Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/workflows:review
Run multi-agent econometric review on estimation code, identification arguments, and research artifacts
Passed 10 of 16 test cases with the skill, and 7 of 16 without it.
and 5 more in the full report
7 fixed7 passed either way6 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
A review finding highlights minor table formatting alignment issues in a LaTeX output snippet that do not alter any numerical values. Which P-scale severity level should be assigned?
| Checked | Without skill | With skill |
|---|---|---|
| Assigns P3 severity to minor cosmetic and table formatting suggestions. | Passed | Passed |
| Leaves P3 severity findings to author's discretion. | Missed | Passed |
The instructions your model reads when the skill loads.
Pipeline mode: This command operates fully autonomously. All decisions are made automatically.
Perform exhaustive econometric and methodological review using multi-agent parallel analysis. Domain-specific reviewers check estimation quality, identification strategy, numerical stability, and mathematical rigor.
<review_target> #$ARGUMENTS </review_target>
Eligibility Check
Before launching review agents, verify there is something to review. If no research artifacts are found (no estimation code, no proofs, no pipeline files, no data scripts, no output files), state "No research artifacts found to review" and stop. Do not launch agents against an empty target.
Determine Review Target
The review is artifact-centric: it reviews research files (estimation code, proofs, pipelines, data scripts), not git metadata. Determine the target in priority order:
estimation.py, src/models/, proof.tex) → review those artifacts directlyplan-3) → find the plan in docs/plans/, review files it referencesgh pr view --json filesClassify Artifacts
Scan the target files and classify by type:
estimation_code: *.py with statsmodels/scipy.optimize/pyblp/linearmodels imports
*.R with fixest/lfe/AER/gmm imports
*.jl with Optim/NLsolve imports
*.do with reg/ivregress/gmm commands
simulation_code: Monte Carlo loops, DGP code, bias/RMSE computation
proofs: *.tex with theorem/proof environments, *.md with derivation sections
pipeline_files: Makefile, Snakefile, dvc.yaml, master.do
data_code: data loading, cleaning, merge operations
test cases passed, vs 7 / 16 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.