Deep Researcher /deep-researcher

About this skill

Deep Researcher turns a one-line question into a proper research brief. It plans sub-questions, fans out to multiple web sources in parallel, then cross-checks claims across sources before writing anything down.

Every factual claim in the report links back to its source, and each section carries a confidence score so you know which parts are rock-solid and which deserve a second look. Outputs are clean Markdown that drops straight into docs, wikis, or slide decks.

Agencies use it for competitive intel and market scans; engineering teams use it for technology evaluations. It pairs well with Meeting Scribe — research the topic, brief the team, scribe the meeting.

Inputs

• topic · string
  Research question or topic.
• depth · string
  quick | standard | deep. Controls source count and passes.
• max_sources · number
  Cap on sources consulted (1–40).

Outputs

• report_markdown · string
  Full cited report in Markdown.
• sources · array
  URLs consulted, in citation order.
• confidence · number
  0–1 aggregate confidence score.

Permissions

Deny-by-default: the skill can only use what it declares.

Manifest

{
  "spec": "agentskills.io/v1",
  "name": "deep-researcher",
  "version": "2.1.0",
  "description": "Plans a research brief, queries multiple web sources in parallel, cross-checks claims, and returns a cited Markdown report with a confidence score per section.",
  "inputs": {
    "topic": {"type": "string", "description": "Research question or topic.", "required": true},
    "depth": {"type": "string", "description": "quick | standard | deep. Controls source count and passes.", "required": false},
    "max_sources": {"type": "number", "description": "Cap on sources consulted (1–40).", "required": false}
  },
  "outputs": {
    "report_markdown": {"type": "string", "description": "Full cited report in Markdown."},
    "sources": {"type": "array", "description": "URLs consulted, in citation order."},
    "confidence": {"type": "number", "description": "0–1 aggregate confidence score."}
  },
  "permissions": ["net:http", "fs:write"],
  "author": "AgentWorks",
  "category": "Research"
}

Changelog