Topic Briefing Skill for ChatGPT: Deduplicate Signals and Offer Editorial Choices
Turn supplied research signals into a concise topic menu. Rank by evidence, timing, and audience fit, then expand the option the editor selects.
中文Install in ChatGPT
Use an eligible ChatGPT workspace with permission to create skills and, for uploads, upload permission. The installation path for this text-only adaptation was checked against OpenAI documentation. Workspace runtime verification is pending.
- Download community/agents/research-agent/.claude/skills/topic-briefing/SKILL.md from the pinned GitHub source. Keep the name, description, and instructions for topic-briefing together as a standalone text skill.
- In a ChatGPT workspace with skills and uploads enabled, open Plugins, Skills, Create, and Upload from your computer. Choose a skill package format accepted by the file picker. You can also choose Create with editor and enter the original name, description, and instructions.
- After the scan completes, check that topic-briefing appears in Installed. Type @ in a new chat, select the skill, and use the fictional example on this page to check the output.
Example task
Three fictional signals include two write-ups of one mobile library pilot and an announcement of added seats. Give two distinct topics and evidence checks for each.What to check
Group the two pilot write-ups together and keep the seat announcement separate. For each topic, state audience value, known facts, and missing data. Wait for selection before expanding a detailed brief.
Original SKILL.md on GitHub · Updated
Frequently asked question
Should the highest-popularity topic always lead?
Consider evidence strength and audience fit. A popular item with thin evidence can remain an option with a named verification need.