Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Replicate Study Skill · aperivue | DecimalAI

scienceby aperivue

Replicate Study Skill

aperivue/replicate-study

Source aperivue/medsci-skills ↗License MIT

Replicate an existing cohort study's methodology on a different database. Extracts study design from a source paper, maps variables to the target DB via harmonization table, generates analysis code, and produces a replication difference report.

SkillScore77Maintained

Automatic

Research pack

Last verified 8/24/2026

What it changes

Passed 15 of 19 test cases with the skill, and 10 of 19 without it.

Without skill55%

With skill77%

Checks it passed that the model alone missed

The response specifies generating an R script named analysis_code.R.
The response specifies creating replication_report.md in the working directory.
The generated code subsets the survey design object directly for subgroup analyses.

and 4 more in the full report

5 fixed12 passed either way5 still failing0 broke

Pass-rate lift: +23 pp
Tokens: +59%
Agent turns: 0%
Response time: -16%

Model gemini-3.6-flashMeasured 8/24/2026v1 · latest is v217 of 22 cases passed with skill · 19 comparable

Tokens, turns and time describe resource use, not a dollar price.

This benchmark measured an earlier version of the skill.

A newer attempt on gemini-3.6-flash on 10/3/2026 did not produce a publishable comparison (not comparable). The snapshot above is the previously measured run.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/aperivue-replicate-study/SKILL.md https://app.decimal.ai/s/aperivue-replicate-study/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add aperivue-replicate-study, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/aperivue-replicate-study/ and pins it in .decimal/skills.lock

decimalai skills add aperivue-replicate-study

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/aperivue-replicate-study/SKILL.md https://app.decimal.ai/s/aperivue-replicate-study/SKILL.md

Raw file: /s/aperivue-replicate-study/SKILL.md ↗ · machine-readable summary at /s/aperivue-replicate-study.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 4

Prompt

When attempting to map covariates from a published cardiovascular risk study onto target dataset `/data/knhanes_subset.csv`, we discovered that dietary sodium intake was not collected in the target survey wave. What flag should be assigned to this variable in the mapping report?

What was checked, without and with the skill
Checked	Without skill	With skill
The response classifies unmapped variables as NOT_AVAILABLE or PROXY_AVAILABLE in the mapping report.	Missed	Passed

case-09 · gemini-3.6-flash · 8/24/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md117 lines4 files

Replicate Study Skill

Apply a published study's methodology to a different database and report every place the target database forced a deviation.

Inputs

Source paper: PDF, DOI, or markdown of the paper to replicate
Target database path: CSV/SAS data file(s) to use
Harmonization table (optional): CSV mapping source → target variables
- Default: ${CLAUDE_SKILL_DIR}/references/harmonization_knhanes_nhanes.csv (if KNHANES↔NHANES)

Reference Files

${CLAUDE_SKILL_DIR}/references/methodology_extraction_template.md — checklist for extracting study design
${CLAUDE_SKILL_DIR}/references/harmonization_knhanes_nhanes.csv — KNHANES↔NHANES variable mapping (67 rows)
${CLAUDE_SKILL_DIR}/references/harmonization_3country.csv — KNHANES+NHANES+CHNS 3-country mapping (46 rows)
Upstream templates (read on demand):
- ${CLAUDE_SKILL_DIR}/../write-paper/references/paper_types/nhis_cohort.md
- ${CLAUDE_SKILL_DIR}/../write-paper/references/paper_types/cross_national.md
- ${CLAUDE_SKILL_DIR}/../analyze-stats/references/analysis_guides/survey_weighted.md
- ${CLAUDE_SKILL_DIR}/../analyze-stats/references/analysis_guides/propensity_score.md

Workflow

Phase 1: Source Paper Analysis

Read the source paper (PDF → text, or markdown).
Extract the methodology by filling methodology_extraction_template.md: study design, database (name, country, years, N), population (inclusion/exclusion, age range), exposure and outcome (variable, definition, coding), covariates with definitions, statistical methods (regression type, adjustment models, subgroup analyses), survey design (weights, strata, PSU), and every sensitivity analysis.
Outdated source definitions: if the source used a pre-2023 definition that has since been superseded (e.g., NAFLD → MASLD 2023, CKD-EPI 2009 → 2021 race-free), call /define-variables to cross-check whether to mirror the legacy definition (pure replication) or upgrade to the current one (extension). Record the choice in the difference report.
Output: structured extraction summary for user review.

Phase 2: Variable Mapping

Track record

Benchmark

15 / 19

test cases passed, vs 10 / 19 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 10/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

aperivue / medsci-skills

skills/replicate-study/SKILL.md

View on GitHub ↗

License MITImported 10/3/2026Version v2Bundled 3 files

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

brycewang-stanford/replicate-paperRun a full 6-phase autonomous replication of a biomedical/epidemiology paper against UK Biobank or similar cohort data, producing Python and R scripts plus a validated replication report. Use when asked to replicate a paper end-to-end, or when invoked as /replicate-paper [paper.pdf] [data.csv|dta].Close match+41 pp pass-rate lift

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Replicate Study Skill

Inputs

Reference Files

Workflow

Phase 1: Source Paper Analysis

Phase 2: Variable Mapping

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills