peer-review

Prepare evidence-bounded, constructive peer-review drafts and structured manuscript assessments. Use for authorized review of scientific manuscripts, protocols, preprints, or research proposals; reporting-guideline selection; claim–evidence checks; methods, statistics, reproducibility, ethics, figure/table, and citation critique; or revision-response planning.

Quality

92%

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

92%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-engineered, high-stakes procedural skill: executable local CLIs with templates, a gated multi-step workflow with validation and feedback loops, and clean one-level-deep progressive disclosure. Only minor conciseness tightening is possible.

Dimension	Reasoning	Score
Conciseness	Lean and dense for a high-stakes domain: it assumes Claude's competence (no padding about what peer review or statistics are) and every section earns its place, though the nine-item 'Never:' list and a few enumerated checklists could be trimmed slightly.	4 / 5
Actionability	Provides fully executable, copy-paste-ready commands with named inputs/outputs and template starting points ('python3 scripts/validate_review_intake.py completed-intake.json', 'Start from assets/claim_evidence_matrix_template.csv'), and the ordered 9-point methods/statistics assessment is concrete guidance covering common cases.	5 / 5
Workflow Clarity	An 11-step numbered workflow with explicit validation checkpoints ('Proceed only when status is READY_FOR_LOCAL_REVIEW', 'Generate a private scaffold only after intake passes') and feedback loops (intake validation, final lint), plus a gate that blocks specific failure modes.	5 / 5
Progressive Disclosure	SKILL.md is a clear overview with well-signaled one-level-deep references to references/, scripts/, and assets/; every referenced path resolves to a real bundle file, and dedicated 'Local tool index' and 'References and assets' sections make navigation easy.	5 / 5
	Total	19 / 20 Passed

Description

92%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, third-person description that clearly states what the skill does and when to use it, with comprehensive concrete actions and a distinct scientific-peer-review niche. Only minor trigger-term synonyms are missing.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'Prepare evidence-bounded, constructive peer-review drafts and structured manuscript assessments', 'reporting-guideline selection', 'claim–evidence checks', 'methods, statistics, reproducibility, ethics, figure/table, and citation critique', 'revision-response planning' — giving comprehensive coverage of the review domain.	5 / 5
Completeness	Explicitly answers both what ('Prepare evidence-bounded, constructive peer-review drafts and structured manuscript assessments') and when ('Use for authorized review of scientific manuscripts, protocols, preprints, or research proposals; ...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural-term coverage with synonyms ('scientific manuscripts, protocols, preprints, or research proposals', 'peer-review', 'reporting-guideline', 'claim–evidence', 'statistics', 'reproducibility', 'ethics', 'citation'), but a few common phrasings a reviewer might say ('referee report', 'review a paper', 'grant review') are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — authorized scientific peer review — with distinct triggers (manuscripts, preprints, reporting guidelines, claim–evidence checks) and minimal overlap risk with other skills.	5 / 5
	Total	19 / 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: K-Dense-AI/scientific-agent-skills
Path: skills/peer-review/SKILL.md
Commit: 1e5eeff

Reviewed: 3 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.