Agent skill · research science · daymade
deep-research
Creates reusable, source-traced research reports and coordinates provider/mode lanes with original exports. Use for 深度研究, 调研报告, literature reviews, market or company research, and ChatGPT/Kimi/UniFuncs research routes. Technology choice uses tech-selection; competitor code uses competitors-analysis.
Why this skill is useful
Adds a structured multi-pass research workflow with evidence tracking and source governance that the AI cannot generate on its own.
What it needs
About 11k tokens when loaded. Last updated 2026-08-07. 1,320 stars on the source repository.
What this skill does
Deep Research Create high-fidelity research reports with strict format control, evidence mapping, source governance, and multi-pass synthesis. Architecture: Lead Agent + Subagents Context discipline: Keep raw search-result noise in task workspaces. Pass evidence packets to the lead agent, including locators and short source excerpts. Notes are routing aids, not authorities: the lead agent must open the original source for every load-bearing claim, conflicting claim, and exact figure/date/quotation used in the report. Run and asset contract — every invocation Before external retrieval, read research-asset-contract.md. Create or resume a durable project study for single-route and multi-route research alike. Search its explicit prior-study catalog, open relevant earlier originals and record reuse/adapt/reject decisions. Draft the decision questions and provider × actual-mode lanes in study.json. Write one exact dispatchcontext with the user-supplied seed URL, named entities, and verified codes or other identifiers needed for the query. Include that string in every lane prompt; researchassets.py start rejects an omission. Capture the user's named seed article or document as an original before external dispatch, and follow the provider handoff when a provider cannot read its URL. A model workspace may not see the user's link or local files just because the coordinator does. Then run providerruns.py plan. Keep every user-requested mode in the plan; a route that adds no value, is unavailable or lacks paid authorization gets a reasoned deferred event. A report assembled from direct web search and internal subagents still needs a direct-source lane and the same archive. New studies use schema 2's request mode contract: archive the original request and accepted workflow, interpret the required modes independently of the execution lanes, and map each to matching lanes. An explicit empty mode inventory is valid when none was requested; a missing contract is not. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills daymade/deep-research