Run one of the ML/CS reproducibility checklists (ML Reproducibility Checklist, REFORMS, NeurIPS Paper Checklist, Model Cards, Datasheets for Datasets) against a paper as a reader-side audit, producing a category (Yes/No/NA) plus free-text reason per item. Use this whenever the user wants a reproducibility/completeness self-check run on an ML or CS paper — invoke this directly, it has no study-design gate in this package since these checklists are engineering self-audits, not clinical-study tools
SkillScore64Maintained
Automatic
◆AI Engineer pack
Last verified 9/7/2026
What it changes
Passed 13 of 21 test cases with the skill, and 5 of 21 without it.
Without skill23%
With skill64%
Checks it passed that the model alone missed
Frames the checklist item as a verification question.
Appraises the systematic review using PRISMA reporting standards.
Includes a free-text reasoning column alongside each status rating.
and 7 more in the full report
9 fixed5 passed either way8 still failing0 broke
Pass-rate lift
+41 pp
Tokens
+56%
Agent turns
0%
Response time
+24%
Model gemini-3.6-flashMeasured 9/7/2026v114 of 22 cases passed with skill · 21 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 9
Prompt
Transform this self-certification item into the audit format: 'The dataset split code is included in src/data/split.py.'
What was checked, without and with the skill
Checked
Without skill
With skill
Frames the checklist item as a verification question.
Missed
Passed
case-13 · gemini-3.6-flash · 9/7/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md21 lines2 files
Dual Column Self-Check
Category (Yes/No/NA) + free-text reason per item, across 5 ML/CS reproducibility checklists. Originally author-facing self-certification tools, reversed here for reader-side auditing — each item's framing must be flipped to a question before being answered.
Execution
Subagent — spawned via spawn-agent skill.
No upstream gate (intentional, not a gap)
Unlike quality-appraisal-checklist/reporting-standard-checklist, this SOP has no in-edge from study-design-tool-gate in the graph — its 5 checklists are ML/CS engineering self-audits, not tied to a clinical study design, so no study-design dispatch was ever drawn to it (spec §5's flagged note). Do not add a gate dependency here without revisiting that decision explicitly.
Available SOPs
SOP
When to use
spawn-agent
Spawn a customized CC subagent with full MCP tool access.