Collaboratively build and refine paper screening rubrics through brainstorming, test-driven development, and iterative feedback
SkillScore68Maintained
Automatic
◆Research pack
Last verified 8/8/2026
What it changes
Passed 15 of 22 test cases with the skill, and 5 of 22 without it.
Without skill23%
With skill68%
Checks it passed that the model alone missed
The response keys entries in abstracts-cache.json by paper DOI or PMID.
The response saves the approved rubric definition into screening-criteria.json.
The response states that 70% accuracy fails to meet the 80% accuracy requirement.
and 12 more in the full report
10 fixed5 passed either way7 still failing0 broke
Pass-rate lift
+45 pp
Tokens
+201%
Agent turns
0%
Response time
-42%
Model gemini-3.6-flashMeasured 8/8/2026v115 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 10
Prompt
After finishing the brainstorming session for a new literature search on kinase inhibitors, what is the exact step to complete Phase 1 before creating the test set?
What was checked, without and with the skill
Checked
Without skill
With skill
The response asks the user to confirm whether the proposed scoring logic matches expectations.
Missed
Passed
The response saves the approved rubric definition into screening-criteria.json.
Missed
Passed
case-19 · gemini-3.6-flash · 8/8/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md595 linessingle file
Building Paper Screening Rubrics
Overview
Core principle: Build screening rubrics collaboratively through brainstorming → test → refine → automate → review → iterate.
Good rubrics come from understanding edge cases upfront and testing on real papers before bulk screening.
When to Use
Use this skill when:
Starting a new literature search that will screen 50+ papers
Current rubric misclassifies papers (false positives/negatives)
Need to define "relevance" criteria before automated screening
Want to update criteria and re-screen cached papers
Building helper scripts for evaluating-paper-relevance
When NOT to use:
Small searches (<20 papers) - manual screening is fine