Universal Meta-Analysis Codebook v2.2 - AI-Human collaboration for meta-analysis data extraction. 4-layer design: Identifiers, Statistics, AI Provenance, Human Verification. Integrates with C5/C6/C7 agents and Category I systematic review pipeline. Triggers: meta-analysis, codebook, data extraction, Hedges g, effect size
SkillScore82Maintained
Automatic
◆Research pack
Last verified 8/8/2026
What it changes
Passed 17 of 21 test cases with the skill, and 8 of 21 without it.
Without skill36%
With skill82%
Checks it passed that the model alone missed
The framework structure assigns Layer 3 to context-specific moderators.
The cluster adjustment fields specify cluster_size, icc, and n_clusters.
An OCR rendering source subtracts 20% to yield 60% effective confidence.
and 14 more in the full report
11 fixed7 passed either way3 still failing1 broke
Pass-rate lift
+45 pp
Tokens
+130%
Agent turns
0%
Response time
-25%
Model gemini-3.6-flashMeasured 8/8/2026v118 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 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 11
Prompt
For an extracted standard deviation metric, Method A reports 4.0 while Method B reports 4.4. Relative difference is 10% and absolute difference is 0.4. Should this be automatically reconciled or sent to human review?
What was checked, without and with the skill
Checked
Without skill
With skill
The discrepancy falls within the 15% relative tolerance threshold for standard deviations.
Missed
Passed
The standard deviation values do not trigger mandatory human conflict review.
Missed
Passed
case-16 · 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.md439 linessingle file
Universal Meta-Analysis Codebook
Version: 2.2
Status: Production
Codex Review: APPROVE WITH MINOR CHANGES (2026-01-26)
Update: Context-specific extensions (2026-01-26)
Purpose
A universal, AI-Human collaboration codebook for meta-analysis that enables:
AI extraction from PDFs (RAG/OCR) with confidence tracking
Human verification of AI-extracted values
100% human-verified data through structured workflow
Integration with Diverga C5/C6/C7 agents and Category I pipeline
Context-specific extensions for domain-specific moderator variables
Context-Specific Extensions
The Universal Codebook supports project-specific moderator layers that extend the base 4-layer structure. Each meta-analysis context may have unique moderator variables.