peer-review

Structured manuscript/grant review with checklist-based evaluation. Use when writing formal peer reviews with specific criteria methodology assessment, statistical validity, reporting standards compliance (CONSORT/STROBE), and constructive feedback. Best for actual review writing, manuscript revision. For evaluating claims/evidence quality use scientific-critical-thinking; for quantitative scoring frameworks use scholar-evaluation.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

65%

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

A thorough, well-structured peer-review methodology with concrete report templates and a clear staged workflow, but it is token-heavy with inline content and checklists that restate concepts Claude already knows. Some referenced bundle paths do not exist locally.

Suggestions

Move the large presentation-review and scientific-schematic sections into separate reference files and link to them, keeping SKILL.md as a lean overview.

Trim enumerative checklists of well-known peer-review concepts (e.g., generic 'common issues', 'red flags') to only the non-obvious or skill-specific guidance.

Fix broken/external references: either bundle scripts/scientific-slides/scripts/pdf_to_images.py and the venue-templates resource or drop the references, so signaled paths resolve within the skill.

Dimension	Reasoning	Score
Conciseness	The ~570-line body is mostly long enumerative checklists of standard peer-review criteria Claude already knows, plus promotional sections for external skills (scientific-schematics, venue-templates) that add tokens without earning their place.	2 / 3
Actionability	Provides copy-paste-ready report templates (Summary/Major/Minor comments, line-by-line, questions for authors), example slide-issue lines, an example review-process log, and concrete commands (generate_schematic.py, pdf_to_images.py) — actionable for an instruction skill.	3 / 3
Workflow Clarity	Stages 1-7 are clearly sequenced and a final checklist exists, but there are no inter-stage validation gates or feedback loops, so checkpoints are implicit rather than explicit.	2 / 3
Progressive Disclosure	References that exist are signaled one level deep (references/reporting_standards.md, references/common_issues.md, scripts/generate_schematic.py), but large sections (presentations, schematics) are inline that could be split out, and several referenced paths are absent from the bundle (skills/scientific-slides/scripts/pdf_to_images.py, venue-templates).	2 / 3
	Total	9 / 12 Passed

Description

100%

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, well-scoped description that states concrete capabilities, natural trigger terms, and explicit when-to-use guidance while disambiguating from neighboring skills. Third-person voice is maintained throughout.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'methodology assessment, statistical validity, reporting standards compliance (CONSORT/STROBE)... constructive feedback' plus 'review writing, manuscript revision' — rather than vague abstractions.	3 / 3
Completeness	Explicitly states what it does ('Structured manuscript/grant review with checklist-based evaluation') and when to use it ('Use when writing formal peer reviews...'), answering both what and when with explicit triggers.	3 / 3
Trigger Term Quality	Covers natural terms a user would actually say ('manuscript/grant review', 'peer reviews', 'statistical validity', 'reporting standards compliance', 'manuscript revision'), not jargon.	3 / 3
Distinctiveness Conflict Risk	Has a clear niche (formal manuscript/grant peer review) and explicitly disambiguates from adjacent skills ('For evaluating claims/evidence quality use scientific-critical-thinking; for quantitative scoring frameworks use scholar-evaluation').	3 / 3
	Total	12 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (572 lines); consider splitting into references/ and linking	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: K-Dense-AI/claude-scientific-writer
Path: .claude/skills/peer-review/SKILL.md
Commit: 4717803

Reviewed: about 10 hours 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.