Atlas / Skills / galaxy-dawn / Paper Self Review

Paper Self ReviewSAFE

skills/galaxy-dawn/paper-self-review

Semi-automated research assistant for academic research and software development. Supports Claude Code, Codex CLI, Kimi Code CLI, and OpenCode across ideation, coding, experiments, writing, and publication.

Verdict
SAFE
Grade
B
Trust score
89 /100
Version
0.1.0
Hosts
—
License
MIT
Stars
5,693
01

Overview

Semi-automated research assistant for academic research and software development. Supports Claude Code, Codex CLI, Kimi Code CLI, and OpenCode across ideation, coding, experiments, writing, and publication.

Read from source at commit 29ad4d4206fbOBSERVED · 2026-10-07
02

What it tells the agent

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: paper-self-review
description: 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.
version: 0.1.0
---

# Paper Self-Review

A systematic paper quality checking tool that helps researchers conduct comprehensive self-review before submission.

## Core Features

### 1. Structure Review

Check whether all sections of the paper are complete and conform to academic standards:
- Does the Abstract include problem, method, results, and contributions?
- Does the Introduction clearly articulate research motivation and background?
- Is the Method detailed enough to be reproducible?
- Do the Results sufficiently support the conclusions?
- Does the Discussion address limitations and future work?

### 2. Logic Consistency Check

Verify the logical coherence of the paper:
- Do research questions match the methodology?
- Does the experimental design support the research hypotheses?
- Are result interpretations reasonable?
- Are conclusions supported by evidence?

### 3. Citation Completeness

Check the completeness and accuracy of citations:
- Are all citations present in the references?
- Is the reference format consistent?
- Are key related works cited?
- Do citations accurately reflect the original content?

### 4. Research Claim Audit

Check whether the paper's claims are supported by the available evidence:
- Are the main claims supported by results, citations, or analysis artifacts?
- Are speculative observations clearly marked as tentative?
- Does the paper avoid stronger wording than the evidence allows?
- Are negative results, limitations, and missing baselines presented honestly?
- Do conclusions stay inside the tested scope?

This audit does not replace `results-analysis` for statistics or `citation-verification` for bibliographic verification. It checks whether paper claims correctly use the available evidence.

### 5. Figure/Table Quality

Evaluate the quality and effectiveness of figures and tables:
- Do all figures/tables have clear titles and captions?
- Do figures/tables support the text narrative?
- Are figures/tables clear and readable?
- Do formats comply with journal/conference requirements?

### 6. Writing Clarity

Check writing clarity and readability:
- Is the language concise and clear?
- Is technical terminology used appropriately?
- Are sentence structures clear?
- Is paragraph organization logical?

## Quality Checklist

Use this checklist for systematic paper self-review:

```
Paper Quality Checklist:
- [ ] Abstract includes problem, method, results, contributions
- [ ] Introduction clearly states research motivation
- [ ] Method is reproducible
- [ ] Results support conclusions
- [ ] Main claims are supported by named evidence
- [ ] Over-strong claims are weakened or removed
- [ ] Discussion addresses limitations
- [ ] All figures/tables have captions
- [ ] Citations are complete and accurate
```

## When to Use

Use this skill in the following scenarios:

- **Pre-submission check** - Final review before submitting to a journal or conference
- **After first draft** - Systematic review after completing the first draft
- **Before advisor review** - Self-check before requesting advisor feedback to improve quality
- **Post-revision verification** - After revising based on reviewer comments, verify all issues are addressed
- **Collaborator review** - Quality check before sending to collaborators

## Review Process

Follow these steps for systematic paper review:

### Step 1: Structure Review
Start with the overall structure, checking if all sections are complete and logically coherent.

### Step 2: Content Review
Dive into each section, checking content accuracy and completeness.

### Step 3: Research Claim Audit
Check whether each major claim is supported by the evidence available in the draft, analysis bundle, citations, or project notes.

Use this output shape:

```md
## Claim Audit

Claim:
Verdict: keep | weaken | revise | remove
Evidence used:
Missing evidence:
Overclaim risk:
Suggested wording:
```

### Step 4: Citation Check
Verify the completeness and accuracy of all citations.

### Step 5: Figure/Table Review
Check the quality and captions of all figures and tables.

### Step 6: Writing Quality
Review language expression and writing clarity.

### Step 7: Final Checklist
Use the quality checklist for final verification.

## Best Practices

### Review Timing
- **Spaced review** - Wait 1-2 days after completing the draft before reviewing to maintain objectivity
- **Multiple rounds** - Conduct multiple review rounds, focusing on different aspects each time
- **Print review** - Print a hard copy for review; issues are easier to spot on paper

### Review Techniques
- **Reverse reading** - Read from conclusion backwards to check logical coherence
- **Read aloud** - Reading the paper aloud helps identify language issues
- **Reviewer perspective** - Assume you are a reviewer and read critically

### Common Issues
- Abstract too brief or too verbose
- Introduction lacks clear research question statement
- Method lacks sufficient detail for reproduction
- Results lack statistical significance tests
- Discussion doesn't address research limitations
- Figures/tables lack clear titles and captions
- Inconsistent citation formatting

## Summary

The Paper Self-Review skill provides a systematic paper quality checking process, helping researchers identify and resolve issues before submission, improving paper quality and acceptance rates.


## Reference Files

Load only what is needed:
- `references/SECTION-CHECKLIST.md` - section-by-section review questions
- `references/FINAL-VERDICT.md` - how to summarize submission readiness and blocking issues
- `examples/example-self-rev
03

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codeNA
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.

Audited 2026-10-07 · audit v0.4.1 · source sha 29ad4d4206fbfull audit observations/trust-audit/skill/galaxy-dawn__paper-self-review.json · Report an issue / request a re-scan
04

Audit history

Every audit this skill has had.

DateSourceVerdictGradeScoreChange
2026-10-0729ad4d4206fbSAFEB89first audit
05

Questions

What does the Paper Self Review skill do?

Semi-automated research assistant for academic research and software development. Supports Claude Code, Codex CLI, Kimi Code CLI, and OpenCode across ideation, coding, experiments, writing, and publication.

Is Paper Self Review safe to install?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.

What can Paper Self Review access on my machine?

The audit observed no filesystem, network or shell use at all in its source.

How current is this page?

The grade is for one exact copy of the source (29ad4d4206fb), read on 2026-10-07. The repository is watched, and a new audit runs when it changes — this is the first audit.

Advertisement