Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/paper-reading-assistant
AI-assisted paper reading, PDF Q&A, and summarization workflows
Passed 13 of 23 test cases with the skill, and 12 of 23 without it.
3 fixed10 passed either way8 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
I need to quickly triage 15 papers to figure out which ones are relevant to my work on distributed caching. How should I approach the initial survey pass for each paper, what parts should I read, and how long should I spend per paper?
| Checked | Without skill | With skill |
|---|---|---|
| Allocates 5 to 10 minutes per paper for the initial survey pass | Passed | Passed |
| Instructs to read only the first and last paragraphs of the introduction | Missed | Passed |
The instructions your model reads when the skill loads.
Systematic workflows for reading, annotating, and extracting insights from academic papers, including AI-assisted summarization and critical analysis techniques.
Srinivasan Keshav's three-pass approach provides a structured way to read papers at increasing depth:
Read only:
After Pass 1, you should know:
Decision: Stop here if the paper is not relevant, or continue to Pass 2.
Read the full paper, but skip proofs and complex derivations:
After Pass 2, you should be able to:
test cases passed, vs 12 / 23 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.