- Home
- Skills
- Productivity
- Paper Semantic Map
More screenshots
Works with the AI Agents you already use
Paper Semantic Map
Turn research papers into deep, visual HTML maps and keep an archive that shows where the open gaps are for your own paper.
Free
Paper Semantic Map
Example session with this skill installed
Read the Grounding DINO paper and add it to my paper archive.
- Read your context and instructions
- Compiled the paper semantic map
01-grounding-dino.html: a two-layer page with the sixty second read, a hand-drawn diagram of the query selection rule, the related-work sentence, every results table copied from the paper, and a code section noting the release has no training code and silently truncates prompts past 256 tokens. index.html is updated with the paper's place on the field map, the coverage matrix, the revised gap board and the re-ranked reading queue.
Connects securely to your tools. The creator never sees your data.
About this skill
I built this to prepare my own paper submission. Reading two papers a week was easy; remembering what each one actually did, comparing them on the same terms, and seeing where the open gaps were was not. This skill does that part.
One page per paper, in two layers. On top: a sixty second read (the problem, the mechanism, the headline number, what's actually new, an honest verdict, and why it matters to you), one hand-drawn diagram of the real mechanism, and a sentence you can paste into your related work. Underneath, collapsed: the full breakdown, with every method component and its equations, every results table with the numbers copied exactly, the released code file by file (including where the code and the paper disagree), and the weak points a reviewer would push on.
One archive page framed around your own research question: a field map on two axes, a coverage matrix, a gap board that gets revised as you read, a reading queue, and a do-not-claim register so you don't claim something a paper already did.
Every page is a single self-contained HTML file with light and dark mode, and it works on a phone. The first time, the skill asks a few questions to build your research profile; every map after that is written for it.
Source and a worked example (Grounding DINO): https://github.com/alisoltani7596/paper-semantic-map
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.
Needs the full text of the paper; if it can't fetch it, it asks you for the PDF instead of writing from the abstract. Maps are only as good as the reading, so check the numbers you cite. Works best with web access to arXiv, open-access venue pages and GitHub.
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
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 9 days ago
- Free with an Agensi account
- Accounts
GitHub
Arxiv
Thecvf
- Software
- Web access
Used to read papers on arXiv and open-access pages, and their code on GitHub.
Permissions
Allowed Hosts
File Scopes
Reads public papers and code repositories and writes self-contained HTML pages to your archive folder. No API keys needed.