nature-paper-card
Skill0 starsChanged 2 months agoMITView on GitHub
Build a source-grounded deep-reading Paper Card for one scientific paper, preprint, PDF, DOI, arXiv page, publisher article, or pasted paper text. Use when the user asks for a Paper Card, deep-reading literature card, single-paper deep analysis, module-by-module analysis, experiment-to-claim evidence chain, conclusion-boundary audit, critical analysis, knowledge connections, or candidate research ideas. Produce the fixed Sections 01-16 covering bibliographic position, research question, background route, pain point, core insight, method and module logic, essential formulas, experiment-to-claim evidence, conclusion boundaries, author-stated limitations, critical analysis, learned knowledge, knowledge connections, and testable research ideas. Do not use for full-paper bilingual translation, formal peer-review reports, batch literature monitoring, academic-English collection, comprehension quizzes, or public-article writing.
3 other projects use a version of this, 3 of them edited.
Adopted by
Most recently taken up by
- Luooops/skillsedited, first seen Oct 13, 2026
- Yuan1z0825/nature-skillsedited, first seen Aug 31, 2026
- ZeyuLing/research_autocode_skillsedited, first seen Jun 28, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 3
- Yuan1z0825/nature-skills★ 54k97% same
- ZeyuLing/research_autocode_skills★ 9100% same
- Luooops/skills★ 197% same
Wrote their own version · 0
None found.
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 repository21 other files it gives its agents.
- journal-style-learnSkill
- nature-academic-searchSkill
- nature-citationSkill
- nature-dataSkill
- nature-downloaderSkill
- nature-experiment-logSkill
- nature-figure-prompt-onlySkill
- nature-figureSkill
- nature-image2pptSkill
- nature-literature-pipelineSkill
- nature-paper2pptSkill
- nature-paper-to-patentSkill
- nature-polishingSkill
- researchwriteSkill
- nature-readerSkill
- nature-ref-verifierSkill
- nature-responseSkill
- nature-reviewerSkill
- nature-sharedSkill
- nature-statisticsSkill
- nature-writingSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
34 rules. 17 are common, 2 are distinctive, and 15 are very specific to this project.
17
Common
Most of the 3 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
15
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Treat a source journal as metadata: preserve the source’s facts and structure.
- Distinctive: line 16
Keep this skill’s original source-processing workflow.
- Very specific: line 22
Use ESWA as source metadata and preserve source-grounded claims.
- Very specific: line 24
Only if journal fit or submission requirements are requested, read ../nature-shared/journal-formats/eswa.md.
- Common: line 29
Use this skill to turn one paper into an evidence-grounded research card, not a translated abstract, generic summary, reviewer report, or …
- Common: line 39
Follow these steps every time.
- Very specific: line 43
Read manifest.yaml, then read every file under always_load.
- Very specific: line 54
Prefer an existing nature-reader artifact when supplied.
- Common: line 60
Run exactly the bundled script by its resolved path:
- Very specific: line 67
Add --render-dir WORKDIR/rendered-pages when visual page review is needed.
- Common: line 71
Never write inline Python, a temporary extraction script, or a replacement script during a Paper Card run.
- Common: line 73
Use this fixed locator state machine:
- Very specific: line 79
If preparation fails, record the failure.
- Very specific: line 83
Use the manifest to choose one primary paper_type and, only for a genuinely hybrid paper, one secondary contribution lens:
- Common: line 101
every main figure, table, and essential equation with its argumentative role.
- Common: line 108
Use external search only for Section 04, Section 15, bibliographic verification, or an explicit novelty check.
- Common: line 119
Read references/evidence-and-provenance.md before making analytical or externally verified claims.
- Very specific: line 121
Write a real Markdown artifact, defaulting to paper-card.md.
- Very specific: line 127
Before delivery, resolve the bundled auditor from SKILL_DIR.
- Common: line 152
every major method, result, boundary, and limitation has a source pointer.
- Common: line 158
no academic-English collection, comprehension quiz, or public-article draft was added.
- Common: line 160
If the auditor itself cannot run, state that failure and manually apply only its documented checks.
- Common: line 164
Do not resolve bundled scripts relative to the user's current working directory.
- Common: line 165
Do not write or execute inline Python as a substitute for either bundled script.
