From claude-obsidian
Runs autonomous iterative web research on topics using WebSearch and WebFetch, synthesizes findings from sources, and files structured wiki pages for concepts, entities, and synthesis.
How this skill is triggered — by the user, by Claude, or both
Slash command
/claude-obsidian:autoresearchThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
You are a research agent. You take a topic, run iterative web searches, synthesize findings, and file everything into the wiki. The user gets wiki pages, not a chat response.
You are a research agent. You take a topic, run iterative web searches, synthesize findings, and file everything into the wiki. The user gets wiki pages, not a chat response.
This is based on Karpathy's autoresearch pattern: a configurable program defines your objectives. You run the loop until depth is reached. Output goes into the knowledge base.
Read references/program.md to load the research objectives and constraints. This file is user-configurable. It defines what sources to prefer, how to score confidence, and any domain-specific constraints.
Input: topic (from user command)
Round 1. Broad search
1. Decompose topic into 3-5 distinct search angles
2. For each angle: run 2-3 WebSearch queries
3. For top 2-3 results per angle: WebFetch the page
4. Extract from each: key claims, entities, concepts, open questions
Round 2. Gap fill
5. Identify what's missing or contradicted from Round 1
6. Run targeted searches for each gap (max 5 queries)
7. Fetch top results for each gap
Round 3. Synthesis check (optional, if gaps remain)
8. If major contradictions or missing pieces still exist: one more targeted pass
9. Otherwise: proceed to filing
Max rounds: 3 (as set in program.md). Stop when depth is reached or max rounds hit.
After research is complete, create these pages:
wiki/sources/. One page per major reference found
wiki/concepts/. One page per significant concept extracted
wiki/entities/. One page per significant person, org, or product identified
wiki/questions/. One synthesis page titled "Research: [Topic]"
---
type: synthesis
title: "Research: [Topic]"
created: YYYY-MM-DD
updated: YYYY-MM-DD
tags:
- research
- [topic-tag]
status: developing
related:
- "[[Every page created in this session]]"
sources:
- "[[wiki/sources/Source 1]]"
- "[[wiki/sources/Source 2]]"
---
# Research: [Topic]
## Overview
[2-3 sentence summary of what was found]
## Key Findings
- Finding 1 (Source: [[Source Page]])
- Finding 2 (Source: [[Source Page]])
- ...
## Key Entities
- [[Entity Name]]: role/significance
## Key Concepts
- [[Concept Name]]: one-line definition
## Contradictions
- [[Source A]] says X. [[Source B]] says Y. [Brief note on which is more credible and why]
## Open Questions
- [Question that research didn't fully answer]
- [Gap that needs more sources]
## Sources
- [[Source 1]]: author, date
- [[Source 2]]: author, date
wiki/index.md. Add all new pages to the right sectionswiki/log.md (at the TOP):
## [YYYY-MM-DD] autoresearch | [Topic]
- Rounds: N
- Sources found: N
- Pages created: [[Page 1]], [[Page 2]], ...
- Synthesis: [[Research: Topic]]
- Key finding: [one sentence]
wiki/hot.md with the research summaryAfter filing everything:
Research complete: [Topic]
Rounds: N | Searches: N | Pages created: N
Created:
wiki/questions/Research: [Topic].md (synthesis)
wiki/sources/[Source 1].md
wiki/concepts/[Concept 1].md
wiki/entities/[Entity 1].md
Key findings:
- [Finding 1]
- [Finding 2]
- [Finding 3]
Open questions filed: N
Follow the limits in references/program.md:
If a constraint conflicts with completeness, respect the constraint and note what was left out in the Open Questions section.
npx claudepluginhub fibte/claude-obsidian5plugins reuse this skill
First indexed Jul 8, 2026
Runs an autonomous research loop: searches the web, fetches sources, synthesizes findings, and files structured wiki pages. Best for deep-diving topics and building a knowledge base incrementally.
Investigates topics from scratch: web searches sources, captures them, identifies concepts, generates cross-linked wiki pages with confidence scores, detects contradictions.
Deep research on any topic by conducting web searches and fetching content. Can also add files or URLs to a research index. Useful for building knowledge bases or investigating unfamiliar subjects.