agentleFS
Sign inStart free
alainatoralainator/worldcodex/.claude/skills/researching-papers/SKILL.md

researching-papers

Skill2 starsChanged 7 months agoMITView on GitHub

Searches academic databases (arXiv, Crossref, PMC, Semantic Scholar, Open Library, Stanford Encyclopedia of Philosophy) for papers matching a research query, downloads PDFs, and converts them to markdown. Use when grounding fictional science in real research, finding citations for existing content, or when user says "find papers", "search for research", "download papers", "what does real science say about", "ground this in research", "find citations", or "look up [scientific concept]". Does NOT map research onto canon formalism — use /integrating-research for that.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 5 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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:

    Search open-access academic sources, download PDFs, and convert to markdown.

    line 17
  2. Very specific:

    All commands use tools/research-tool.py:

    line 21
  3. Distinctive:

    Physics/Chemistry/Biology: Default sources. Prefer recent papers (2020+).

    line 62
  4. Very specific:

    Philosophy/Foundations: Use --source humanities. Domains: philosophy of science, formal epistemology, systems theory, cognitive science.

    line 65
  5. Very specific:

    Read converted markdown in _source/research/markdown/ or sep-entries/

    line 72
  6. Distinctive:

    Does NOT map research onto canon formalism (use /integrating-research).

    line 92
  7. Distinctive:

    Does NOT write science files (use /writing-science).

    line 93
  8. Distinctive:

    Does NOT audit existing citations (use /auditing-canon).

    line 94

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Researching Papers

Search open-access academic sources, download PDFs, and convert to markdown.

Tool

All commands use tools/research-tool.py:

# Search default sources (arXiv + Crossref + PMC + Unpaywall)
python3 tools/research-tool.py search "quantum time operator"
python3 tools/research-tool.py search "percolation theory" --source arxiv --max 10

# Search humanities (Semantic Scholar + Open Library + SEP + PhilPapers)
python3 tools/research-tool.py search "autopoiesis" --source humanities
python3 tools/research-tool.py search "structural realism" --source sep --download

# Search everything
python3 tools/research-tool.py search "recursive epistemology" --source all

# Download specific paper
python3 tools/research-tool.py download 2301.12345
python3 tools/research-tool.py download https://arxiv.org/pdf/2301.12345.pdf --title "Title"

# Fetch SEP entry by slug
python3 tools/research-tool.py fetch-sep structural-realism

# Convert PDF to markdown
python3 tools/research-tool.py convert _source/research/papers/paper-name.pdf
python3 tools/research-tool.py convert-all

# List and index
python3 tools/research-tool.py list
python3 tools/research-tool.py list --topic "collapse"
python3 tools/research-tool.py index

File Organization

  • _source/research/papers/ — original PDFs
  • _source/research/markdown/ — converted markdown
  • _source/research/sep-entries/ — Stanford Encyclopedia entries
  • _source/research/INDEX.md — catalog
  • _source/research/last-search-results.json — most recent results

Domain Strategies

Physics/Chemistry/Biology: Default sources. Prefer recent papers (2020+). Prioritize experimental results.

Philosophy/Foundations: Use --source humanities. Domains: philosophy of science, formal epistemology, systems theory, cognitive science.

Process

  1. Identify the gap or concept needing grounding
  2. Search appropriate sources
  3. Read converted markdown in _source/research/markdown/ or sep-entries/
  4. Present findings with relevance assessment
  5. Hand off to /integrating-research for canon formalization

Citations

[Author, Year] inline with ## References section. Each entry includes a one-sentence annotation. Cited science is canon science — no disclaimers.

Configuration

Set your contact email for polite API access:

export RESEARCH_TOOL_EMAIL="your-email@example.com"

Requires pdftotext (poppler-utils) or pypdf for PDF conversion.

Out of Scope

Does NOT map research onto canon formalism (use /integrating-research). Does NOT write science files (use /writing-science). Does NOT audit existing citations (use /auditing-canon).

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