Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/academic-paper-verify
Thoroughly verify all code, tables, figures, modeling decisions, and quantitative claims in an academic paper against its source R scripts and output files.
Passed 15 of 20 test cases with the skill, and 8 of 20 without it.
and 7 more in the full report
8 fixed10 passed either way6 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
Write out the required markdown section heading outline for the final consolidated paper verification report.
| Checked | Without skill | With skill |
|---|---|---|
| The top-level heading is # Paper Verification Report. | Missed | Passed |
| The required second-level sections include ## Table-by-Table Results, ## Inline Claims Results, ## Code Review Findings, ## Replication Test Results, and ## Recommendations. | Missed | Passed |
The instructions your model reads when the skill loads.
A systematic skill for verifying the integrity and replicability of an academic research paper. This covers everything from individual coefficient checks to full end-to-end replication.
Verification proceeds in six phases. Each phase produces structured output. Do not skip phases - earlier phases feed into later ones.
Phase 1: Discovery -> inventory of all project files, scripts, outputs, paper
Phase 2: Table Audit -> cross-check every number in every table
Phase 3: Inline Claims -> verify quantitative claims in paper body text
Phase 4: Code Review -> audit R scripts for correctness, modeling decisions, data pipeline
Phase 5: Manifest Build -> create verification_manifest.json linking claims to code
Phase 6: Replication -> write and run tests/verify_replication.R, fix failures
.Rproj files, README, or ask the user.references/phase-details.md for the full procedure for each phase.references/common-pitfalls.md for known failure modes to watch for.Scan the entire project and build an inventory. You need to know what you're working with before you can verify anything.
Find and catalog:
.R and .Rmd scripts (note execution order if a master script exists).csv, .rds, .tex, .txt, .log in results/, output/, tables/, etc..tex in the root or paper/ or draft/ directory.csv, .dta, .rds, .xlsx in data/ or similarProduce: A file inventory printed to the console, organized by type, with notes on what each script appears to do (based on filename and a quick scan of its first ~30 lines).
test cases passed, vs 8 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.