Skip to main content
affpapa.org
RU EN
skill

scholar-evaluation · davila7 — Claude Code skill for research review

Assess papers, proposals, and literature reviews against research criteria. Use it to organize feedback on methods, evidence, analysis, and academic writing.

Install into Claude Code · claude-code-templates All methods and platforms ↓ 
npx claude-code-templates@latest --skill scientific/scholar-evaluation
Open on GitHub

What scholar-evaluation does

The skill reviews scholarly work across research questions, literature, methods, data, analysis, findings, writing, and references. It can identify strengths and weaknesses for each relevant area, with an optional score on a 1-to-5 scale.

First, it establishes the kind of work and the breadth of review. When that scope is unclear, it asks the user to clarify. Detailed criteria are in references/evaluation_framework.md; scripts/calculate_scores.py can compute combined scores. Numeric ratings are optional, so decide whether they fit the review you need.

The final feedback can bring together an overall judgment, ranked revisions, and publication readiness when relevant. For documents, the skill suggests considering diagrams and points to scientific-schematics for creating them. It includes python scripts/generate_schematic.py "your diagram description" -o figures/output.png as a generation command.

What it helps with

  • review a research design for rigor and fit
  • spot gaps in a literature review
  • check whether claims follow from the analysis
  • audit references and source balance
  • rank revisions before submission

Example prompts for the agent

  • Review this paper's methodology and report its strengths and weaknesses.
  • Check this literature review for gaps and assess how it connects its sources.
  • Evaluate the full paper across the relevant criteria and rank the revisions.

How to install scholar-evaluation

1claude-code-templates

npx claude-code-templates@latest --skill scientific/scholar-evaluation

2Skills CLI (Vercel)

npx skills add davila7/claude-code-templates --skill scholar-evaluation -a claude-code

3Manually: put the files in place

~/.claude/skills/scholar-evaluation/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/scholar-evaluation/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about scholar-evaluation

How do I install scholar-evaluation in Claude Code?

Run npx claude-code-templates@latest --skill scientific/scholar-evaluation.

What does scholar-evaluation do?

It assesses scholarly work across areas such as research design, evidence, analysis, writing, and citations, then helps produce structured feedback.

How does the skill score research work?

It offers an optional 1-to-5 rating for each assessed area. Use scripts/calculate_scores.py to calculate aggregate scores.

Similar skills

All skills for Science and research →

scholar-evaluation by other authors comes first.

scholar-evaluation K-Dense-AI Provides qualitative, evidence-traceable developmental feedback on research drafts and protocols. Audits assessment rubrics without proxy prestige metrics. CX Codex +1 2,100installs anysearch anysearch-ai This skill gives an agent web search, domain-specific queries, parallel batch search, and page extraction. Use it when a task needs current information or a claim needs checking. CX Codex +1 38,500installs academic-paper Imbad0202 This skill runs a 12-agent academic pipeline across 11 modes. It guides projects from literature searches and outlines to citation audits and rebuttal reviews. CX Codex +1 10,900installs nature-figure Yuan1z0825 A skill that builds, revises and audits scientific figures for manuscripts in Python or R. Useful when plots go to submission, not to a report. CX Codex +1 18,800installs academic-paper-reviewer Imbad0202 This skill reviews an academic paper through five role-based perspectives. Use it for peer review, revision checks, or a focused methodology assessment. CX Codex +1 9,900installs nature-polishing Yuan1z0825 A skill that polishes, translates and tightens existing academic prose. Facts, terminology and evidence boundaries stay intact. CX Codex +1 17,500installs nature-citation Yuan1z skill, refactored into static/dynamic layers Finds Nature and CNS-family papers for manuscript claims, maps claims to sources, and prepares a reference-manager export. Use it when the journal scope matters. CX Codex +1 15,600installs

From the same set804

The whole set →
hono This skill guides Hono API and app development, covering routes, middleware, validation, and typed RPC clients. Use it when building for runtimes such as Bun or Cloudflare Workers. 54installs command-creator Assists in designing reusable Claude Code slash commands. Sets up parameters, picks storage scope, and generates structured Markdown files for agents. 54installs plan-mode-game This hook opens a browser game when Claude Code enters Plan Mode and tracks tool activity. It gives you something to do while a plan takes shape. 54installs szamlazz Issue, cancel, and download Hungarian invoices through the szamlazz.hu Agent API. It also looks up taxpayer details and keeps a reusable customer cache. 54installs pytorch-lightning Helps Claude Code structure PyTorch code into LightningModules and configure multi-GPU or TPU training. It removes boilerplate loops and organizes data pipelines. 53installs naming-analyzer Reviews variable, function, class and file names for clarity, spots misleading labels and offers alternatives that follow language conventions. 53installs kotlin-coroutines-expert This skill guides Claude Code through Kotlin Coroutines and Flow, from coordinating concurrent work to handling failures and testing asynchronous functions. Use it when debugging cancellation or building reactive data streams. 53installs aeon Gives Claude a working map of the aeon Python library for classification, forecasting, clustering and anomaly detection on time series. 52installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor