agentleFS
context-dot-devcontext-dot-dev/cursor-plugin/skills/context-parse/SKILL.md

context-parse

Skill9 starsChanged 3 months agoMITView on GitHub

Convert local document bytes into clean Markdown with Context.dev. Use when the user asks to parse, read, OCR, summarize, or extract text from an attached PDF, Office document, spreadsheet, image, source file, HTML file, or other supported local file.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use the Context.dev parse-document MCP tool for local file bytes.

    line 8
  2. Very specific:

    Read the target file and base64-encode its bytes into fileBase64.

    line 12

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Parse documents

Use the Context.dev parse-document MCP tool for local file bytes. Use a scrape tool instead when the source is a web URL.

Workflow

  1. Read the target file and base64-encode its bytes into fileBase64.
  2. Supply the file extension when known.
  3. Preserve links when they matter to the requested output.
  4. For PDFs, restrict the page range when the user names specific pages.
  5. Enable OCR only for scanned pages or when image text is required.
  6. Work from the returned Markdown for subsequent summarization or extraction.

The decoded input must not exceed 25 MiB. Do not upload unrelated files, and do not paste file contents into chat when the user only asked for a derived answer.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.