Skip to content
Agentmart
Submit a tool

deep-researcher

Conducts multi-step web research with source synthesis and citations.

Skill by Fadil369

IndexedMIT★ 1
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/fadil369-deep-researcher

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Conducts multi-step web research with source synthesis and citations.

Use cases: research

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/deep-researcher

What's inside

Skill name
deep-researcher
Description
Conducts multi-step web research with source synthesis and citations.
License
MIT
Instructions
55 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Deep Researcher

Conduct thorough, multi-step web research on any question or topic. Synthesize sources into a structured report with inline citations and an honest confidence assessment.

## How to invoke

Give the agent a question, topic, or research brief. Optionally specify:
- Depth: quick (3 sources) / standard (5–8 sources) / deep (10+ sources)
- Output format: report / bullet summary / comparison table
- Source preferences: prefer academic / prefer recent (within N months) / prefer primary sources

## Research process

1. **Decompose** the question into 3–5 concrete sub-questions that, answered together, cover the topic fully.
2. **Search** for each sub-question using targeted web searches. Prefer:
   - Primary sources and official documentation
   - Peer-reviewed work and institutional reports
   - Reputable news and technical publications
   - Over: blog aggregators, SEO content, social media
3. **Read sources in full** — do not skim. Extract specific claims, data points, and direct quotes with attribution.
4. **Synthesize** a report structured by sub-question. Cite every non-obvious claim inline (source name + URL).
5. **Close with a "Confidence & Gaps" section** noting:
   - Where sources agreed vs disagreed (explain which you find more credible and why)
   - Where coverage was thin or missing
   - What a follow-up search would focus on

## Standards

- Be skeptical. Don't paper over uncertainty with confident-sounding prose.
- If sources conflict, say so explicitly.
- A claim without a source is an opinion — label it as such.
- Prefer specifics over generalities: numbers, dates, named entities.

## Output format

Structured markdown report:
```
# [Topic]
*Research date: YYYY-MM-DD*

## [Sub-question 1]
...

## [Sub-question 2]
...

## Confidence & Gaps
...

## Sources
1. [Title](URL)
...
```

From Fadil369/hnh, MIT.

More from Fadil369/hnh

Signals

Stars
1
Forks
0
Open issues
1
Last commit (this folder)
May 12, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

Same skill elsewhere

Copies of this SKILL.md published by others; search shows only one of them.

More from Fadil369

Cite this page

deep-researcher skill. Agent Mart. https://agentmart.dev/skills/fadil369-deep-researcher (last updated 2026-10-24)