write-paper
Skill0 starsChanged 47 days agoMITView on GitHub
Write an APA-style manuscript from completed, reviewed analysis results. Use in the final phase, after the stats review has passed and GATE 2 approval.
7 other projects use a version of this.
Adopted by
Most recently taken up by
- tsingyuai/scientifytheir own version, first seen Oct 8, 2026
- SebastianElvis/reapertheir own version, first seen Sep 12, 2026
- zhanyinx/skillstheir own version, first seen Sep 3, 2026
- frenzymath/Danustheir own version, first seen Aug 23, 2026
- Felpix-Studios/social-science-researchtheir own version, first seen Jul 6, 2026
- sunnnybala/Rstacktheir own version, first seen Apr 2, 2026
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- tsingyuai/scientify★ 2.2ksame name
- frenzymath/Danus★ 391same name
- sunnnybala/Rstack★ 69same name
- SebastianElvis/reaper★ 9same name
- Felpix-Studios/social-science-research★ 8same name
- mr-devs/cc-research-project-template★ 4same name
- zhanyinx/skills★ 1same 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 repository6 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- analysis-planSkill
- data-scoutSkill
- literature-scanSkill
- run-analysisSkill
- stats-reviewSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
0
Distinctive
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 20
Every number traceable to estimates.json/results.md.
“Common” is measured: kept by at least 6 in 10 of the 7 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
Write Paper
Produce paper/manuscript.md from lit_review.md, plan.md, results.md, and stats_review.md. Convert to docx if pandoc is available: pandoc manuscript.md --citeproc --bibliography=../literature/references.bib -o manuscript.docx (fallback: plain pandoc, references written out from references.bib).
Structure (APA 7)
- Title page: descriptive title stating variables and population; note "Draft generated with AI assistance" (user can remove).
- Abstract (≤250 words): objective, method (design, N, data source), key results WITH numbers (effect size + CI), conclusion. No claims absent from Results.
- Introduction: funnel from broad to specific; every empirical claim cited from references.bib; end with numbered hypotheses verbatim from plan.md.
- Method: Data source & sample (provenance, years, exclusion flow with Ns — from results.md); Measures (operationalizations per plan.md, reliability where computed); Analysis plan (models, inference criteria; note analyses were pre-specified before outcome analysis; software versions from requirements.txt).
- Results: descriptives table first; then hypothesis by hypothesis with statistics sentences copied exactly from results.md — do not re-round or re-type numbers. Robustness summary. Clearly separated "Exploratory Analyses" subsection if applicable.
- Discussion: findings vs. literature; limitations (mandatory, honest: design cannot establish causation, measurement limits, generalizability, sensitivity limits, anything flagged in stats_review.md); future directions; brief conclusion.
- References: from references.bib only.
Rules
- Every number traceable to
estimates.json/results.md. Every citation present inreferences.bib. No new literature at this stage — if a claim needs an uncited source, cut the claim or rerun literature-scan. - Associational language throughout for observational designs ("was associated with", not "led to"/"caused"/"increased").
- Exact p-values (p = .034) except p < .001. Effect sizes + 95% CIs in text, not just tables.
- Figures by reference (
) with APA-style captions. - Tone: precise, hedged proportionate to evidence, no hype. Null/negative findings get equal prominence.
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.

