agentleFS
VeryMathVeryMath/AI4Math-Paper-Reading/skills/paper-to-skill/SKILL.md

paper-to-skill

Skill6 starsChanged 4 months agoMITView on GitHub

Use when extracting reusable AI4Math research skills from papers, especially PDF-to-SkillCard workflows, paper triage, PDF preparation, proof-pattern extraction, and cross-paper SkillCard synthesis for a coding-agent-neutral paper-to-skill workflow.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Start user-facing paper-to-skill work from:

    line 12
  2. Very specific:

    Use skills/registry.yaml to inspect phase order, review gates, and optional upstream or downstream Skills.

    line 18
  3. Distinctive:

    Do not require external LLM APIs for extraction.

    line 26
  4. Very specific:

    Keep platform-specific adapters thin and point them back to skills/registry.yaml and the shared skills/ layer.

    line 27
  5. Very specific:

    Every accepted or review-worthy SkillCard must include source.paper_md, source.start_line, and source.end_line.

    line 28
  6. Distinctive:

    Treat structured JSON, YAML, and reports as indexes or review artifacts, not replacements for the original paper.

    line 29
  7. Distinctive:

    Use human feedback and review decisions as explicit workflow state when available.

    line 30

≈ “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

Paper To Skill

This repository is a Skill-first paper-to-skill workflow package for AI4Math auto research. Codex is the reference operator, but the shared Skill layer is intended for any capable coding agent.

Entry Point

Start user-facing paper-to-skill work from:

skills/paper-to-skill-workflow/SKILL.md

Use skills/registry.yaml to inspect phase order, review gates, and optional upstream or downstream Skills.

This root SKILL.md is not the workflow driver. It is a compatibility entrypoint for platforms that expect one top-level Skill file.

Operating Boundary

  • Accept paper.pdf as the default user input; accept paper.md when conversion has already happened.
  • Preserve the original paper.pdf when provided and the full converted paper.md.
  • Do not require external LLM APIs for extraction; the active coding agent is the extraction engine.
  • Keep platform-specific adapters thin and point them back to skills/registry.yaml and the shared skills/ layer.
  • Every accepted or review-worthy SkillCard must include source.paper_md, source.start_line, and source.end_line.
  • Treat structured JSON, YAML, and reports as indexes or review artifacts, not replacements for the original paper.
  • Use human feedback and review decisions as explicit workflow state when available.
  • Record mathematical dependencies, independent verification, failure cases, and cross-problem reuse in each SkillCard. A high extraction score does not establish library readiness.

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.