academic-paper-reviewer

Simulates academic peer review, evaluating papers across Originality, Methodology, Results, and Writing to provide Major/Minor Revision recommendations with actionable feedback. Triggers when a user asks to "review my paper," "simulate peer review," or "give my paper a peer review.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable instruction skill: explicit criteria, calibrated Major/Minor issue examples, a concrete output template, and sensible edge-case handling. Its main gaps are the missing mapping from dimension findings to the overall recommendation/score and mild verbosity in dimension intro sentences.

Suggestions

Add an explicit decision rule for the overall recommendation, e.g., 'any Major issue in Methodology or Results → Major Revision; only Minor issues → Minor Revision; no issues → Accept', and how per-dimension scores map to the 1-10 overall score.

Trim the dimension intro sentences (e.g., 'Assesses the scientific rigor, soundness, and reproducibility...') that restate what the dimension names already convey, keeping only the criteria and issue examples.

If the skill grows, move the per-dimension 'Common issue examples' into one-level-deep reference files (e.g., references/originality.md) to keep SKILL.md a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is dense and substantive — per-dimension Major/Minor issue examples, severity definitions, and a full output template are genuine calibration content, not filler. Minor over-explanation could be trimmed (e.g., "Assesses the paper's academic novelty and contribution to the existing body of knowledge" restates what Claude already knows, and the role-play opener is unnecessary padding).	4 / 5
Actionability	Guidance is highly concrete for an instruction-only skill: a copy-paste-ready report template, explicit review criteria, Major/Minor severity definitions, and edge-case handling (PDF input, abstract-only submissions, review focus, interdisciplinary papers). Not 5 because the decision rule mapping dimension findings to the overall Accept/Minor Revision/Major Revision/Reject recommendation and the 1-10 scores is left implicit.	4 / 5
Workflow Clarity	The sequence is clear: gather inputs (with an explicit minimum of the first two items and a venue-standard fallback), review across four dimensions, classify severities, and produce the structured report. Not 5 because the workflow is presented as sections rather than an explicit ordered procedure with checkpoints, leaving the end-to-end flow implicit.	4 / 5
Progressive Disclosure	No bundle files exist, so everything lives in a single SKILL.md; that file is well-organized with clear section headers and appropriate placement for most content (output format, severity definitions, principles). Not 5 because the four dimension sections (~90 lines of criteria and issue examples) are inline candidates for one-level-deep reference files if the skill grows.	4 / 5
	Total	16 / 20 Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that states concrete capabilities in third person and gives explicit, naturally phrased triggers for both what and when. The only weakness is that trigger coverage omits a few natural synonyms (manuscript, draft) and does not mention the structured report output.

Dimension	Reasoning	Score
Specificity	"Simulates academic peer review, evaluating papers across Originality, Methodology, Results, and Writing to provide Major/Minor Revision recommendations with actionable feedback" lists several concrete, named actions in third-person voice. Not 5 because coverage has minor gaps (e.g., the structured review report and per-dimension scoring it produces are not mentioned); well above the 1-2 actions of a 3.	4 / 5
Completeness	It explicitly answers both questions: what ("Simulates academic peer review, evaluating papers across ... to provide Major/Minor Revision recommendations with actionable feedback") and when ("Triggers when a user asks to 'review my paper,' 'simulate peer review,' or 'give my paper a peer review'"), matching the top anchor with concrete trigger phrases.	5 / 5
Trigger Term Quality	"Triggers when a user asks to 'review my paper,' 'simulate peer review,' or 'give my paper a peer review'" quotes natural user phrasings verbatim. Not 5 because common synonyms such as 'manuscript,' 'draft,' or 'feedback on my paper' are missing; far better than the generic keyword coverage of a 3.	4 / 5
Distinctiveness Conflict Risk	Clear niche (academic paper peer review) with distinct triggers — every trigger phrase names 'paper' or 'peer review,' minimizing overlap risk with code-review or general document-review skills. Matches the 'clear niche with distinct triggers; minimal conflict risk' anchor.	5 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: zebbern/claude-code-guide
Path: skills/academic-paper-reviewer/SKILL.md
Commit: a2e6ee3

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.