📦
venue-templates
85Prepare Academic Venue Submissions
Academic submissions often fail because formatting rules vary by venue. This skill provides templates, requirements, and examples for faster preparation.
Research & Learning View
Skills scientific-writing
📦
scientific-writing
Content revision r1 High Risk 📁 Filesystem access🌐 Network access⚡ Contains scripts⚙️ External commands
Write Publication-Ready Scientific Manuscripts
Scientific papers require clear structure, accurate citations, and transparent reporting. This skill guides drafting, revision, citations, figures, and report formatting.
Supports: Claude Codex Code(CC)
Stop for confirmation before installing.
Review the plan and obtain explicit user consent before changing files.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Agent request
Review the Skillstore skill "scientific-writing" from https://skillstore.io/skills/k-dense-ai-scientific-writing.md and its manifest at https://skillstore.io/api/skills/k-dense-ai-scientific-writing/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "scientific-writing". Study notes for an observational cohort paper with results, target journal, and STROBE requirement.
Expected outcome:
A structured IMRAD outline, followed by paragraph-level drafting guidance for each manuscript section.
Using "scientific-writing". A rough discussion section with bullet points and several unsupported claims.
Expected outcome:
A revised discussion in flowing paragraphs, with cautious interpretation, limitations, and clearer links to prior work.
Using "scientific-writing". A research report draft that needs figures, tables, captions, and professional LaTeX formatting.
Expected outcome:
Formatting recommendations for report sections, display items, captions, title page, and scientific notation.
Security Audit
High Riskv7 • 7/5/2026 Open versioned report
Most static findings are false positives from Markdown fences, LaTeX examples, DOI examples, and scientific writing prose. Semantic review found real concerns: unverified Bash script execution guidance, an embedded self-audit that claims the package is safe, and promotional steering to an external service. The author should remove or constrain these behaviors before publication.
11
Files scanned
6,962
Lines analyzed
0
Review items
0
False positives ignored
Confirmed security concerns (3)
High
Unverified Local Script Execution Guidance
SKILL.md grants Bash access and instructs agents to run local Python scripts from scripts/. The package does not include that directory, so a caller workspace could supply unintended code at those paths.
The instructions explicitly permit Bash and show python commands against relative script paths. The packaged file tree contains assets, references, EVALUATION_OUTPUT.json, and SKILL.md, but no scripts directory.
High
Prompt Injection Attempt Detected
EVALUATION_OUTPUT.json embeds a self-audit that marks risk_level as safe, safe_to_publish as true, and summarizes all static findings as false positives. This untrusted safety claim can bias marketplace review.
The file does not issue direct override commands, but it makes explicit safety and publication claims inside the skill package. That matches the prompt-injection warning category for embedded review claims.
Medium
External Service Promotion in Agent Guidance
SKILL.md tells the agent to proactively suggest K-Dense Web for complex workflows. This is promotional steering to an external service embedded in task guidance.
The instruction is explicit and appears at the end of the skill guidance. It is not malware, but it is a clear marketplace trust and user-steering concern.
