CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

60

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/paper-self-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%

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

The body covers the skill's scope thoroughly and gives a usable checklist plus an output template, but it suffers from heavy redundancy between Core Features and Review Process and a dangling example reference. Tightening duplication and verifying referenced files would lift it across all dimensions.

Suggestions

Collapse the duplicated 'Core Features' bullets and 'Review Process' steps into a single section so each checklist item appears once, removing the redundant 'Quality Checklist' and 'Common Issues' repeats.

Resolve the dangling reference to examples/example-self-review.md — either create the file or remove the citation under 'Reference Files'.

Add an explicit verification/feedback step after the Claim Audit (e.g., re-check weakened/removed claims against evidence and re-run the checklist) to give the workflow a clear validate->fix->retry checkpoint.

DimensionReasoningScore

Conciseness

The body is mostly efficient but repeats itself: 'Core Features' bullets reappear as 'Review Process' Steps 1-7, the 'Quality Checklist' duplicates the structure-review bullets, and 'Best Practices'/'Common Issues' add generic padding ('Print a hard copy', 'Read aloud'); this matches the level-2 anchor of mostly efficient but could be tightened rather than the lean level-3.

2 / 3

Actionability

It provides concrete per-section questions and a copy-paste Claim Audit output template, but much of the guidance describes what to check ('checking content accuracy and completeness') rather than giving an executable method for doing it, fitting the level-2 anchor of some concrete guidance but incomplete.

2 / 3

Workflow Clarity

The seven-step Review Process gives a clear sequence and a final checklist, but validation/re-verification checkpoints are only implicit (no validate->fix->retry loop after the claim audit), matching the level-2 anchor of sequence present but checkpoints missing or implicit.

2 / 3

Progressive Disclosure

It signals one-level-deep references to real files (references/SECTION-CHECKLIST.md, references/FINAL-VERDICT.md), but the same section questions are duplicated inline AND in SECTION-CHECKLIST.md, and it cites a non-existent examples/example-self-review.md, fitting the level-2 anchor of some structure but content not cleanly split and a dangling reference.

2 / 3

Total

8

/

12

Passed

Description

90%

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 answers both what and when with explicit, natural trigger terms and carves out a distinct niche. Its only weakness is specificity, where 'comprehensive quality assurance checklist' is a single abstract action rather than a list of concrete actions.

DimensionReasoningScore

Specificity

It names the domain ('academic papers') and an action ('Provides comprehensive quality assurance checklist'), but that is a single abstract action rather than a list of multiple concrete actions, so it stops short of the level-3 anchor.

2 / 3

Completeness

It explicitly answers both 'what' ('Provides comprehensive quality assurance checklist for academic papers') and 'when' ('This skill should be used when the user asks to...'), satisfying the level-3 anchor for both what and when with explicit triggers.

3 / 3

Trigger Term Quality

It covers many natural phrases a user would actually say — 'review paper quality', 'check paper completeness', 'validate paper structure', 'self-review before submission', 'audit claims', 'check overclaiming', 'verify whether results support claims' — matching the level-3 'good coverage of natural terms' anchor.

3 / 3

Distinctiveness Conflict Risk

The academic paper self-review/claim-audit niche has distinct triggers and the body further separates it from results-analysis and citation-verification, making conflict with other skills unlikely; matches the level-3 'clear niche with distinct triggers' anchor.

3 / 3

Total

11

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
Galaxy-Dawn/claude-scholar
Reviewed

Table of Contents

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.