catalog, locale, and sanitizer. Failures include CITATION_BIBLIOGRAPHY_INVALID, CITATION_KEY_UNRESOLVED, CITATION_STYLE_UNSUPPORTED, CITATION_LOCALE_UNSUPPORTED, MARKDOWN_INVALID_ENCODING, MARKDOWN_COMPLEXITY_LIMIT, and OUTPUT_LIMIT_EXCEEDED.
Context footprint
At most 1000 bibliography items, 2000 citation occurrences, 16384 UTF-8 bytes per free-text field, and 1000000 output bytes. A successful call costs 2 execution credits.
When to use it
When Markdown contains the documented @key citation subset and all CSL-JSON items are already available.
When a custom style, remote lookup, or full Pandoc citation grammar is required.
Powered by citeproc-java 3.5.0 and Squillify's canonical Markdown parser.
Scope
Non-goals
- No arbitrary CSL styles
- No BibTeX or RIS import
- No DOI lookup
- No network access
- No figure or table numbering
Properties
Capabilities
Cost & billing
Flat rate per invocation
File handling
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 | 488.3 KiB | Skill maximum |
How we handle your data
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.
- 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.
Input schema
| Field | Type | Required | Description |
|---|---|---|---|
| markdown | string | No | Inline Markdown up to 200000 characters. Required unless file_ref is present; 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 500000 bytes. When omitted, the inline markdown field is used. |
| profile | string | No | commonmark, gfm, or squillify-safe; defaults to squillify-safe. |
| theme | string | No | squillify (default), none, light, dark, or auto. The default embeds the frozen Squillify Design System presentation. |
| includeCss | boolean | No | Embed the selected scoped Markdown stylesheet; defaults to true. Set false when the host page already provides it. |
| bibliography | object | Yes | Required {type:'csl_json',items:[...]}; at most 1000 bounded items with unique ids. |
| style | string | No | One of apa-7, chicago-author-date, harvard, mla-9, ieee, or nature; defaults to apa-7. |
| locale | string | No | Closed locale identifier; version 1 supports en-US only and defaults to en-US. |
| outputFormat | string | No | Only html is supported in version 1; defaults to html. |
| includeBibliography | boolean | No | Include formatted bibliography entries; defaults to true. |
| errorPolicy | string | No | report (default) preserves unresolved syntax with warnings; fail rejects the first unresolved key. |
Output schema
| Field | Type | Required | Description |
|---|---|---|---|
| renderedContent | string | Yes | Sanitized rendered Markdown HTML. |
| bibliography | array | Yes | From 0 through 1,000 closed {id, html} bibliography entry objects in style order. |
| unresolvedKeys | array | Yes | From 0 through 1,000 unresolved citation-key strings in encounter order. |
| warnings | array | Yes | From 0 through 1,000 closed unresolved-citation warning objects. |
| _meta | object | Yes | Closed receipt containing parser, style, locale, sanitization, and citation-engine provenance. |
API contract
POST /v1/executecurl -sS -X POST "$BASE/v1/execute" -H "Authorization: Bearer $KEY" -H 'Content-Type: application/json' -d '{"skillKey":"markdown.render_citations","input":{"markdown":"Claim [@doe2024].","bibliography":{"type":"csl_json","items":[{"id":"doe2024","type":"article-journal","title":"Example"}]}}}'import { Squillify } from "@squillify/sdk";
const sq = new Squillify({ apiKey: process.env.SQUILLIFY_API_KEY });
const { output } = await sq.execute("markdown.render_citations", {"includeCss":false,"bibliography":{"type":"csl_json","items":[{"id":"doe2024","title":"Example","issued":{"date-parts":[[2024]]},"type":"article-journal","author":[{"family":"Doe","given":"Jane"}]}]},"markdown":"Claim [@doe2024]."});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. |
| CITATION_BIBLIOGRAPHY_INVALID | 400 | No | The request payload failed this skill's input validation. |
| CITATION_KEY_UNRESOLVED | 400 | No | The request payload failed this skill's input validation. |
| CITATION_STYLE_UNSUPPORTED | 400 | No | The request payload failed this skill's input validation. |
| CITATION_LOCALE_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
- No arbitrary CSL styles
- No BibTeX or RIS import
- No DOI lookup
- No network access
- No figure or table numbering
- Pandoc compatibility
- Remote bibliography lookup
- Custom institutional styles
How to call
POST /v1/execute (requires authentication)
{
"skillKey": "markdown.render_citations",
"input": {
"includeCss": false,
"bibliography": {
"type": "csl_json",
"items": [
{
"id": "doe2024",
"title": "Example",
"issued": {
"date-parts": [
[
2024
]
]
},
"type": "article-journal",
"author": [
{
"family": "Doe",
"given": "Jane"
}
]
}
]
},
"markdown": "Claim [@doe2024]."
