archive
Skill17 starsChanged 3 months agoMITView on GitHub
Assembles the replication package to the Data and Code Availability Standard — inventory with checksums, licenses and data citations, renv lockfile, a replication README from the bundled template with an exhibit-to-script map, and a clean-room rebuild that regenerates every table and figure from raw data — and stages the OSF/Dataverse upload. Use at acceptance, whenever the user asks for a replication or reproducibility package, or mentions a Dataverse/OSF deposit or the journal's data policy.
22 other projects use a version of this.
Adopted by
Most recently taken up by
- phuthuycoding/kanban-flowtheir own version, first seen Nov 8, 2026
- egregore-labs/egregoretheir own version, first seen Nov 6, 2026
- myowinthein/claude-helmtheir own version, first seen Nov 1, 2026
- serbanghita/plan-critique-skillstheir own version, first seen Nov 1, 2026
- kirkchen/beattheir own version, first seen Nov 1, 2026
- bks-lab/open-bridgetheir own version, first seen Oct 30, 2026
Used with
Projects with it also use distill, plan and 3 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
HK-hubSkilldistill
Strip designs to their essence by removing unnecessary complexity. Great design is simple, powerful, and clean. Use when the user asks to simplify, declutter, reduce noise, remove elements, or make a UI cleaner and more focused.
Also in 3 projects that use this
BlockSkillplan
Draft a TDD, PRD, or lightweight plan in the conversation without committing it.
Also in 5 projects that use this
AnthropicSkillstatus
Case status summary by audience — client-facing (plain language), internal (for the professor), or court-ready (formal caption format per local rules). Same facts, different framing and depth. Use when a student needs to update the client, brief the professor, or prepare a court status report.
Also in 3 projects that use this
Microsoft AzureSkilltest
Also in 3 projects that use this
MicrosoftSkillhandoff
Compact the current conversation into a handoff document for another agent to pick up.
Also in 3 projects that use this
Other versions22 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 22
- ReScienceLab/opc-skills★ 1.9ksame name
- egregore-labs/egregore★ 293same name
- bks-lab/open-bridge★ 13same name
- serbanghita/plan-critique-skills★ 13same name
- kirkchen/beat★ 9same name
- philippe-desplats/second-brain★ 6same name
- codebycorey/delta-spec★ 4same name
- grasscaograss/AwesomeWeldoneSkills★ 2same name
- jcordon5/archive-skill★ 2same name
- phuthuycoding/kanban-flow★ 2same name
12 more not listed
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
- 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
- submission-packSkill
- survey-buildSkill
- theory-buildSkill
- title-shotgunSkill
- unfreezeSkill
- vizSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 18 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 48
"Available upon request.": Not a package, whatever the journal allows.
- Distinctive: line 49
An exhibit with no script: Every table and figure maps to code.
- Distinctive: line 50
Unflagged hand-edited figures: Document post-processing so the unedited version can be rebuilt.
“Common” is measured: kept by at least 6 in 10 of the 18 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
/mstack:archive
Stage: reflect (at acceptance) · Voice: replicator
At acceptance, before the production deadline. The goal is not the journal's data policy; it is that in two years anyone can rebuild every table and figure from raw data. The README follows the Data and Code Availability Standard (Vilhuber et al.) that the AJPS verification process and the AEA data editor apply, so a verifier finds what they expect where they expect it.
Procedure
- Load
.mstack/config.yaml(title, the actual journal and its replication policy),paper/,data/,code/,output/,prereg/,data/raw/PROVENANCE.md. - Inventory to
replication-manifest.txt, with a SHA-256 checksum per file: raw files with sources, vintages, licenses; crosswalks; clean data; code in run order; outputs (tables, figures, model objects); the accepted manuscript; preregistration and any addenda;.mstack/llm-usage.jsonlplus everyprompt_user_ref/code_reffile it names (GUIDE-LLM artifacts), if the ledger exists. - Licenses and citations. Open or public-domain raw files ship; restricted ones (commercial, IRB, DUA) become a stub + re-acquire script, with the restriction, the access procedure, and the exhibits that need them documented in the README. Every source has a data citation (from
PROVENANCE.mdandpaper/refs.bib). Tag each file in the manifest. - Pin dependencies. R:
sessionInfo()andrenv::snapshot()→renv.lockplusrenv/activate.Rso the package self-restores. System dependencies (LaTeX distribution, JAGS, Stan, GDAL) and Quarto / LaTeX versions listed. For long-lived packages, note a container recipe (arockerimage pinned to the R version) as optional insurance. Write the replication README from
${CLAUDE_PLUGIN_ROOT}/skills/archive/assets/replication-README-template.mdintoREADME.md, filling every section: overview with runtime and machine; data availability and provenance with the access certification; the data-sources table; computational requirements; the code table; replicator instructions that run every numbered script, not a hardcoded four (/mstack:codebook,/mstack:power-analysis, and/mstack:robustnessadd 00/05/06-series scripts whose outputs also ship):renv::restore() scripts <- sort(list.files("code", pattern = "^[0-9].*\\.R$", full.names = TRUE)) scripts <- scripts[!grepl("00-fetch", scripts)] # raw data ships; fetch scripts hit the network for (f in scripts) source(f)the exhibits table mapping every table and figure in the paper and appendix to its script and output file; deviations from the published paper (a figure hand-edited in Illustrator, journal typesetting); data and software citations. A controller script
code/00-run-all.Rcontaining the loop above is worth adding.- Clean-room rebuild. Copy the project to a temporary directory;
renv::restore(); run the loop; diff the rebuiltoutput/tables/andoutput/figures/against the originals (checksums, or a visual diff for figures); check every exhibit in the exhibits table was regenerated. Fix or document every divergence; refuse to mark the package ready while any divergence is unexplained or any exhibit lacks a producing script. - Stage the upload: repository (the journal's designated Dataverse if it has one; otherwise OSF; institutional as a mirror); build
submission/replication-<short_name>.zipexcluding.git/,renv/library/(rebuilt fromrenv.lock), and restricted raw files (stubs instead); print the upload checklist including the metadata the repository asks for (title, authors, related publication DOI, keywords, license). - Config:
paper.status: "archived"; add the DOI / OSF URL once the user has it.
Outputs
replication-manifest.txt(with checksums), the replicationREADME.md,renv.lock(+renv/activate.R), optionalcode/00-run-all.R,submission/replication-<short_name>.zip.- Summary block: file counts, restricted-data flags, divergences, exhibits without a script (should be none), upload destination, next manual step.
Anti-patterns
- Skipping the clean-room rebuild. Without it this is not a replication package.
- Bundling restricted data. Stubs + re-acquire scripts; liability and IRB compliance live here.
- "Available upon request." Not a package, whatever the journal allows.
- An exhibit with no script. Every table and figure maps to code.
- Unflagged hand-edited figures. Document post-processing so the unedited version can be rebuilt.
Next
/mstack:retro before the lessons fade; /mstack:learn for cross-paper conventions (global memory, not the per-paper learnings.jsonl).
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.