- Very specific: line 166
Do not create extract_pdf.py, parse_paper.py, or another one-off replacement.
- Common: line 167
Do not patch skill code during a normal Paper Card generation request.
- Common: line 168
Do not fabricate page numbers when preparation fails.
- Common: line 169
Do not remove all grounding in fallback mode.
- Very specific: line 173
Use nature-reader for full-text bilingual reading artifacts, extraction, and stable source maps.
- Very specific: line 174
Use nature-academic-search when external literature is needed to verify field history or knowledge connections.
- Very specific: line 175
Use nature-reviewer for formal reviewer-style manuscript assessment.
- Very specific: line 176
Use nature-literature-pipeline for batch discovery and lightweight monitoring notes.
- Very specific: line 177
Use nature-paper2ppt when the requested end product is a presentation.
- Common: line 179
Do not silently switch the requested Paper Card into any of these outputs.
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Nature Paper Card - Router
Additional configured journals
For Applied Soft Computing (ASC), Engineering Applications of Artificial
Intelligence (EAAI), ISA Transactions, Knowledge-Based Systems (KBS),
Measurement, Neurocomputing, or IEEE Transactions on Reliability, use
../nature-shared/journal-formats/index.md to resolve the exact journal.
Treat a source journal as metadata: preserve the source’s facts and structure.
Load submission constraints only when target formatting or fit is requested.
Keep this skill’s original source-processing workflow.
ESWA journal context
Recognize Expert Systems with Applications (ESWA, Expert Syst. Appl.)
as the same journal, case-insensitively; distinguish similarly named titles.
Use ESWA as source metadata and preserve source-grounded claims. Apply
journal-fit criteria only when the user actually requests that assessment.
Only if journal fit or submission requirements are requested, read
../nature-shared/journal-formats/eswa.md; otherwise keep this workflow
source-oriented without loading submission rules.
Use this skill to turn one paper into an evidence-grounded research card, not a translated abstract, generic summary, reviewer report, or publication article.
The skill uses:
- a static core under
static/core/for principles, workflow, and the fixed output contract; - one paper-type fragment under
static/fragments/paper_type/; - on-demand references for evidence labels, the exact card schema, and research-idea checks.
Routing protocol
Follow these steps every time.
1. Load the manifest and core layer
Read manifest.yaml, then read every file under always_load. Do not generate the card from this router alone.
2. Establish the source boundary
Identify which material is available:
- full paper with figures and tables;
- paper text without reliable layout;
- abstract or metadata only;
- an existing
nature-readerartifact with stable source IDs.
Prefer an existing nature-reader artifact when supplied. Do not repeat full bilingual translation or figure extraction. If only partial material is available, create a visibly partial card and mark every unsupported section Not assessable from supplied material.
For a PDF or nature-reader source-map JSON, the bundled script is mandatory.
- Resolve
SKILL_DIRas the directory containing this loadedSKILL.md. - Verify
SKILL_DIR/scripts/prepare_paper.pyexists. - Run exactly the bundled script by its resolved path:
python "SKILL_DIR/scripts/prepare_paper.py" INPUT \
--output WORKDIR/source_bundle.jsonAdd --render-dir WORKDIR/rendered-pages when visual page review is needed. Inspect the script exit code and the bundle validation block before drafting.
For source-map input, also inspect locator_summary and unlocated_blocks. Only records under pages have verified positive PDF page locators. Missing or invalid page locators remain in unlocated_blocks with an explicit status and must be cited structurally, never as page 1.
Never write inline Python, a temporary extraction script, or a replacement script during a Paper Card run. Never patch the bundled scripts during a normal Paper Card run. Modify these scripts only when the user explicitly asks to develop, debug, or improve the skill itself.
Use this fixed locator state machine:
page-grounded: the bundled script succeeds and validates reliable PDF page indices. Use PDF page plus structural locators. Printed page labels are optional metadata.structure-grounded: page extraction is unreliable, but reliable sections, figures, tables, equations, source blocks, or full text remain available. Do not emit page-number citations.source-limited: only an abstract, metadata, or user-provided excerpt is reliable. Do not emit page-number citations or infer unseen evidence.
