Ready to supercharge your AI agents?

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

Skill: /replicate-paper · brycewang-stanford | DecimalAI

scienceby brycewang-stanford

Skill: /replicate-paper

brycewang-stanford/replicate-paper

Source brycewang-stanford/Auto-Empirical-Research-Skills ↗License NOASSERTION

Run 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.

SkillScore73Maintained

Automatic

Research pack

Last verified 8/9/2026

What it changes

Passed 12 of 16 test cases with the skill, and 5 of 16 without it.

Without skill32%

With skill73%

Checks it passed that the model alone missed

Specifies exact matching with zero margin for integer counts
Reassesses the standard error clustering level specification
Specifies a standard error tolerance threshold of plus or minus 0.05

and 6 more in the full report

9 fixed7 passed either way6 still failing0 broke

Pass-rate lift: +41 pp
Tokens: +49%
Agent turns: 0%
Response time: -46%

Model gemini-3.6-flashMeasured 8/9/2026v116 of 22 cases passed with skill · 16 comparable

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

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/brycewang-stanford-replicate-paper/SKILL.md https://app.decimal.ai/s/brycewang-stanford-replicate-paper/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add brycewang-stanford-replicate-paper, 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/brycewang-stanford-replicate-paper/ and pins it in .decimal/skills.lock

decimalai skills add brycewang-stanford-replicate-paper

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

curl -fsSL --create-dirs -o .claude/skills/brycewang-stanford-replicate-paper/SKILL.md https://app.decimal.ai/s/brycewang-stanford-replicate-paper/SKILL.md

Raw file: /s/brycewang-stanford-replicate-paper/SKILL.md ↗ · machine-readable summary at /s/brycewang-stanford-replicate-paper.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 6

Prompt

After completing validation steps for `papers/Evans2022.pdf`, where should the primary final replication report markdown file be saved?

What was checked, without and with the skill
Checked	Without skill	With skill
Specifies reports/Evans2022_replication_report.md as the destination	Missed	Passed

case-15 · gemini-3.6-flash · 8/9/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md230 linessingle file

Skill: /replicate-paper

Trigger: /replicate-paper [paper.pdf] [data.csv|dta] or "replicate this paper"

Purpose: Full 6-phase autonomous replication of a biomedical/epidemiology paper using UK Biobank or similar data. Produces Python and R scripts plus a polished validation report.

Invocation

/replicate-paper papers/AuthorYear.pdf data/ukb_extract.csv

Or with just: "replicate this paper" (Claude will ask for paths if not provided).

The 6-Phase Pipeline

Phase 1: Intake

Goal: Understand exactly what needs to be replicated.

Read the paper PDF (all sections: Abstract, Methods, Results, Supplementary)
Identify every table and figure that presents empirical results
For each: record the gold standard values, SEs/CIs, sample sizes, and source location
Save targets to quality_reports/[paper_name]_replication_targets.md
Summarize: original software, data source, sample N, key methods, any replication package available

Output: quality_reports/[paper_name]_replication_targets.md

Phase 2: Data Audit

Goal: Confirm what we can and cannot replicate given the available data.

Load the provided dataset (data/[filename])
Compare to paper's described sample:

Track record

Benchmark

12 / 16

test cases passed, vs 5 / 16 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 v4 — 8/2/2026

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

brycewang-stanford / Auto-Empirical-Research-Skills

skills/28-maxwell2732-paper-replicate-agent-demo/dot-claude/skills/replicate-paper/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/2/2026Version v1

Other skills for the same job

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

aperivue/replicate-studyReplicate 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.Close match+23 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

Skill: /replicate-paper

Invocation

The 6-Phase Pipeline

Phase 1: Intake

Phase 2: Data Audit

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills