submission-pack
Skill17 starsChanged 3 months agoMITView on GitHub
Builds the submission bundle — anonymization sweep for double-blind review (self-citations, acknowledgments, metadata), word-count and format checks against the journal's limits, title-page separation, final checklist. Use when the user is about to submit or asks to anonymize or format the manuscript for a journal.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- SaudSatopay/bullseyetheir own version, first seen Nov 8, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- SaudSatopay/bullseye★ 4same 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 repository38 other files it gives its agents.
- abstract-shotgunSkill
- analyzeSkill
- archiveSkill
- carefulSkill
- coauthor-reviewSkill
- codebookSkill
- cover-letterSkill
- data-acquireSkill
- data-cleanSkill
- design-researchSkill
- draft-sectionSkill
- freezeSkill
- guardSkill
- hypothesis-designSkill
- idea-shotgunSkill
- identification-reviewSkill
- journal-fitSkill
- learnSkill
- lit-mapSkill
- llm-checklistSkill
- mstack-initSkill
- mstack-upgradeSkill
- paper-statusSkill
- pdf-ingestSkill
- power-analysisSkill
- preregisterSkill
- r-and-rSkill
- referee-mockSkill
- research-questionSkill
- results-auditSkill
- retroSkill
- robustnessSkill
- scope-challengeSkill
- survey-buildSkill
- theory-buildSkill
- title-shotgunSkill
- unfreezeSkill
- vizSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 19
After /mstack:journal-fit and a final manuscript.
- Distinctive: line 30
Gate: Not ready while any identifying string remains in the anonymized sources (show the grep proof) or any check fails without a …
- Distinctive: line 39
Anonymizing by deletion: Use the journal's anonymous convention.
≈ “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.
Files
/mstack:submission-pack
Stage: submit · Voice: production-editor
After /mstack:journal-fit and a final manuscript. Everything else in MStack front-runs the reviewers; this front-runs the desk: the mechanical checks that bounce papers before anyone reads them.
$ARGUMENTS is the journal; default the tier-1 journal in .mstack/config.yaml.
Procedure
- Journal requirements. WebFetch the author guidelines or ask the user; never trust memory for word caps, anonymization policy, abstract limits, or reference style. Record: word cap and what counts toward it, abstract cap, double-blind y/n, figure / table placement, reference style, supplementary-material policy.
- Anonymization sweep (double-blind journals): grep
paper/for every author name and affiliation in.mstack/config.yaml; recast self-identifying citations ("our previous work", "as we showed (Name YEAR)") in the third person or as "Author (YEAR)" per the journal's convention, never deleting the citation itself; move acknowledgments, grant numbers, institution-tied IRB numbers, and\thanks{}/\author{}content intopaper/title-page.tex, outside the anonymized build; note that the compiled PDF's document properties must not carry author names. - Compliance: word count vs. the cap (
texcount main.tex -inc -totalif available, else a documented approximation), stating count and margin; abstract length vs. its cap; reference style vs. what the bibliography actually produces; figures / tables count, placement (embedded vs. end), resolution. - Bundle. Compile the anonymized manuscript and the title page separately (
latexmk/pdflatexorquarto render; without a TeX toolchain, stage the sources and list the compile steps). Stage undersubmission/<journal-slug>/: anonymized PDF, title page, figures at spec, supplementary material, and the prereg URL ifdesign.preregis true. - Checklist to
submission/submission-checklist-<YYYY-MM-DD>.md: every check with pass / fail and evidence (grep counts, word counts, file list). - Gate. Not ready while any identifying string remains in the anonymized sources (show the grep proof) or any check fails without a user-acknowledged waiver.
Outputs
submission/<journal-slug>/bundle;paper/title-page.tex;submission/submission-checklist-<date>.md.- Summary block: word count vs. cap, anonymization result, remaining manual steps (portal fields, PDF metadata).
Anti-patterns
- Anonymizing by deletion. Use the journal's anonymous convention; never drop the reference.
- Remembered journal rules. Fetch or ask; caps and policies change between volumes.
- "Probably fine" on identity. One grep hit is a desk reject; the sweep ends at zero hits or an explicit waiver (single-blind journals).
Next
/mstack:cover-letter for the same journal, then submit; /mstack:referee-mock editor beforehand stress-tests fit. Set paper.status: "submitted" in .mstack/config.yaml once the portal confirms.
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.

