peer-review

Use before submission or when reviewing papers - provides evaluation checklists, bias detection, and self-review templates

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/peer-review/SKILL.md

Quality

Content

65%Weight 40%Scale 1-3

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

A well-organized, actionable peer-review guide with concrete templates and prompts, but it is monolithic with no progressive disclosure and the workflow lacks explicit verification checkpoints. Some redundancy in the final checklist could be trimmed for token efficiency.

Suggestions

Add explicit validation checkpoints between review stages (e.g., "verify your summary against the abstract before proceeding to section review") to strengthen workflow clarity.

Move the report-template and self-review-prompt blocks into reference files (e.g., templates/review-report.md, prompts/self-review.md) and link to them from SKILL.md to improve progressive disclosure.

Remove or consolidate the final "审稿检查清单" with the earlier checklists to reduce redundancy and respect the token budget.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes Claude's competence (no over-explanation of what papers or statistics are), but the final "审稿检查清单" recapitulates items already covered in sections one and two, so it could be tightened.	2 / 3
Actionability	Provides copy-paste-ready instruction guidance — a markdown report template, a structured self-review prompt (Role/Task/Output/Input), a quick-check prompt, and bias/logic tables — giving concrete, executable direction.	3 / 3
Workflow Clarity	The three-stage review workflow (阶段1→2→3) is clearly sequenced with specified outputs, but it lacks explicit validation/verification checkpoints between stages, leaving the gates implicit.	2 / 3
Progressive Disclosure	The skill is a single ~170-line file with well-organized sections but no bundle files; substantial reference material (report templates, prompt blocks) that could be split into separate reference files remains inline, fitting the anchor where content that should be separate is inline.	2 / 3
	Total	9 / 12 Passed

Description

85%Weight 40%Scale 1-3

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 concise, third-person description that clearly conveys both capability and trigger conditions, with concrete deliverables and a distinct academic-review niche. Its main weakness is trigger-term coverage, which misses several natural phrasings a user might say.

Suggestions

Broaden trigger terms to include common user phrasings such as "peer review", "manuscript review", "refereeing", or "审稿" so the skill matches more natural requests.

Consider naming the deliverable formats explicitly (e.g., "generates a structured review report") to make the output even more concrete.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete deliverables — "evaluation checklists, bias detection, and self-review templates" — matching the anchor for naming several specific actions.	3 / 3
Completeness	Explicitly states both what it does ("provides evaluation checklists, bias detection, and self-review templates") and when to use it ("Use before submission or when reviewing papers"), satisfying the what-and-when requirement.	3 / 3
Trigger Term Quality	"Use before submission or when reviewing papers" includes natural terms (submission, reviewing papers) but omits common variations such as "peer review", "manuscript", or "审稿", so it falls short of full coverage.	2 / 3
Distinctiveness Conflict Risk	The academic paper-review niche with "submission" and "reviewing papers" triggers is clearly distinguishable from other skills and unlikely to fire for unrelated tasks.	3 / 3
	Total	11 / 12 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: Norman-bury/research-writing-skill
Path: skills/peer-review/SKILL.md
Commit: 6f79595

Reviewed: 10 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.