Skill, /deep-research

This is the verbatim text that Claude Code 2.1.311 uses for the built-in /deep-research skill.

Where It Comes From

Bundled skill. Captured from the program with PROBE-ARG, the argument the test used in place of your input.

How to Override It

Create .claude/skills/deep-research/SKILL.md with the same name. The program then uses your file in place of this text, and it adds a Base directory line above the skill text. The same-name rule was tested with /simplify only. See Override a Prompt.

Full Text

PROBE-ARG is the test's argument.

<command-message>deep-research</command-message>
<command-name>/deep-research</command-name>
<command-args>PROBE-ARG</command-args>

Run the "deep-research" workflow.

Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report.

When the user wants a deep, multi-source, fact-checked research report on any topic. BEFORE invoking, check if the question is specific enough to research directly — if underspecified (e.g., "what car to buy" without budget/use-case/region), ask 2-3 clarifying questions to narrow scope. Then pass the refined question as args, weaving the answers in.

Phases:
- Scope: Decompose question (from args) into 5 search angles
- Search: 5 parallel WebSearch agents, one per angle
- Fetch: URL-dedup, fetch top 15 sources, extract falsifiable claims
- Verify: 3-vote adversarial verification per claim (need 2/3 refutes to kill)
- Synthesize: Merge semantic dupes, rank by confidence, cite sources

Invoke: Workflow({ name: "deep-research", args: "PROBE-ARG" })

If the user asks you to modify this workflow or write a new script, load the `workflow-authoring` skill first.