- Home
- Skills
- Productivity
- synthesize obsidian research
Works with the AI Agents you already use
synthesize obsidian research
Turn fragmented Obsidian notes into a traceable, evidence-based claim ledger and research synthesis.
$15
synthesize obsidian research
Example session with this skill installed
Run a health diagnostic on my 'Machine Learning Research' folder. I need to know which claims are currently unsupported and where my source notes are missing locators.
- Read your context and instructions
- Compiled the synthesize obsidian research
Diagnostic complete. Found 42 source notes.
- Traceability: 12 notes missing locators (page numbers/URLs).
- Claim Health: 5 propositions identified as 'unsupported' due to missing evidence links.
- Recommendation: Convert 'Attention-Mechanism-Notes.md' from a general summary to a claim ledger.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Research vaults in Obsidian often become "write-only" graveyards of fragmented highlights, ambiguous paraphrases, and untraceable claims. Developers and researchers struggle to distinguish their own ideas from source material, leading to weak arguments and evidence gaps.
What it does
- Performs a read-only health diagnostic to identify fragmentation, link quality, and citation coverage.
- Maps existing notes into a structured research model including source notes, evidence items, and claims.
- Constructs a claim ledger that links propositions to specific supporting or contradicting evidence with exact locators.
- Generates synthesis reports that highlight source disagreement and identify missing data points.
- Prepares reversible, incremental vault updates to improve organization without destroying original wording.
Frameworks & tools
Designed for Obsidian vaults using Markdown. Utilizes citation keys, BibTeX/Zotero conventions, and YAML frontmatter. Includes a Python-based vault scanner for local execution.
Why this beats prompting it yourself
Generic LLM prompts often hallucinate connections or "average away" source disagreements. This skill enforces strict evidence traceability, preventing the AI from turning semantic similarity into false evidential support while preserving your specific citation keys and folder structures.
Use cases
- Auditing a research vault for evidence gaps before starting a thesis or whitepaper.
- Consolidating messy Zotero imports into a structured literature review.
- Building a defensible claim-evidence matrix for technical reports or books.
- Mapping contradictions between multiple sources in a specialized domain.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Productivity.
Requires local Python execution for full vault scanning. Works best with vaults using consistent citation keys or Zotero-linked workflows.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 3 months ago