Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/cscw-supplementary
Use when assembling supplementary materials for a CSCW submission — appendices, codebooks, interview guides, survey instruments, analysis code, and data extracts — deciding what accompanies a journal-model paper, anonymized end to end and consistent across R&R rounds.
Passed 20 of 23 test cases with the skill, and 15 of 23 without it.
and 3 more in the full report
5 fixed15 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
What is the general decision rule for deciding whether an artifact belongs in the main CSCW paper/appendix versus an external supplementary file versus nowhere?
| Checked | Without skill | With skill |
|---|---|---|
| States that items required to trust the method belong in the supplementary file. | Missed | Passed |
| States that unconsented participant data belongs nowhere. | Missed | Passed |
The instructions your model reads when the skill loads.
Supplements at CSCW serve a journal-style review: they let reviewers verify the methods section without bloating a paper already policed by the contribution-vs- length standard. Because Revise and Resubmit sends the paper back to the same reviewers, the supplement is also a versioned record — round-two reviewers can and do compare it against round one.
| Material | Main paper | Appendix | Separate supplement file |
|---|---|---|---|
| Method summary + key instrument excerpts | ✓ | ||
| Full interview guide / survey instrument | ✓ | ✓ if long | |
| Codebook (definitions + paraphrased exemplars) | ✓ | ✓ | |
| Trace-pipeline ledger and attrition table | summary | ✓ | code as archive |
| Analysis scripts | ✓ (archive) | ||
| Additional tables/robustness checks | ✓ | ✓ | |
| Consent forms / recruitment text | ✓ | ||
| Raw transcripts, identifiable data | never | never | never |
Decision rule: anything a reviewer needs to evaluate a claim belongs in the paper or appendix; anything a reviewer needs to trust the method belongs in the supplement; anything participants did not consent to share belongs nowhere.
The supplement is the classic identity leak at this venue, because it aggregates exactly the artifacts teams forget to scrub:
/home/username/), git history, package
lockfiles with private registry URLs, notebook execution metadata. Export clean
archives, never a cloned .git.test cases passed, vs 15 / 23 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.