GRADE Report Skill for ChatGPT: Summarize Evidence Ratings and Unassessed Sources
Reconcile supplied quality assessments with a source inventory. Count existing ratings by level and source type, list unassessed items, and flag summary claims that exceed recorded evidence.
中文Install in ChatGPT
Requires a ChatGPT workspace where you can create skills. This is a text adaptation of the pinned GitHub source.
- Review the inputs and outputs in the pinned agentic/code/plugins/codex-sdlc/skills/grade-report/SKILL.md.
- In ChatGPT, open Plugins, Skills, Create, and Create with editor.
- Write the skill rules using the workflow described here. Provide existing ratings, source types, and any conclusion wording to check.
- Save the skill and check the fictional example in a new chat.
Example task
A fictional inventory has A rated high, B low, and C unassessed. B's draft says it was proven for every sample, while its assessment covers one small sample. Produce counts and a claim check.What to check
Report one high, one low, and one unassessed out of three sources. Flag B's limited scope and C's missing rating while preserving the supplied assessments.
Original SKILL.md on GitHub · Updated
Frequently asked question
Should missing ratings be counted as very low?
Report them as unassessed. Very low is an assigned evidence rating, and keeping the groups separate preserves assessment coverage.