If preparation fails, record the failure. Prefer an existing nature-reader source map or the environment PDF/OCR capability, but do not create a replacement script. Then enter the strongest supported fallback mode.
3. Classify the paper type
Use the manifest to choose one primary paper_type and, only for a genuinely hybrid paper, one secondary contribution lens:
methodsdiscoveryresourceclinicalmaterialsreview
Load the primary fragment and no more than one secondary fragment. Classify by the paper's argument and evidence structure, not merely its discipline. State both selections before analysis. For example, an algorithm paper that also introduces a substantial dataset may use methods as the primary lens and resource as the secondary lens.
4. Build the evidence base before drafting
Build an internal evidence inventory before drafting. At minimum, enumerate:
- bibliographic metadata and access status;
- research question and claimed contribution;
- method components, assumptions, and data flow;
- every main figure, table, and essential equation with its argumentative role;
- experiments, baselines, metrics, ablations, and reported results;
- author-stated limitations;
- stable source pointers to pages, sections, equations, figures, tables, or
nature-readerblock IDs.
Then build a compact claim-evidence matrix linking each central claim to the evidence that supports it and to any unresolved gap.
Use external search only for Section 04, Section 15, bibliographic verification, or an explicit novelty check. Never present the paper's own related-work narrative as independently verified field history. Record whether the context mode is paper-only, targeted external check, or externally verified.
5. Generate the fixed Sections 01-16 Paper Card
Apply, in order:
- core principles;
- the selected paper-type fragment;
- core workflow;
- output contract.
Read references/evidence-and-provenance.md before making analytical or externally verified claims. Read references/card-schema.md when drafting the final Markdown. Read references/research-idea-gates.md before writing Section 16.
Write a real Markdown artifact, defaulting to paper-card.md. Keep all 16 numbered sections in order, but write Not applicable or Not assessable instead of inventing content.
Match the user's language by default. The skill source and schema remain English, but localize the Paper Card headings and prose when the user writes in another language. Preserve canonical technical terms and formulas.
6. Run groundedness QA
Before delivery, resolve the bundled auditor from SKILL_DIR. In page-grounded mode, run:
python "SKILL_DIR/scripts/audit_paper_card.py" \
--card WORKDIR/paper-card.md \
--bundle WORKDIR/source_bundle.json \
--locator-mode page-grounded \
--report WORKDIR/audit-report.jsonIn either fallback mode, run the same auditor without a bundle:
python "SKILL_DIR/scripts/audit_paper_card.py" \
--card WORKDIR/paper-card.md \
--locator-mode structure-grounded-or-source-limited \
--report WORKDIR/audit-report.jsonReplace the last value with the actual canonical mode. Treat audit errors as blockers. Review warnings with scientific judgment rather than suppressing them mechanically.
Also verify:
- numerical results match the source;
- the evidence inventory covers every main figure and table;
- every major method, result, boundary, and limitation has a source pointer;
- PDF page pointers distinguish PDF page index from printed page labels;
- author statements are separated from Agent analysis;
- external field-history claims have external citations or are marked unverified;
- proposed ideas are hypotheses, not novelty claims;
- Sections 17 and 18 do not exist;
- no academic-English collection, comprehension quiz, or public-article draft was added.
If the auditor itself cannot run, state that failure and manually apply only its documented checks. Do not write a substitute auditor.
Script red lines
- Do not resolve bundled scripts relative to the user's current working directory.
- Do not write or execute inline Python as a substitute for either bundled script.
- Do not create
extract_pdf.py,parse_paper.py, or another one-off replacement. - Do not patch skill code during a normal Paper Card generation request.
- Do not fabricate page numbers when preparation fails.
- Do not remove all grounding in fallback mode; use structural locators or explicit source-scope locators.
Relationship to adjacent skills
- Use
nature-readerfor full-text bilingual reading artifacts, extraction, and stable source maps. - Use
nature-academic-searchwhen external literature is needed to verify field history or knowledge connections. - Use
nature-reviewerfor formal reviewer-style manuscript assessment. - Use
nature-literature-pipelinefor batch discovery and lightweight monitoring notes. - Use
nature-paper2pptwhen the requested end product is a presentation.
Do not silently switch the requested Paper Card into any of these outputs.
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.

