AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

Scholar Evaluation

Runs developmental, evidence-traceable reviews of papers, protocols and research ideas, plus local audits of low-stakes assessment rubrics.

EducationAdvanced★ 33,030⑂ 3,248AI score 9/10Last updated: Aug 9, 2026

What it does

  • Reviews a scholarly work (paper, draft, protocol, literature synthesis, research idea) qualitatively first; optional scores only describe how submitted evidence maps to a predeclared bounded rubric.
  • Bans prestige and proxy metrics — Impact Factor, h-index, citation counts, altmetrics, venue or institutional prestige — and the rubric validator rejects such criteria.
  • Provides an 8-step workflow: confirm allowed use → define the construct → validate the rubric → build traceable evidence records → rate independently → run local quality checks → synthesize findings → human committee review.
  • Ships standard-library Python CLIs for score calculation, traceability checks, inter-rater agreement, weight sensitivity, and a fail-closed process checklist — all local, no network, credentials, or external models.
  • Hard-refuses consequential uses: hiring, promotion, tenure, admissions, funding, prizes, or discipline, and never ranks people.

Who it's for

  • Researchers and PhD students who want systematic pre-submission or lab-internal peer review.
  • Research-integrity or assessment officers auditing whether a review process documents validity, fairness, privacy, and governance.
  • PIs replacing metric-driven judgments with evidence-based, developmental feedback.

Example uses

  1. Feed a pre-submission manuscript and get criterion-level comments that separate observed evidence, interpretation, missing, and not_applicable.
  2. Run scripts/validate_rubric.py on a homemade rubric to catch citation-count or venue-prestige criteria.
  3. Load three raters' CSV into summarize_agreement.py, inspect agreement, and redesign the criteria that raters disagree on.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/HEAD/skills/scholar-evaluation/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the skills/scholar-evaluation folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/scholar-evaluation/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git /tmp/sas && mkdir -p ~/.claude/skills && cp -r /tmp/sas/skills/scholar-evaluation ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and confirm Python 3.11+: python3 --version.
  2. Clone the repository: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git /tmp/sas
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy just this skill: cp -r /tmp/sas/skills/scholar-evaluation ~/.claude/skills/
  5. Restart Claude Code and ask: "Use the scholar-evaluation skill to review my draft."
  6. Before any organizational use, read references/responsible_assessment.md first.
  7. To run the CLIs, fill the JSON/CSV templates in assets/ with pseudonymous IDs only — never raw applications, CVs, or reviewer identities.
View source on GitHub ↗License: MIT