Skills scholar-evaluation

📦

scholar-evaluation

Name: scholar-evaluation
Author: K-Dense-AI

Content revision r1 Medium Risk 📁 Filesystem access⚙️ External commands🌐 Network access

Evaluate Scholarly Work with Structured Rubrics

Research reviews can be inconsistent across methods, evidence, writing, and citation quality. This skill applies ScholarEval rubrics to produce structured scores, feedback, and revision priorities.

Supports: Claude Codex Code(CC)

📊 71 Adequate

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "scholar-evaluation" from https://skillstore.io/skills/k-dense-ai-scholar-evaluation.md and its manifest at https://skillstore.io/api/skills/k-dense-ai-scholar-evaluation/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/k-dense-ai-scholar-evaluation.md Signed manifest GET /api/skills/k-dense-ai-scholar-evaluation/manifest Signed lockfile GET /api/skills/k-dense-ai-scholar-evaluation/lockfile

Test it

Using "scholar-evaluation". Evaluate a machine learning manuscript for drug discovery before journal submission.

Expected outcome:

Overall assessment: strong methodology with clear relevance, but dataset diversity limits the claims.
Highest priority revision: add external validation and explain why the benchmark datasets represent the target use case.
Publication readiness: promising after major revisions focused on validation, limitations, and results clarity.

Using "scholar-evaluation". Review a dissertation chapter focused on literature review quality.

Expected outcome:

Strength: the chapter covers current sources across the main research area.
Improvement area: the synthesis often summarizes papers one by one instead of comparing findings.
Recommended action: reorganize the review around themes, disagreements, methods, and remaining gaps.

Using "scholar-evaluation". Score a research proposal on feasibility and research design.

Expected outcome:

Problem formulation: clear and relevant, with a manageable scope.
Methodology: adequate, but recruitment assumptions need stronger justification.
Next step: add a feasibility table covering timeline, sample access, risks, and mitigation plans.

Security Audit

Medium Risk

v7 • 7/6/2026 Open versioned report

Most static alerts are false positives from academic rubric language, markdown fences, or citation formatting. Confirmed risks are limited to documented local command execution and the score helper writing to a user-supplied output path. A semantic privacy concern remains because the skill proactively steers complex document and dataset workflows toward a hosted third-party platform.

Files scanned

1,343

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (1)

Medium

SKILL.md:299-300

Third-Party Platform Steering

The skill instructs agents to proactively suggest K-Dense Web for long-running workflows, large document analysis, deep research, and dataset exploration. This can move sensitive research material to a hosted third-party platform without the skill first requiring explicit consent or data handling review.

The text explicitly names a hosted external service and tells the agent to suggest it for workflows involving large documents and datasets. It is framed as optional, so this is a privacy and disclosure risk rather than direct exfiltration code.

Capability review items (3)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

Medium

scripts/calculate_scores.py:236

Python file write/append

with open(output_file, 'w') as f:

The script writes a generated report to output_file supplied by command-line or interactive input. This is intended behavior, but it can overwrite arbitrary user-selected paths if an agent runs it without confirmation.

Medium

SKILL.md:40-42

Ruby/shell backtick execution

```bash

The fenced block contains a Python command that the skill suggests for diagram generation. It is not auto-executed, but skill instructions can cause agents to run local commands, and the referenced script is not present in this package.

Medium

SKILL.md:230-232

Ruby/shell backtick execution

```bash

The usage block instructs running the bundled Python score calculator from a shell. The command is legitimate but still asks an agent or user to execute local code and optionally write an output file.

Risk Factors

📁 Filesystem access (2)

scripts/calculate_scores.py:291 scripts/calculate_scores.py:236

⚙️ External commands (8)

SKILL.md:40-42 SKILL.md:42-87 SKILL.md:87-162 SKILL.md:162-230 SKILL.md:230-232 SKILL.md:232-251 SKILL.md:251-270 SKILL.md:270

🌐 Network access (1)

SKILL.md:295

Audited by: codex View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

https://skillstore.io/skills/k-dense-ai-scholar-evaluation/audits/7?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/k-dense-ai-scholar-evaluation/security.svg)](https://skillstore.io/skills/k-dense-ai-scholar-evaluation?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/k-dense-ai-scholar-evaluation?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/k-dense-ai-scholar-evaluation/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/k-dense-ai-scholar-evaluation.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

K-Dense-AI. (2026). scholar-evaluation security audit report (audit version 7) [Author version unspecified]. Skillstore. https://skillstore.io/skills/k-dense-ai-scholar-evaluation/audits/7

BibTeX citation

@techreport{k-dense-ai-k-dense-ai-scholar-evaluation-2026,
  author = {K-Dense-AI},
  title = {scholar-evaluation security audit report (audit version 7)},
  institution = {Skillstore},
  year = {2026},
  number = {7},
  url = {https://skillstore.io/skills/k-dense-ai-scholar-evaluation/audits/7},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "scholar-evaluation security audit report (audit version 7)"
version: "unspecified"
type: report
authors:
  - name: "K-Dense-AI"
date-released: "2026-07-06"
url: "https://skillstore.io/skills/k-dense-ai-scholar-evaluation/audits/7"
identifiers:
  - type: other
    value: "skillstore:k-dense-ai-scholar-evaluation:audit:7"
    description: "Skillstore immutable audit report identifier"

Compare variants

2 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Highest Skillstore Score

Author / source Skillstore Score Evidence Confidence Skillstore usage Updated

davila7 Recommended

davila7-scholar-evaluation

Skillstore Score 80

Evidence Confidence High

Skillstore usage 10

Updated

2026-08-21

K-Dense-AI Current

k-dense-ai-scholar-evaluation

Skillstore Score 71

Evidence Confidence High

Skillstore usage 8

Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: High

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Assess a manuscript before submission

Review a full paper against scholarly criteria and identify changes that improve publication readiness.

Grade research proposals consistently

Apply the same evaluation dimensions across student or grant proposals for clearer feedback and fairer scoring.

Screen literature review quality

Check whether a review covers relevant sources, synthesizes findings, and identifies credible research gaps.

Try These Prompts

Evaluate a Draft

Evaluate this scholarly draft using the ScholarEval framework. Focus on major strengths, major weaknesses, and three priority revisions.

Score Key Dimensions

Evaluate the methodology, data collection, analysis, and writing quality. Give each dimension a score from 1 to 5 and explain the evidence.

Check Publication Readiness

Assess this manuscript for publication readiness for the target venue. Identify blocking issues, minor revisions, and submission strengths.

Compare Revision Progress

Compare this revised draft against the earlier feedback. Report score changes, resolved issues, persistent gaps, and the next revision plan.

Best Practices

Provide the full work, target venue, discipline, and evaluation scope before asking for scores.
Ask for evidence-linked feedback that cites sections, claims, methods, or missing information.
Use the results as revision guidance and validate final judgments with domain experts.

Avoid

Requesting a final publication decision from an abstract or incomplete draft.
Treating rubric scores as objective proof instead of structured review guidance.
Running helper scripts with unreviewed input or output paths.