Description
scholar-evaluation is an agent skill for developmental, evidence-traceable feedback on a scholarly work, such as a paper, draft, protocol, literature synthesis or research idea. It starts with qualitative judgement, and any scores are optional. They only describe how the submitted evidence maps to a predeclared, bounded rubric. The skill also audits whether a low-stakes assessment process documents its construct, provenance, rater quality, uncertainty, traceability, sensitivity to choices, fairness, accessibility, privacy and human governance. It has a hard safety boundary. It must never be used to automate, recommend, materially influence or score people in the ways its boundary forbids. Use it when you want a candid, constructive second read of your own draft, or a check that an assessment process is sound before it is used. It is part of the k-dense-ai scientific agent skills repository on GitHub, which has about 49,600 stars. The listing shows it as free, and it has about 1,900 installs. Its security audits show passes from Gen Agent Trust Hub and Socket, with a warning from Snyk.…
Highlights
- Qualitative-first developmental feedback
- Scores only as a bounded rubric mapping
- Audits assessment process quality
- Checks fairness, privacy and governance
- Hard boundary against automated decisions
Ratings & Reviews
No ratings yet
Be the first to rate scholar-evaluation.
People also visit
scholar-evaluation FAQ
What does it review?
Scholarly works such as papers, drafts, protocols, literature syntheses and research ideas, with developmental, evidence-traceable feedback.
Are scores part of it?
Optionally. The skill says scores only describe how submitted evidence maps to a predeclared rubric, and judgement comes first.
What is it not for?
The skill has a hard boundary against automating, recommending, materially influencing or scoring people, and the list of forbidden uses is set out in the skill.
What can it audit?
Whether a low-stakes assessment documents its construct, provenance, rater quality, uncertainty, fairness, privacy and human governance.
How do I install it?
Run npx skills add https://github.com/k-dense-ai/scientific-agent-skills --skill scholar-evaluation.
Is it checked for security?
Its security audits show passes from Gen Agent Trust Hub and Socket, and a warning from Snyk.
What are the best scholar-evaluation alternatives?
Popular alternatives to scholar-evaluation include agent-eval, dynamic-workflow-mode and eval-harness. See all scholar-evaluation alternatives