- Home
- Skills
- Research & Analysis
- reviewer
Works with the AI Agents you already use
reviewer
A full pre-submission peer review that finds the weaknesses real reviewers will flag, before they do.
$9
reviewer
Example session with this skill installed
Use reviewer to do a pre-submission review of my manuscript on few-shot object detection before I submit it.
- Read your context and instructions
- Compiled the reviewer
Reviewed the manuscript against 10 dimensions. Overall: revise before submitting. Two major weaknesses (experimental rigor, missing ablations) and three minor issues, with concrete fixes.
Scorecard
| Dimension | Score | Notes |
|---|---|---|
| Novelty | 7/10 | Solid, but positioned against 2 missing baselines |
| Clarity | 8/10 | Method section is clear; intro is dense |
| Contribution significance | 7/10 | Impact understated in intro |
| Methodological rigor | 5/10 | No significance testing; single seed reported |
| Experimental validity | 5/10 | Missing cross-dataset generalization |
| Threats to validity | 6/10 | Discussed but no mitigation plan |
| Reproducibility | 7/10 | Code promised, no configs shown |
| Figures and tables | 7/10 | Fig. 3 crowded; add a summary table |
| References | 8/10 | Complete, 2 self-citations borderline |
| Structure | 8/10 | Follows IMRaD |
Top 3 fixes (do these first)
- Add baselines: compare against the two strongest recent methods, since reviewers will ask.
- Add rigor: report the mean ± std over 5 seeds and a significance test (McNemar or paired t-test).
- Add a cross-dataset experiment to preempt the overfit-to-one-benchmark criticism.
Likely reviewer concerns (and your answers)
- Why not method X? Cite it and explain the fair-comparison rationale.
- Results are marginal. Add effect sizes and the significance test above.
Next steps
- Apply the top 3 fixes, then re-run
reviewerto confirm the score rises above 7/10 across the board.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Reviewers find the same weaknesses every time: weak baselines, missing ablations, unsupported claims, and unclear figures. Finding them yourself before submission is far cheaper than a rejection. This skill performs a comprehensive pre-submission review.
What it does
- Evaluates novelty, clarity, contribution significance, methodological rigor, and experimental validity.
- Checks threats to validity, reproducibility, figure and table quality, and reference completeness.
- Identifies the weaknesses real reviewers would flag and suggests concrete fixes.
- Produces a scored report with a prioritized fix list.
Why this beats prompting it yourself
General prompts return polite, vague feedback. This skill scores the paper across ten dimensions, separates critical from minor issues, and simulates the exact questions a reviewer will ask, with suggested answers.
Use cases
- Running a pre-submission review before submitting.
- Preparing for resubmission after a rejection.
- Doing a friendly internal review before sharing with collaborators.
- Quality assurance before posting a preprint.
Known limitations
It is a pre-submission triage, not a substitute for real peer review. It works only with the draft you provide, and some judgments, such as novelty, remain partly subjective.
Important
It reviews and scores the manuscript; it does not rewrite it for you. Apply the fixes, then re-run it to confirm the score rises, as the final step of the Polish Pack.
Why buy it
Use it before submitting to anticipate and address reviewer concerns. It is the cheapest second opinion you can get and the final step of the Polish Pack.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Research & Analysis.
Requires complete paper draft (all sections, figures, references) and target venue for accurate calibration. Cannot verify raw data or physical code execution.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 1 month ago
Permissions
No special permissions declared or detected