- Home
- Skills
- Research & Analysis
- Evidence Concept Graph
Evidence Concept Graph
Build verifiable, source-grounded concept graphs with local Python/SQLite tools, review, and bounded retrieval.
$3
Works with the AI Agents you already use
Evidence Concept Graph
Example session with this skill installed
Run the bundled synthetic example in a new local database, review relation R1, and retrieve its source-grounded result.
- Read your context and instructions
- Compiled the evidence concept graph
A SQLite graph and reviewed relation records linked to original synthetic excerpts, with unresolved issues and statuses retained.
Connects securely to your tools. The creator never sees your data.
About this skill
Build source-grounded concept relations with local Python/SQLite tools: import, quote/offset/hash validation, explicit review, source-version invalidation, and bounded one-hop retrieval. Includes English instructions, synthetic multilingual examples, tests, and integration guidance. Commercial internal use and client outputs are permitted under LICENSE.txt. Redistribution, resale, or third-party product/service embedding of the Skill itself requires separate written authorization.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Research & Analysis.
Does not parse PDF/Word directly or provide production authentication. Structural quote validation does not prove semantic correctness. Model-generated candidates require separate review. Synthetic demonstration data is not scholarly evidence.
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 days ago
- Software
Python 3.10 or newer
A compatible AI assistant for semantic candidate extraction.
Permissions
File Scopes
The bundled tool makes no network requests. Use isolated demonstration data first. Tenant and library CLI inputs are local filters, not production authorization.