Documents & files

Convert anything at a URL - HTML, PDF, or an image - to clean markdown. The 'I have a URL but it might be any content-type, give me markdown either way' workflow: HEAD-detect the content-type, branch to the right deterministic extractor (article extract for HTML, pdf-to-markdown for PDFs, OCR for images), and report token/word stats on the output so the caller can budget the result against an LLM context window.

Extract/convert the audio track of any media URL (mp4, mov, wav, m4a, ogg…) to MP3 - the "mp4 to mp3" conversion, deterministic ffmpeg, no AI. Body: {"url":"https://…/video.mp4","bitrate":"192k"?}. Returns the MP3 as base64.

Top holdings from an institutional investment manager's most recent 13F-HR filing (managers >$100M AUM file quarterly). Parses the standard SEC informationtable.xml attached to the filing - returns issuer, CUSIP, shares, USD value, and voting authority for each position. Sorted by USD value, descending. Source: data.sec.gov + filing archive.

The 'user uploaded a thing, normalize it before storing' workflow. Probe the file (image or audio/video) with media-info, decode any embedded barcodes/QRs, resize and thumbnail the image, convert it to a web-friendly format, and normalize audio loudness to broadcast standard. Six tools, one canonical normalize-on-upload pipeline that turns arbitrary user uploads into predictable storage artifacts.

Take a signup form submission and run the full onboarding workup deterministically: validate the email, score the chosen password, mint a stable internal ID, derive a URL-safe handle from the display name, generate a recovery / API secret, hash the password for storage, and verify the 2FA setup code. One pass, every step a pure-CPU call.

Validate, pretty-print, and convert JSON to CSV in one pass - the complete JSON processing workflow. JSON pipeline skill pack: one x402 payment runs 3 underlying tools (json-validate, json-format, json-to-csv); partial-success per step.

Fetch an RSS 2.0, Atom, or RSS 1.0 feed URL and parse it into normalized JSON: feed title/description/link plus items (title, link, id, published, author, plain-text summary, categories). Deterministic pure-XML parse with a lenient recovery pass for common malformations (reported in a warnings array). Item count is bounded (default 20, max 50). SSRF-guarded.

Markdown to HTML and back - a round-trip conversion that proves fidelity and gives you both formats from one input. Markdown to HTML round-trip skill pack: one x402 payment runs 3 underlying tools (markdown-to-html, html-to-markdown, text-diff); partial-success per step.

Convert CSV into a GitHub-flavored Markdown table (first row is the header).

Parse CSV (quoted fields supported) into a JSON array of objects, using the first row as headers (header=false for arrays).

Score an OpenAPI 3.x or Swagger 2.x spec on agent-readiness - i.e. does an LLM-driven caller have what it needs to call the API correctly without guessing. Returns a 0..100 score, severity counts, and a structured list of violations with stable rule codes. Checks: documented title/servers/paths, per-operation summary/description/operationId/tags, documented 2xx + error responses, param descriptions/schemas/examples, response descriptions, JSON response schemas.

Build a runnable curl command for one operation in an OpenAPI 3.x or Swagger 2.x spec. Locate the operation by operationId (preferred) or by method + path, substitute path parameters using the spec's example values, include required query and header parameters with their example values, and attach a JSON body when the operation defines one. Returns the structured request (method, url, headers, body) alongside the assembled curl string with POSIX single-quote escaping.

Convert subtitles between SRT, WebVTT, plain text, and JSON cues. Send SRT or VTT text (auto-detected) - or a JSON cues array [{start,end,text}] with times in ms - and the target format. Deterministic, pure CPU.

Parse XML into a JSON object tree (attributes under _attrs, text under _text; repeated elements become arrays).

Safely evaluate an arithmetic expression (+ - * / % ^ and parentheses). No code execution - a real parser, not eval.

Convert text between camelCase, PascalCase, snake_case, kebab-case, CONSTANT_CASE, Title Case, lower, UPPER.

Read one 32-byte storage slot from a contract, the raw state under whatever the source code calls it. Returns the word as hex plus three readings of the same bytes - unsigned integer, address (low 20 bytes) and boolean - because a slot is untyped on chain and only the caller knows which it meant. Useful for proxy implementation slots, paused flags and any value the ABI does not expose. EVM chains: ethereum, base, polygon, arbitrum, optimism.

Convert a color between hex, RGB, and HSL. Accepts "#1a2b3c", "rgb(26,43,60)", or "hsl(210,40%,17%)".

Validate CSV structure: consistent column counts across rows, properly closed quotes, delimiter detection. Returns row/column counts and any structural errors. Pure CPU.

Parse a 5-field cron expression and return the next N run times (UTC).

Parse a duration like "2h30m" / "1d4h" / "90s" to seconds, or humanize a number of seconds.

Convert an HTML fragment or document you already have into clean markdown. (To fetch + convert a live URL, use /api/extract.)

Deep-compare two JSON values. Returns a list of changed/added/removed paths (capped at 1000 differences).

Flatten nested JSON to dot-path keys, or unflatten dot-path keys back to nested JSON. mode: flatten (default) | unflatten.

Validate, pretty-print (any indentation, 0-8 spaces), or minify JSON, optionally with object keys sorted. canonical: true returns the RFC 8785 (JCS) canonical form - keys sorted, no whitespace, ECMAScript number and string serialization - plus its SHA-256, for hashing and signing. Numbers are read as IEEE-754 doubles and a duplicate key keeps its last value. Returns parse errors with position when invalid.

Convert between a JSON array and JSONL/NDJSON (one JSON object per line). mode: to-jsonl (array → lines) or from-jsonl (lines → array). For streaming records to and from agents and datasets.

Delete a remembered document by id from the recall store.

Compare two OpenAPI 3.x or Swagger 2.x documents and return a structured diff: added / removed / changed endpoints, with a conservative "is any change breaking?" flag. Breaking = an endpoint or required-2xx status was removed, a required parameter was added, an optional param became required, a param type changed, or a JSON body field became required. Pure CPU - deterministic, no network, no $ref dereferencing (resolve refs upstream if needed).

Shrink an OpenAPI 3.x or Swagger 2.x document for LLM context by stripping verbose meta-fields (examples, descriptions, summaries, tags, externalDocs, deprecated). Categories are explicit; default is `["examples", "descriptions"]`. User-defined property names under `properties: { ... }` are protected - only the meta-field `example` keyword inside a property schema is removed, not a user property literally named "example".

Parse a URL query string into an object, or build one from an object. mode: parse (default) | build.