Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/ase-supplementary
Use when deciding what belongs in the 10-page ASE (IEEE/ACM Automated Software Engineering) paper body versus the artifact and supplementary material, splitting content by decision-criticality so nothing that decides acceptance lives outside the reviewed pages under the 10+2 budget.
Passed 18 of 22 test cases with the skill, and 18 of 22 without it.
and 1 more in the full report
2 fixed16 passed either way2 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
I am preparing a research paper draft and accompanying artifact repository for submission to ASE. Could you review our current layout where we placed the main technique description, core benchmark results, and main threats to validity in the main text, while putting detailed configuration files, raw execution logs, and full subject breakdown tables into the supplementary package? Please evaluate our setup and provide a formatted audit report covering whether key paper components are properly situated in the main draft, where data availability is stated, what belongs exclusively in the artifact, whether the paper stands on its own, and if double-anonymous constraints are preserved.
| Checked | Without skill | With skill |
|---|---|---|
| The evaluation confirms that decision-critical elements must fit within the 10-page main text limit. | Missed | Passed |
| The report requires the Data Availability Statement to be located inside the 10-page body after the Conclusions section. | Missed | Passed |
The instructions your model reads when the skill loads.
Split content by decision-criticality. ASE gives you 10 pages of body (plus 2 for references), and reviewers judge the paper on those pages. The artifact and any supplementary material support reproduction and reuse — they do not carry the argument. The failure mode is exiling a decision-critical result to the artifact and assuming reviewers will dig for it; they judge what is in the body.
If a result decides acceptance, it lives in the body even if space is tight; cut elsewhere.
| Content | Where | Why |
|---|---|---|
| Task, technique, headline evaluation, closest-baseline comparison, key ablation | Body (≤10 pp) | Decision-critical; reviewers score these |
| Central threats-to-validity argument | Body | Construct/oracle validity is judged, not reproduced |
| Data Availability Statement | Body, after Conclusions, inside 10 pp | Mandatory and reviewed |
| Full config files, seeds, environment | Artifact | Reproduction detail, not an argument |
| Complete/extra result tables, extra subjects | Artifact / supplement | Support, not headline |
| Proofs, derivations too long for the body | Artifact / supplement (if the venue permits) | Verification detail |
| Raw logs, cached LLM outputs, dataset snapshots | Artifact | Provenance and reuse |
test cases passed, vs 18 / 22 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.