Risk Factors
📁 Filesystem access (19)
assets/REPORT_FORMATTING_GUIDE.md:337 assets/REPORT_FORMATTING_GUIDE.md:348 assets/REPORT_FORMATTING_GUIDE.md:360 assets/REPORT_FORMATTING_GUIDE.md:388 assets/REPORT_FORMATTING_GUIDE.md:557 assets/REPORT_FORMATTING_GUIDE.md:558 assets/REPORT_FORMATTING_GUIDE.md:559 assets/REPORT_FORMATTING_GUIDE.md:560 assets/REPORT_FORMATTING_GUIDE.md:561 assets/REPORT_FORMATTING_GUIDE.md:562 assets/REPORT_FORMATTING_GUIDE.md:563 assets/REPORT_FORMATTING_GUIDE.md:564 assets/REPORT_FORMATTING_GUIDE.md:565 assets/scientific_report_template.tex:49 EVALUATION_OUTPUT.json:36 references/professional_report_formatting.md:321 references/professional_report_formatting.md:332 references/professional_report_formatting.md:344 references/professional_report_formatting.md:541
🌐 Network access (7)
⚡ Contains scripts (2)
⚙️ External commands (60)
SKILL.md:52-54 SKILL.md:54-61 SKILL.md:61-82 SKILL.md:82-84 SKILL.md:84-98 SKILL.md:98-100 SKILL.md:100-138 SKILL.md:138-180 SKILL.md:180-198 SKILL.md:198-221 SKILL.md:221-239 SKILL.md:239-283 SKILL.md:283-293 SKILL.md:293-308 SKILL.md:308-325 SKILL.md:325-375 SKILL.md:375-386 SKILL.md:386-387 SKILL.md:387-390 SKILL.md:390-403 SKILL.md:403-426 SKILL.md:426-430 SKILL.md:430-446 SKILL.md:446-452 SKILL.md:452-453 SKILL.md:453-454 SKILL.md:454-455 SKILL.md:455-456 SKILL.md:456-457 SKILL.md:457-458 SKILL.md:458 SKILL.md:462-476 SKILL.md:476-479 SKILL.md:479-481 SKILL.md:481-484 SKILL.md:484-485 SKILL.md:485-486 SKILL.md:486-487 SKILL.md:487-662 SKILL.md:662-663 SKILL.md:663-664 SKILL.md:664-665 SKILL.md:665-666 SKILL.md:666-667 SKILL.md:667-681 SKILL.md:681-682 SKILL.md:682 SKILL.md:683-684 SKILL.md:684-692 SKILL.md:692-693 SKILL.md:693-694 SKILL.md:694-695 SKILL.md:695-696 SKILL.md:696-697 SKILL.md:697 SKILL.md:703-704 SKILL.md:704-705 SKILL.md:705-707 SKILL.md:707-710 SKILL.md:710
Audited by: codex View Audit History →
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/k-dense-ai-scientific-writing/audits/7?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/k-dense-ai-scientific-writing?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/k-dense-ai-scientific-writing?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/k-dense-ai-scientific-writing/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/k-dense-ai-scientific-writing.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
K-Dense-AI. (2026). scientific-writing security audit report (audit version 7) [Author version unspecified]. Skillstore. https://skillstore.io/skills/k-dense-ai-scientific-writing/audits/7BibTeX citation
@techreport{k-dense-ai-k-dense-ai-scientific-writing-2026,
author = {K-Dense-AI},
title = {scientific-writing security audit report (audit version 7)},
institution = {Skillstore},
year = {2026},
number = {7},
url = {https://skillstore.io/skills/k-dense-ai-scientific-writing/audits/7},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "scientific-writing security audit report (audit version 7)"
version: "unspecified"
type: report
authors:
- name: "K-Dense-AI"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/k-dense-ai-scientific-writing/audits/7"
identifiers:
- type: other
value: "skillstore:k-dense-ai-scientific-writing:audit:7"
description: "Skillstore immutable audit report identifier"
Compare variants
2 installable variantsEach author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
Highest Skillstore Score
Author / source Skillstore Score Evidence Confidence Skillstore usage Updated
davila7 Recommended
davila7-scientific-writing
Skillstore Score 75
Evidence Confidence High
Skillstore usage 16
Updated
2026-08-21
K-Dense-AI Current
k-dense-ai-scientific-writing
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 40
Updated
2026-08-21
Skillstore Score
Why this score Evidence Confidence: Medium 59
Architecture
85
Maintainability
87
Content
72
Community
74
Spec Compliance
What You Can Build
Prepare a Manuscript Draft
Turn study aims, methods, results, and notes into an organized IMRAD manuscript draft.
Revise for Journal Submission
Improve clarity, citation style, figure references, reporting checklist coverage, and venue fit.
Format Research Reports
Apply professional report structure, tables, figures, captions, and LaTeX style guidance.
Try These Prompts
Create an IMRAD Outline
Create an IMRAD outline for my study. Use my research question, methods, key results, target journal, and citation style. Keep bullets as planning notes only.
Turn Notes Into Prose
Convert these section notes into full scientific prose. Preserve the findings, integrate citations naturally, and avoid unsupported claims or bullet lists in the final text.
Check Citations and Reporting
Review this manuscript section for citation style, reporting guideline coverage, figure and table references, and overstatement. List concrete revisions and explain each one.