}
}Examples
Render one author-date citation
{
"includeCss": false,
"bibliography": {
"type": "csl_json",
"items": [
{
"id": "doe2024",
"title": "Example",
"issued": {
"date-parts": [
[
2024
]
]
},
"type": "article-journal",
"author": [
{
"family": "Doe",
"given": "Jane"
}
]
}
]
},
"markdown": "Claim [@doe2024]."
}{
"warnings": [],
"renderedContent": "<article class=\"sqfy-markdown sqfy-markdown-v2 sqfy-theme-squillify sqfy-markdown-citations\"><p>Claim <span class=\"sqfy-citation\">(Doe, 2024)</span>.</p></article>",
"_meta": {
"inputBytes": 31,
"style": "apa-7",
"theme": "squillify",
"cssIncluded": false,
"sanitized": true,
"profileVersion": "1",
"parser": "commonmark",
"parserVersion": "0.24.0",
"inputChars": 31,
"nodeCount": 2,
"styleDigest": "sha256:1ece4fb3c295e66d04b4394e295aa58a87741ceeef1658192437eb9953c2f13e",
"themeVersion": "sqfy-markdown-v2",
"profile": "squillify-safe",
"truncated": false,
"_input_conflict_resolved": false,
"locale": "en-US",
"citationEngineVersion": "3.5.0",
"citationEngine": "citeproc-java"
},
"bibliography": [
{
"id": "doe2024",
"html": " <div class=\"csl-entry\">Doe, J. (2024). <span>Example</span>.</div>\n"
}
],
"unresolvedKeys": []
}Report an unresolved key
{
"includeBibliography": false,
"markdown": "Claim [@missing].",
"bibliography": {
"type": "csl_json",
"items": []
},
"includeCss": false
}{
"warnings": [
{
"code": "CITATION_KEY_UNRESOLVED",
"key": "missing",
"message": "Citation key is not present in the bibliography"
}
],
"renderedContent": "<article class=\"sqfy-markdown sqfy-markdown-v2 sqfy-theme-squillify sqfy-markdown-citations\"><p>Claim <span class=\"sqfy-citation\">[@missing]</span>.</p></article>",
"_meta": {
"inputBytes": 31,
"style": "apa-7",
"theme": "squillify",
"cssIncluded": false,
"sanitized": true,
"profileVersion": "1",
"parser": "commonmark",
"parserVersion": "0.24.0",
"inputChars": 31,
"nodeCount": 2,
"styleDigest": "sha256:1ece4fb3c295e66d04b4394e295aa58a87741ceeef1658192437eb9953c2f13e",
"themeVersion": "sqfy-markdown-v2",
"profile": "squillify-safe",
"truncated": false,
"_input_conflict_resolved": false,
"locale": "en-US",
"citationEngineVersion": "3.5.0",
"citationEngine": "citeproc-java"
},
"bibliography": [],
"unresolvedKeys": [
"missing"
]
}Recommended use cases
- Research notes with an explicit bibliography
- Deterministic reference-list generation
Avoid for
- Pandoc compatibility
- Remote bibliography lookup
- Custom institutional styles
Related skills
Composable with
Safety & privacy
- Runs without calling any external service.
- Your payloads are never stored permanently.
- Telemetry captures metadata only — never your payload contents.
- We never train models on your payloads.
- No human reviews your payloads.