Skip to content
Development
Skill

/deep-research

Deprecated name; the skill formerly here is now opinionated-research:interactive-research. Retained as a context-level notice because Claude Code now ships a built-in deep-research workflow that runs one-shot, non-interactive fan-out research (no conversation after the report).

From plugin
opinionated-claude-skills
919 skills3 agents
Install
$ npx -y skills add Pyroxin/opinionated-claude-skills --skill deep-research --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/deep-research

Context preview

The summary Claude sees to decide when to auto-load this skill.

Deprecated name; the skill formerly here is now opinionated-research:interactive-research. Retained as a context-level notice because Claude Code now ships a built-in deep-research workflow that runs one-shot, non-interactive fan-out research (no conversation after the report).

SKILL.md

deep-research.SKILL.md
name: deep-research
description: Deprecated name; the skill formerly here is now opinionated-research:interactive-research. Retained as a context-level notice because Claude Code now ships a built-in deep-research workflow that runs one-shot, non-interactive fan-out research (no conversation after the report). interactive-research instead runs a persistent agent team you can keep questioning after the report is delivered. Guidance for Claude: when the user makes a research request, ask whether they want the interactive team (interactive-research) or the built-in non-interactive deep-research workflow before starting.

Renamed — routing notice

This skill was renamed to `opinionated-research:interactive-research`. It's kept only so the old name doesn't silently resolve to the wrong thing, and to remind Claude to disambiguate. Two different tools now answer to "deep research":

  • **`opinionated-research:interactive-research`** (this plugin): a persistent

agent team that researches the topic and *stays alive*, so you can question the researchers, push back on the synthesis, and refine after the report is delivered.

  • **Built-in `deep-research`** (ships with Claude Code): a one-shot workflow —

fan-out search, fetch, adversarial verification, synthesized report. Fast and thorough, but *non-interactive*: when it finishes, there's nothing left to talk to.

**When a user asks for research, ask which they want before proceeding**, then invoke the chosen tool. Don't treat this notice itself as a research tool.

Read more
Ships withopinionated-claude-skills

This project descends from the personal prompts I'd been keeping for Claude Code prior to the release of skills and plugins. Over time it's also evolved into a sandbox where I figure out what makes Claude reliably good at a task, and find prompts that work.

Get the whole plugin

Other skills on opinionated-claude-skills.