This walks you through building a research framework before you dive deep into a topic. It starts by drafting an initial structure from Claude's knowledge, then spins up a web search agent to find recent additions and gaps, and finally outputs two YAML files: one with your research targets and execution config (batch size, parallel agents), another with field definitions organized by detail level. The workflow is pretty rigid about its prompts, which means consistent output but less flexibility if you want to tweak the search strategy. Best for structured competitive analysis or technology comparisons where you need a repeatable framework. Once you have the outline, you'd use the follow-up commands to actually execute the deep research phase.

install copies · 90 days. Times the install command was copied on this site in the last 90 days, bots filtered.
5
skills.sh installs
770
GitHub stars
2.5K
last updated
Aug 21, 2026

Install

$ npx -y skills add weizhena/deep-research-skills --skill research --agent claude-code

Installs into .claude/skills of the current project.

Files

Research Skill - Preliminary Research

Trigger

/research <topic>

Workflow

Step 1: Generate Initial Framework from Model Knowledge

Based on topic, use model's existing knowledge to generate:

  • Main research objects/items list in this domain
  • Suggested research field framework

Output {step1_output}, use request_user_input to confirm:

  • Need to add/remove items?
  • Does field framework meet requirements?

Step 2: Web Search Supplement

Use request_user_input to ask for time range (e.g., last 6 months, since 2024, unlimited).

Parameter Retrieval:

  • {topic}: User input research topic
  • {YYYY-MM-DD}: Current date
  • {step1_output}: Complete output from Step 1
  • {time_range}: User specified time range

Hard Constraint: The following prompt must be strictly reproduced, only replacing variables in {xxx}, do not modify structure or wording.

Launch 1 web-search-agent (background), Prompt Template:

prompt = f"""## Task
Research topic: {topic}
Current date: {YYYY-MM-DD}

Based on the following initial framework, supplement latest items and recommended research fields.

## Existing Framework
{step1_output}

Sponsors

Details

Repository
github.com/weizhena/deep-research-skills
Category
Data Science & ML
First seen
Jun 3, 2026

More from weizhena/deep-research-skills

All 5
1boshu2 avatarpr-researchboshu2/agentopsResearch an upstream repo.757skills.sh installs
2aradotso avatartaiwan-equity-research-coveragearadotso/trending-skillstaiwan equity research coverage755skills.sh installs
3alchaincyf avatarhuashu-researchalchaincyf/huashu-skills结构化网络调研流程,确保调研成果增量保存到文件,不因会话截断丢失。当用户说"调研"、"搜索资料"、"帮我查一下"、"了解一下"、"最新信息"时使用此技能。753skills.sh installs
4ruvnet avatarresearch-synthesizeruvnet/rufloSynthesize research findings from memory into structured reports with evidence grading, contradiction resolution, and actionable recommendations752skills.sh installs
5alinaqi avatarposthog-analyticsalinaqi/claude-bootstrapposthog analytics736skills.sh installs
6alirezarezvani avataranalytics-trackingalirezarezvani/claude-skillsSet up, audit, and debug analytics tracking implementation — GA4, Google Tag Manager, event taxonomy, conversion tracking, and data quality. Use when building a731skills.sh installs