Enterprise Search Strategy Skill for ChatGPT: Decompose Questions Into Source-specific Queries
Extract entities, date range, scope, and intent from a question. Plan queries for docs, trackers, or messages, and rank supplied results by relevance, authority, and timing.
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 enterprise-search/skills/search-strategy/SKILL.md.
- In ChatGPT, open Plugins, Skills, Create, and Create with editor.
- Write the skill rules using the workflow described here. Provide the authorized source scope, question, date window, and any existing results.
- Save the skill and check the fictional example in a new chat.
Example task
A fictional question asks when the team decided to pause legacy exports. Input includes an old spec, recent meeting notes, and a later implementation ticket. Draft queries and rank the evidence.What to check
Treat it as a decision and timing question. Prioritize meeting conclusions with attributable links, use the ticket for execution evidence, and retain the spec as dated background.
Original SKILL.md on GitHub · Updated
Frequently asked question
When does the user need a clarification first?
Clarify when a missing project, version, or date would materially change the search and cannot be resolved from context. Where useful, list assumptions for alternate queries.