Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
Muse
Dots+21 moreClaude CodeCursorCodex CLIMuseDots
Manus
Grok
Grok Bot+18 agentsMedical & Clinical Writing Skill for AI Agents Skill
Draft and QC medical manuscripts, abstracts, and posters using clinical reporting frameworks and evidence traceability.
$29.99
Medical & Clinical Writing Skill for AI Agents Skill
Example session with this skill installed
Review this draft abstract for a Phase II trial against the provided results table. Check for consistency and apply CONSORT reporting standards for abstracts.
- Read your context and instructions
- Compiled the medical & clinical
I have reviewed the Phase II trial abstract against the provided results table and the CONSORT for Abstracts reporting checklist.
Clinical Writing QC Summary
Scope: Phase II Trial Abstract Review
Framework: CONSORT for Abstracts (2008)
Status: Completed with 1 Critical and 2 Major findings.
| Item | Finding | Severity | Rationale | Recommended Action |
|---|---|---|---|---|
| Methods | Randomization technique missing. | Major | CONSORT Item 4 requires description of random sequence generation. | Add '1:1 computer-generated randomization' per protocol page 12. |
| Results | Primary endpoint discrepancy. | Critical | Abstract states 85% response; Source Table 2 indicates 78% (N=45/58). | Update abstract to 78% to match source data. |
| Results | Adverse Events (AEs) denominator. | Major | The denominator in text (n=60) exceeds the ITT population (n=58). | Correct denominator to 58 per CONSORT Item 12. |
| Conclusions | Balanced interpretation. | Minor | Conclusion implies superiority without p-value for secondary endpoints. | Soften language to 'suggested improvement' until p-values are confirmed. |
Evidence Traceability Matrix
- Claim: "78% (45/58) of patients achieved the primary endpoint." -> Source: Table 2, Row 1, Column C.
- Claim: "Most common AE was fatigue (12%)." -> Source: Safety Summary Table, Section 4.2.
Next steps
- Update the Results section to correct the primary endpoint percentage.
- Insert the randomization method from the study protocol to meet CONSORT requirements.
- Verify the final AE denominator before human sign-off.
Connects securely to your tools. The creator never sees your data.
About this skill
This skill provides a structured framework for drafting and quality-checking medical, clinical, and scientific documents. It addresses the high-stakes need for accuracy in pharmaceutical workflows by enforcing evidence-first drafting and systematic QC against established reporting standards.
What it does
- Evidence-first drafting generates manuscripts, abstracts, and posters using only supplied study data and protocols to prevent hallucinated results.
- Framework application applies specific reporting guidelines such as CONSORT, PRISMA, and STROBE based on study design and document type.
- Scientific consistency checking cross-references data points across tables, figures, and text to flag arithmetic errors or inconsistent sample sizes.
- Prioritized QC reporting categorizes findings by severity from minor style issues to critical safety or data integrity gaps.
- Traceability mapping links material claims directly to source passages or verified references for audit-ready documentation.
How it works
- Intake and Scoping where you provide the document type, target journal or congress, and raw study data or protocol files.
- Framework Selection to identify which reporting standards (e.g., GPP, ICMJE) apply to the specific study design.
- Structured Production of the requested content, ensuring interpretations remain distinct from observed findings.
- Validation and Handoff including a QC summary, traceability matrix, and a human-review checklist for final verification.
Frameworks & tools
This tool utilizes clinical reporting guidelines including CONSORT, PRISMA, STROBE, CARE, and SPIRIT. It adheres to ICMJE and Good Publication Practice (GPP) principles for publication workflows.
Why this beats prompting it yourself
Generic prompts often hallucinate p-values or fail to maintain consistency between abstracts and results tables. This skill enforces a "not assessable" state for missing data and uses a tiered QC severity model that mimics professional medical writing workflows.
Use cases
- Draft a manuscript introduction and methods section from a clinical study protocol.
- Perform a consistency audit on a congress poster against raw data tables.
- Convert a full manuscript into a structured abstract following specific journal word limits.
- Generate an evidence traceability matrix for a medical communication piece.
Known limitations
Requires specific source data to function. Cannot verify references against external sources not provided in the context. Does not substitute for professional medical or regulatory review.
Requires provided source data; cannot invent missing results. Cannot access external subscription journals for citation verification. Not a substitute for qualified human medical review.
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
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 24 days ago