agentleFS
Sign inStart free
jonfunk21jonfunk21/co-scientist/literature-scan/SKILL.md

literature-scan

Skill4 starsChanged 25 days agoMITView on GitHub

Use only when the user asks for a literature search on a question, claim or method: verified references only, documented search coverage, results mapped onto the reasoning chain.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. AndreasADL/ai-papermill★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository9 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Do not overstate what a paper shows.

    line 15
  2. Distinctive:

    Use available tools: web search, and any connected literature sources (e.g.

    line 27
  3. Distinctive:

    Run several query formulations.

    line 28
  4. Very specific:

    Add verified references to literature.md (verified section) with L-ids.

    line 50
  5. Very specific:

    Update the familiarity flag that triggered the scan to scanned.

    line 51
  6. Very specific:

    If a chain link changes status, update chain.md and tell the user.

    line 52

≈ “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

Literature scan

Find out whether a question has been addressed, what supports or contradicts a claim, and which methods could be borrowed. Run only when asked (often after a familiarity flag).

Hard rules

  • Every reference is verified: fetched from its source, with title, authors, year, venue and DOI/URL taken from that source, not from memory. If you cannot verify it, it is not a reference; at most it is an unverified lead, labelled as such.
  • Never claim exhaustiveness. Say what was searched. "Not found in <sources> with <queries>" is different from "does not exist".
  • Distinguish peer-reviewed from preprint.
  • Do not overstate what a paper shows; report its actual claim and setting.

1. Scope

State the target precisely, ideally tied to the ledger:

  • which claim or chain link (e.g. "link I2 → N", "C2")
  • what would count as: directly answers / supports / contradicts / method to borrow

Translate the recalled concept from the familiarity flag into search terms, including synonyms used in neighbouring fields (ML, structural biology, biophysics, statistics).

2. Search

  • Use available tools: web search, and any connected literature sources (e.g. PubMed, bioRxiv, arXiv, Semantic Scholar) if present.
  • Run several query formulations; follow citations from the most relevant hits (backward and forward) where possible.
  • For fast-moving ML topics, explicitly include recent preprints.

3. Report

Target: <claim / link>
Searched: <sources>, <queries>, <date>; ~<n> results screened

Directly addresses: L1, …
Supports: …
Contradicts: …
Methods to borrow: …
Not found: <what was looked for and not found>

Implication for the chain: <does any link change status? does N need narrowing? is the result less novel than thought?>

Per reference: one or two sentences on what it actually shows and how it bears on the claim.

4. Ledger

  • Add verified references to literature.md (verified section) with L-ids.
  • Update the familiarity flag that triggered the scan to scanned.
  • If a chain link changes status, update chain.md and tell the user.

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