paper-deep-reading
Skill2 starsChanged 35 days agoMITView on GitHub
Writes one structured note per included paper and appends findings to the evidence table with page locators and no invented identifiers. Trigger on "read this paper", "deep read", "evidence table", or "paper note". Do not use it to outline the review, draft a section, or summarize a paper you cannot open.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- Jinsong-Zhou/bio-research-skillstheir own version, first seen Nov 15, 2026
- Robertmorrisluminousenergy177/paper-deep-reading-skilltheir own version, first seen Oct 9, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- Robertmorrisluminousenergy177/paper-deep-reading-skill★ 1same name
- Jinsong-Zhou/bio-research-skills★ 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 repository20 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/literature-review.mdcCursor rule
- exemplar-review-analysisSkill
- figure-permissionsSkill
- journal-selectionSkill
- literature-screeningSkill
- manuscript-polishingSkill
- reviewer-responseSkill
- review-figures-and-tablesSkill
- review-orchestratorSkill
- review-outline-builderSkill
- review-project-setupSkill
- review-scoping-and-gapsSkill
- review-section-drafterSkill
- review-writingSkill
- search-export-and-dedupSkill
- search-strategy-builderSkill
- submission-packageSkill
- zotero-library-syncSkill
The file
We split this skill into the rules it gives an agent
11 rules. About 0 are common, 5 are distinctive, and 6 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.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 26
Only when use_zotero is true in project.yaml: <project>/04-library/collection_checklist.tsv with every user_confirmed cell yes.
- Very specific: line 35
Create 05-reading/<citation_key>.md from the template.
- Very specific: line 36
Write the aim, the design (one label from the evidence schema: rct, cohort, case-control, cross-sectional, qualitative, in-vitro, …
- Distinctive: line 47
No project lock. Stop when the PDF and the library record disagree on DOI, PMID, or year, and ask the user which source to trust.
- Very specific: line 57
Every finding row has a page locator and a claim_strength.
- Distinctive: line 60
No evidence id was reused.
- Distinctive: line 64
Do not deep-read from the abstract, a blog, or a citation manager snippet.
- Distinctive: line 65
Do not invent sample size, p values, or effect directions.
- Distinctive: line 66
Do not paste long quotations.
- Very specific: line 67
Do not add a row for a paper that is not in included.tsv.
- Very specific: line 68
Do not delete an evidence row.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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.
Files
Paper deep reading
Opening
On first use in a project, say this verbatim:
I am paper deep reading. I write a note and evidence rows only from a file you hold, and I do not invent page numbers.
When to use
An included record has a legal PDF or other full text the user can open (04-library/pdf_status.csv status available, user_has_pdf, or user_uploaded). Read one paper at a time. If the status is no_legal_copy_found, awaiting_user_upload, or requested_ill, log a no-PDF skip for that record and move on; do not wait for the user's upload. When the file arrives later, read it then. Do not read from an abstract alone and call it a deep read.
Inputs (paths) / Preconditions
<project>/03-screening/included.tsvand<project>/04-library/pdf_status.csv.- Only when
use_zoteroistrueinproject.yaml:<project>/04-library/collection_checklist.tsvwith everyuser_confirmedcellyes. Do not start whilecheck_collections.py --readywould fail. <project>/02-records/library.csvfor DOI, PMID, authors, andjournal. Copyjournalinto the evidence columnvenueand into the note'svenueline.03-screening/included.tsvalready stores that same value asvenue.- The user's open copy of the paper.
- Column rules in
references/evidence_columns.md(same header asshared/evidence_table_schema.md). - Note skeleton in
references/paper_note_template.md.
Procedure (numbered steps)
- Pick the next included
record_idthat has no05-reading/<citation_key>.md. Open the PDF the user supplied. If a DOI or PMID on the PDF differs fromlibrary.csv, stop and mark the note[VERIFY]. Do not "fix" the library by typing a new DOI. - Create
05-reading/<citation_key>.mdfrom the template. Fill bibliographic fields from the library and the PDF first page.n_authorsis a count you can see, or empty. - Write the aim, the design (one label from the evidence schema:
rct,cohort,case-control,cross-sectional,qualitative,in-vitro,in-silico,systematic-review,scoping-review,narrative-review,overview-of-reviews,methods,other), and the setting, only when the paper states them. - For each finding you may later want to cite, add one evidence row, not a paragraph of mixed claims. Each row needs
page(printed page, section, or figure/table id). A number you did not see on that page does not go instatistic. - Quotes: leave
quoteempty by default. If a short sentence is worth keeping, copy at most one sentence and put the page inpage. Paraphrase everything else. - Limitations: only those the paper states. If you see a limitation the authors do not mention, put it under
Reader notein the markdown file, not in thelimitationscolumn. - Figure ideas: describe an original schematic this review could draw. Name the published figure as something not to copy (
Do not copy: Fig. 2 of this paper). Do not trace it. - Append rows to
evidence/evidence_table.csv. If the file is missing, write the header fromreferences/evidence_columns.mdfirst.evidence_idstarts atE001. The next id is one above the current maximum, zero-padded to at least three digits. Never reuse or renumber an id. - Set
supports_claimto the claim this row can actually support, andclaim_strengthtodirect,indirect,conflicting, orbackground. A result that disagrees with the locked question's expected direction isconflicting, and it is still appended. - Append
YYYY-MM-DD | paper-deep-reading | note <citation_key> with <k> evidence rows | agent.
Human gate(s)
No project lock. Stop when the PDF and the library record disagree on DOI, PMID, or year, and ask the user which source to trust. Do not continue that paper until they answer.
Outputs (exact paths + formats)
05-reading/<citation_key>.md— template sections, including the linerecord_id: R0001near the top.evidence/evidence_table.csv— appended rows only. Header inreferences/evidence_columns.md.
Quality checklist
- The note's
record_id, DOI, and PMID matchlibrary.csvor are marked[VERIFY]with the work stopped. - Every finding row has a page locator and a
claim_strength. statisticis empty or a verbatim fragment from that page.quoteis empty or a single sentence.- No evidence id was reused. The CSV still parses (commas inside fields are quoted).
Guardrails
- Do not deep-read from the abstract, a blog, or a citation manager snippet.
- Do not invent sample size, p values, or effect directions.
- Do not paste long quotations. One sentence is the maximum, and only with a page.
- Do not add a row for a paper that is not in
included.tsv. - Do not delete an evidence row. A correction is a new row whose
method_noteiscorrects E014.
Next step
The next unread included paper. When every included record is either noted or logged as skipped for lack of a legal copy, go to exemplar-review-analysis. Attaching a note inside the user's reference manager is optional, and only after they ask: that export is zotero-library-sync, with a log of what was attached.
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.

