Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/comm-lit-review
Communications-domain literature review and related-work search with database-aware source control.
Passed 7 of 14 test cases with the skill, and 7 of 14 without it.
3 fixed8 passed either way8 still failing4 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 am preparing a paper on dynamic beam-hopping and joint power-spectrum resource allocation in LEO satellite constellations. Could you conduct a rigorous literature search and synthesize a formal research note on this topic? Please include a structured comparative table of key studies, a short narrative on where the field currently stands, and a clear breakdown of open research gaps and unresolved design assumptions.
| Checked | Without skill | With skill |
|---|---|---|
| Includes a structured comparative literature table. | Passed | Passed |
| Categorizes included papers into foundational works before 2022 and recent developments from 2022 onward. | Missed | Passed |
| Includes a dedicated narrative section identifying open research gaps. | Passed | Passed |
The instructions your model reads when the skill loads.
Run communications-focused paper search with tighter source policy than a generic literature review. Default to formal publications, prioritize IEEE Xplore and ScienceDirect, then ACM Digital Library, and output a review that is structured for research use rather than casual browsing.
Read references/source-policy.md before searching. Use references/domain-taxonomy.md to classify the topic, references/venue-tiering.md to rank venues, and references/output-template.md to format the final answer.
Decide whether the request is primarily about:
If the request is not clearly in communications systems research, fall back to a more general literature skill.
Apply these defaults unless the user overrides them:
IEEE Xplore, ScienceDirect, then ACM Digital Library, then broader webIf the user explicitly narrows scope, obey the narrower scope:
test cases passed, vs 7 / 14 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.