Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/cscw-artifact-evaluation
Use when packaging what stands behind a CSCW paper — systems, analysis pipelines, codebooks, instruments, datasets from real communities — for review-time scrutiny and post-acceptance release, where community-data ethics constrain release more than any badge checklist.
Passed 23 of 23 test cases with the skill, and 14 of 23 without it.
and 12 more in the full report
9 fixed14 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
I am writing the CSCW artifact release README.md setup documentation. I'm providing a detailed 25-step manual build process requiring manual compilation of 10 dependencies. What guideline should I follow for setup complexity in the release README?
| Checked | Without skill | With skill |
|---|---|---|
| Specifies that setup instructions in the README should take 5 or fewer steps. | Missed | Passed |
The instructions your model reads when the skill loads.
CSCW has no artifact-evaluation committee stamping badges; the "evaluators" of your artifacts are the reviewers deciding whether to trust your methods, and later the researchers and the studied communities themselves who encounter the released materials. That second audience is the venue's distinctive constraint: a CSCW artifact release is an act with consequences for real people who never signed your consent form.
| Artifact | Review-time form | Post-acceptance form | Governing constraint |
|---|---|---|---|
| Study instruments (guides, surveys) | Anonymized in supplement | Public archive | Institution redaction only |
| Codebooks | Anonymized in supplement | Public archive | Paraphrased exemplars only |
| Analysis code | Anonymized archive | Public repository + DOI archive | Strip identity from history |
| Built systems / prototypes | Screenshots/video + code where feasible | Open source if maintainable | Third-party assets, API keys |
| Trace datasets | Aggregates or synthetic sample | Aggregates; raw only if terms + ethics allow | Platform ToS + re-identification risk |
| Interview/field data | Never | Almost never | Consent scope is absolute |
Before releasing any dataset or exemplar text derived from an online community, run the adversary exercise — assume a motivated actor (a journalist, a harasser, a platform admin, a community member with a grudge):
Document the outcome in a short release memo; it becomes the honest core of the
paper's data-availability statement (cscw-reproducibility).
test cases passed, vs 14 / 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.