pdf2md
AGENTS.md0 starsChanged 4 months agoApache-2.0View on GitHub
This repository is a batch PDF → Markdown OCR tool (Tesseract-based, quality-first, fully local) packaged as an agent skill. Read SKILL.md and follow it as your runbook. It walks you through the whole job in order: check prerequisites → run the built-in self-test → ask the user for the input folder, output folder, and document language(s) → dry-run and confirm scope → convert → report results. It is written to be agent-agnostic; $SKILL in its commands is the directory containing…
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
The file
We split this AGENTS.md 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
- Very specific: line 18
All scripts live in scripts/ and run with the local .venv Python (see SKILL.md section 2).
- Very specific: line 20
Do not skip the self-test (scripts/selftest.py) before touching the user's real files.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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.
Files
pdf2md — instructions for AI agents
This repository is a batch PDF → Markdown OCR tool (Tesseract-based, quality-first, fully local) packaged as an agent skill.
Read SKILL.md and follow it as your runbook. It walks you
through the whole job in order: check prerequisites → run the built-in
self-test → ask the user for the input folder, output folder, and document
language(s) → dry-run and confirm scope → convert → report results. It is
written to be agent-agnostic; $SKILL in its commands is the directory
containing SKILL.md (for a repository checkout, the repository root).
Key facts:
- The tool only ever writes
.mdfiles (plus_errors.log/_review.log) under the output folder the user picks. It never modifies the input PDFs. - All scripts live in
scripts/and run with the local.venvPython (see SKILL.md section 2). Never install into the system Python. - Do not skip the self-test (
scripts/selftest.py) before touching the user's real files.
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
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.