Weizhena/Deep-Research-skills

Preliminary Research builds an initial research framework from model knowledge, supplements it with web search, and generates outline.yaml and fields.yaml to guide deeper research.

Research conducts preliminary research on a topic, generating an initial framework from model knowledge, supplementing it with web search results, and producing outline.yaml and fields.yaml files for subsequent deep research. Use it for academic research, benchmark research, technology selection, and similar tasks requiring structured outlines.

Research creates a preliminary research outline for a target topic, combining internal knowledge, web search, and user-defined fields. Use it before deep research for academic surveys, benchmark evaluations, or technology selection.

Research Add Fields appends new field definitions to an existing research outline fields.yaml file. Use it when a deep research topic needs additional fields sourced from user input or web search.

Research Add Fields adds new field definitions to an existing research outline's fields.yaml. Use it when you need to expand the structure of a research topic with user-provided or web-searched fields.

Research Add Items appends new research objects (items) to an existing outline.yaml file, prompting the user for supplements and optionally launching web search to find more.

Research Add Items appends new items to an existing research outline.yaml. Use it after /research-add-items to supplement a deep research topic with more targets, optionally triggering web search for discovery.

Research Deep reads a research outline, launches independent web-search agents for each item in batches, disables task output, and writes validated structured JSON results.

Research Deep reads a research outline and launches independent agents for each item to perform deep research, writing structured JSON results with validation and resume support.

Research Deep reads a research outline (outline.yaml) and launches independent background agents to investigate each item, writing structured Chinese JSON results with validation and checkpoint resumption. Use it to run multi-item deep research pipelines in Claude Code.

Research Report summarizes deep research results into a markdown report, covering all fields and skipping uncertain values. Use it after collecting JSON research outputs to produce a navigable report with TOC and categorized details.

Research Report converts deep research JSON results into a structured markdown report, covering all defined fields and skipping values marked as uncertain. Use it after a research agent collects data to produce a clean, navigable summary with a table of contents.

Research Report aggregates deep research results into a structured markdown report, covering all fields and skipping uncertain values. Use it after a research run to generate a navigable markdown report with table of contents and detailed sections.