Skip to main content
AI/MLjmagly

grade-report

Generate corpus-wide GRADE quality distribution report

Stars
141
Source
jmagly/aiwg
Updated
2026-05-31
Slug
jmagly--aiwg--grade-report
View on GitHubRaw SKILL.md

// install — copy + paste into any project

mkdir -p .claude/skills && curl -fsSL https://raw.githubusercontent.com/jmagly/aiwg/HEAD/agentic/code/frameworks/sdlc-complete/skills/grade-report/SKILL.md -o .claude/skills/grade-report.md

Drops the SKILL.md into .claude/skills/grade-report.md. Works with Claude Code, Cursor, and any agent that loads SKILL.md files from .claude/skills/.

GRADE Report Command

Generate a report on the evidence quality distribution across the research corpus.

Instructions

When invoked, analyze and report on corpus quality:

  1. Scan Quality Assessments

    • Load all assessments from .aiwg/research/quality-assessments/
    • Load frontmatter quality fields from all sources

  2. Calculate Distribution

    • Count sources by GRADE level (HIGH, MODERATE, LOW, VERY LOW)
    • Count sources by source type
    • Identify unassessed sources

  3. Generate Report

    • Summary table: GRADE distribution
    • Source type breakdown
    • Unassessed sources list
    • Hedging compliance summary (overclaiming count)
    • Recommendations for corpus improvement

  4. Save Report

    • Display to user
    • Optionally save to .aiwg/reports/grade-report.md

Arguments

  • --brief - Show summary only
  • --unassessed - Show only unassessed sources
  • --save - Save report to .aiwg/reports/grade-report.md

References

  • @.aiwg/research/docs/grade-assessment-guide.md - GRADE methodology
  • @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/agents/quality-assessor.md - Quality Assessor
  • @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/schemas/research/quality-dimensions.yaml - Quality schema