agentleFS
Sign inStart free
B-M-Capital-ResearchB-M-Capital-Research/honeclaw/skills/pdf_understanding/SKILL.md

PDF Understanding

Skill748 starsChanged 3 months agoMITView on GitHub

Read and analyze user-uploaded PDFs, preferably using the system-extracted text fragments, and output summaries, key points, and risk notes

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 6 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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:

    When the message contains a 【PDF extraction text】 block, the system has already attempted to extract text from the PDF.

    line 11
  2. Very specific:

    Prefer the content in 【PDF extraction text】 and answer with a structured conclusion:

    line 16
  3. Distinctive:

    If extraction failed or the text is insufficient, which is common for scanned PDFs:

    line 20
  4. Distinctive:

    Ask the user for OCR text, a key-page screenshot, or a specific page number

    line 22
  5. Distinctive:

    If the user's question requires external fact checking, add tools:

    line 23
  6. Distinctive:

    Do not guess conclusions that are not present in the PDF

    line 29
  7. Distinctive:

    When citing evidence, stay close to the original wording and avoid inventing numbers

    line 30
  8. Distinctive:

    Keep the output concise and actionable for a chat setting

    line 31

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

PDF Understanding Skill

When the message contains a 【PDF extraction text】 block, the system has already attempted to extract text from the PDF. Follow the flow below.

Standard Flow

  1. Identify the user's goal first: summary, Q&A, risk scan, financial metric extraction, investment judgment, and so on
  2. Prefer the content in 【PDF extraction text】 and answer with a structured conclusion:
    • Core conclusion (1-3 points)
    • Key evidence (important text points from the PDF)
    • Uncertain or missing items
  3. If extraction failed or the text is insufficient, which is common for scanned PDFs:
    • State clearly that the current PDF text is insufficient
    • Ask the user for OCR text, a key-page screenshot, or a specific page number
  4. If the user's question requires external fact checking, add tools:
    • web_search(query="...") for news, announcements, or industry context
    • data_fetch(...) for real-time market or company data

Output Requirements

  • Do not guess conclusions that are not present in the PDF
  • When citing evidence, stay close to the original wording and avoid inventing numbers
  • Keep the output concise and actionable for a chat setting

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.

Check your setup, free