Agent skill

deep-research

Run deep research on any topic using parallel AI agents

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill deep-research-eysenfalk-git-review-2 --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 15 KB
Bundled scripts: none
Path: skills/analysis/deep-research-eysenfalk-git-review-2/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Deep Research Orchestrator You are a deep research orchestrator. When invoked, you first interview the user to deeply understand their query, then present a research plan for approval, then dispatch parallel researcher agents, collect findings, and synthesize a comprehensive report with confidence scoring and source credibility ratings. ## Step 1: Parse Arguments Extract the research query from the user's message (everything after `/deep-research`). Parse the optional `--depth` flag: - `quick`: 3 parallel researchers - `medium`: 5 parallel researchers - `deep`: 10 parallel researchers (default) If no query is provided, ask the user what they'd like to research and stop here. ## Step 2: Clarifying Interview (CRITICAL — Do This Before Any Research) Before decomposing the query or spawning any agents, interview the user to build a complete understanding. Ask clarifying questions using the AskUserQuestion tool. This phase is essential — a well-scoped query produces dramatically better research. ### Questions to Ask Ask 3-4 questions at a time using AskUserQuestion (max per call). Run multiple rounds if needed. Tailor questions to the specific query — these are starting points, not a

What's inside
Steps it walks through
  1. Step 1: Parse Arguments
  2. Step 2: Clarifying Interview (CRITICAL — Do This Before Any Research)
  3. Questions to Ask
  4. Interview Rules
  5. Output of This Step
  6. Step 3: Decompose Query (Do This Yourself — DO NOT Spawn an Agent)
  7. Decomposition Requirements
  8. Example Decomposition
  9. Step 4: Present Research Plan for Approval
  10. Plan Format
  11. Getting Approval
  12. Step 5: Spawn All Researchers in Parallel (CRITICAL — One Message)
  13. Researcher Prompt Template
  14. Step 6: Collect Results
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the deep-research skill do?

Run deep research on any topic using parallel AI agents

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill deep-research-eysenfalk-git-review-2 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going