paper-self-review

This skill should be used when the user asks to "review paper quality", "check paper completeness", "validate paper structure", "self-review before submission", "audit claims", "check overclaiming", "verify whether results support claims", or mentions systematic paper quality checking. Provides comprehensive quality assurance checklist for academic papers.

Quality

74%

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/paper-self-review/SKILL.md

Quality

Content

57%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.

The body is a competent, mostly efficient paper-review guide with concrete checklists and a useful claim-audit output template. Its main weaknesses are duplication between the Core Features and Review Process sections, a missing validation/feedback loop in the review workflow, and one non-existent referenced file.

Suggestions

Collapse the "Core Features" sections into the "Review Process" steps to remove the duplication between sections 1-6 and Steps 1-7 and tighten the body.

Add an explicit validation/recheck checkpoint to the review workflow (e.g., after Step 3, re-verify each weakened claim is still supported before moving on) to lift workflow clarity above the batch-operation cap of 3.

Create the missing examples/example-self-review.md referenced in "Reference Files", or remove the dangling reference, so all listed bundle paths resolve.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and does not explain concepts Claude already knows, but the "Core Features" sections (Structure Review, Logic Consistency, etc.) substantially duplicate the later "Review Process" steps and the "Quality Checklist", adding padding. Not a 4 because the duplication is noticeable rather than minor.	3 / 5
Actionability	Provides concrete checklists, a copy-paste-ready Claim Audit output shape, and named reference files to load. Falls short of 5 because most guidance is question-style checks rather than fully specified executable procedures beyond the claim-audit template.	4 / 5
Workflow Clarity	A clear 7-step sequence exists and Step 3 includes an output template, but this batch review operation has no explicit validation checkpoints or fix/retry feedback loops (e.g., re-check after weakening a claim). Per the rubric, missing validation in a batch workflow caps this at 3.	3 / 5
Progressive Disclosure	A "Reference Files" section points to two real reference files (verified: references/SECTION-CHECKLIST.md and references/FINAL-VERDICT.md), but it also references examples/example-self-review.md which does not exist, and inline content that could live in references is duplicated in the body. Structure is present but with a broken link and organizational gaps.	3 / 5
	Total	13 / 20 Passed

Description

91%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.

The description is strong: it explicitly pairs a clear "what" with a rich set of natural "when" trigger phrases and carves out a distinct niche. The only minor gap is that the capability statement is a single bundled checklist rather than a list of distinct concrete actions.

Dimension	Reasoning	Score
Specificity	Names the domain (academic paper quality) and several concrete actions via trigger phrases like "review paper quality", "audit claims", and "verify whether results support claims". Falls just below 5 because the "what" is summarized as a single checklist rather than enumerating multiple distinct concrete capabilities.	4 / 5
Completeness	Explicitly answers both "what" ("Provides comprehensive quality assurance checklist for academic papers") and "when" ("This skill should be used when the user asks to...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases users would actually say ("review paper quality", "self-review before submission", "check overclaiming") including synonyms and variations, matching the anchor for full coverage.	5 / 5
Distinctiveness Conflict Risk	Clear niche (pre-submission paper self-review) with distinct triggers; minor overlap risk with related research skills, and the body helpfully notes it does not replace results-analysis or citation-verification.	4 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Galaxy-Dawn/claude-scholar
Path: skills/paper-self-review/SKILL.md
Commit: 6ed46da

Reviewed: 8 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.