- Home
- Skills
- Research & Analysis
- research paper assistant 2
research paper assistant 2
Scientific manuscript assistant for drafting, peer review, language editing, and automated statistical verification.
$5
/moSubscription · cancel anytime
Secure checkout via Stripe
- Always the latest version
- Delivered live to your agent via MCP
- Cancel anytime, access ends at period end
Works with the AI Agents you already use
research paper assistant 2
Example session with this skill installed
Review the attached Methods and Results sections for a study on solar cycle forecasting. Check the statistics, verify the 13-month smoothing, and provide a scientific review report.
- Read your context and instructions
- Compiled the research paper assistant
I have completed the scientific and statistical audit of your Methods and Results sections. The automated statcheck_lite.py verified the reported t-tests, and forecast_eval.py was used to validate the solar cycle smoothing.
Scientific Review & Statistical Audit
| Check Type | Status | Findings |
|---|---|---|
| Statistical Consistency | PASS | Recomputed p-values (p=0.034) match the reported t(42)=2.18. |
| Smoothing Verification | WARNING | The 13-month tapered mean deviates from SILSO V2.0 standard at cycle 24 boundary. |
| IMRaD Compliance | ISSUE | Results section contains interpretation of mechanism, which belongs in Discussion. |
| Forecast Metrics | PASS | MASE = 0.82 and sMAPE = 12.4% confirm skill against the persistence baseline. |
| Reference Match | PASS | All 12 citations in these sections are present in the reference list. |
Major Issues
Smoothing Implementation: Your smoothing uses a standard rolling average rather than the tapered 13-month window required for SILSO-linked sunspot data. This shifts the peak timing by approximately 2 months.
2.
Causal Language: In paragraph 3 of the Results, you state the solar flux "drove" the anomaly. As this is a correlational observation, the phrasing should be moderated to "was strongly associated with."
Statistical Reporting (APA 7th)
The proposed model demonstrated significant predictive skill ($t(42) = 2.18, p = .034, d = 0.65$). The out-of-sample $R^2$ was $0.78$, representing a $14%$ improvement over the climatology baseline.
Next steps
- Update the smoothing algorithm using
scripts/forecast_eval.py smooth --smooth13. - Move the interpretive sentences in lines 45-52 of the Results to the Discussion section.
- Add the Diebold-Mariano test results to Table 1 to strengthen the model comparison.
Subscription · always the latest version
- Secure checkout via Stripe
- Cancel anytime
- Delivered live via MCP
About this skill
Writing a scientific paper is an exercise in precision that often falls apart under the weight of structural errors, weak statistics, or language barriers. This skill provides a specialized multi-agent workflow to plan, draft, and audit manuscripts according to IMRaD standards and journal-specific guidelines. It handles the heavy lifting of scientific reporting, from verifying p-values to ensuring the Discussion section actually answers the objectives set in the Introduction.
What it does
- Scientific auditing performs deep reviews of manuscript logic, checking for over-generalized conclusions and internal data consistency.
- Statistical verification recomputes p-values from reported test statistics and runs new analyses including ANCOVA, regression, and time-series forecasting.
- Language refinement edits for clarity, tone, and grammar in both English and Arabic manuscripts while preserving the author's voice.
- Automated structural checks validates word counts, citation styles, figure numbering, and required submission statements.
- Continuous learning stores researcher preferences, field-specific terminology, and previous corrections to improve future drafts.
How it works
- Context loading initializes the session by reading the local knowledge base and any attached project style guides.
- Technical audit runs automated scripts to verify references, recompute statistics, and audit text for readability markers.
- Mode execution applies specific frameworks for scientific review, language editing, or manuscript building based on the current drafting stage.
- Validation performs a final check against target journal profiles and reporting guidelines before generating the submission package.
Frameworks & tools
The skill utilizes Python scripts for data analysis (stats_analyzer, statcheck_lite), forecast evaluation (forecast_eval), and manuscript structure validation. It integrates with Crossref and OpenAlex APIs for reference verification and uses Pandoc for document processing.
Why this beats prompting it yourself
Generic prompts often miss the nuances of scientific IMRaD structure and fail to verify the mathematical accuracy of reported data. This skill uses dedicated code to recompute statistics and enforce specific drafting orders, ensuring the evidence dictates the narrative rather than the other way around.
Use cases
- Reviewing a draft for "red flags" and reporting guideline compliance before submission.
- Re-analyzing raw data to generate APA-style results and high-resolution figures.
- Transforming a thesis chapter into a concise journal article or data paper.
- Responding to peer reviewers by tracking changes and drafting formal rebuttal letters.
Known limitations
Network restrictions may occasionally require manual uploads of SILSO data or reference databases. The skill flags but does not automatically correct highly technical field-specific terminology.
Requires Pandoc or pdftotext for file extraction. Reference checks depend on API availability. Arabic language support focuses on editing and terminology, not full translation.
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 any payment.
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
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 24 days ago
Requires
Permissions
Allowed Hosts