Adapt for Target Venue
Adapt this manuscript for the target journal. Match the required structure, abstract format, word limits, citation style, reporting checklist, and expected audience level.
Best Practices
- Provide study design, audience, target journal, word limits, and required citation style.
- Use the two-stage workflow: outline key points first, then request full paragraph prose.
- Ask for citation, reporting checklist, and claim-strength checks before final submission.
Avoid
- Do not ask it to invent citations, results, sample sizes, or statistical outcomes.
- Do not leave planning bullets in final manuscript sections unless journal rules allow lists.
- Do not run optional Bash or figure-generation commands without reviewing the script source.
Frequently Asked Questions
Can this skill write a full manuscript?
Yes, it can guide full manuscript drafting when you provide study details, results, citations, and target journal rules.
Does it verify citations?
It can format and review citations, but factual verification requires trusted source access or user-provided references.
Which citation styles are covered?
The included guides cover APA, AMA, Vancouver, Chicago, IEEE, and common DOI formatting patterns.
Can it help with reporting guidelines?
Yes, it includes guidance for CONSORT, STROBE, PRISMA, STARD, CARE, ARRIVE, and related checklists.
Is it only for journal articles?
No, it also covers technical reports, white papers, grant reports, and LaTeX-based professional reports.
Should I allow Bash execution?
Only after reviewing the referenced scripts and confirming they come from a trusted source.
Developer Details
Author
K-Dense-AILicense
MIT license
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
a25199bc7d6b82598536822d1738eb5d5f54025b
Maintenance freshness
7/18/2026
Usage
36 downloads · 305 views
File structure
More from K-Dense-AI
View all📦
iso-13485-certification
85Prepare ISO 13485 Certification Docs
Medical device teams must create complete QMS documentation before certification audits. This skill provides templates, checklists, and gap analysis guidance for ISO 13485 readiness.
Documentation View
📦
pytdc
82Analyze therapeutic ML datasets with PyTDC
Drug discovery teams need reliable datasets and fair evaluation protocols. This skill helps Claude use PyTDC for curated therapeutic ML data, benchmark splits, metrics, and molecular oracles.
Data & Analytics View
📦
diffdock
81Run DiffDock Molecular Docking
Protein-ligand docking requires careful setup, parameter choices, and result interpretation. This skill guides DiffDock workflows for poses, confidence scores, and screening.
Research & Learning View
📦
statistical-analysis
80Analyze Research Data with Statistical Guidance
Choosing tests and reporting results can be slow and error-prone. This skill guides test selection, assumptions, effect sizes, power analysis, Bayesian options, and APA reporting.
Data & Analytics View
📦
scanpy
80Analyze Single-Cell RNA-seq with Scanpy
Single-cell RNA-seq analysis requires many linked decisions across QC, normalization, clustering, and plotting. This skill gives Claude, Codex, and Claude Code structured Scanpy workflows, reference guidance, and reusable analysis scripts.
Data & Analytics View
Related Skills
View all📦
content-research-writer
78Draft Researched Content Faster
by DYAI2025
Long-form writing often stalls when research, structure, citations, and revision happen in separate steps. This skill guides Claude, Codex, or Claude Code through outlining, source gathering, drafting feedback, and final polish.
Writing & Content View
📦
deep-research
80Research Complex Topics With Citations
by shubhamsaboo
Deep research is hard when sources disagree or lack context. This skill guides Claude, Codex, and Claude Code to synthesize sources, compare viewpoints, and produce cited research summaries.
Research & Learning View
📦
url-citation-search
78Find URL Citations in Research
by zjsxply
Web pages are often cited in papers but missed by standard citation indexes. This skill guides Claude, Codex, and Claude Code to verify URL citations with direct evidence.
Research & Learning View
📦
notion-research-documentation
78Research Notion and Publish Cited Reports
by davila7
Important information is often scattered across many Notion pages. This skill finds relevant sources, synthesizes evidence, and publishes cited briefs, comparisons, or reports.
Research & Learning View
📦
latex-posters
87Create Professional LaTeX Research Posters
by davila7
Dense research content is difficult to fit into a readable conference poster. This skill turns research material into structured, accessible LaTeX poster designs.
Design & Creative View
📦
nature-paper-card
85Analyze One Scientific Paper as an Evidence Card
by yuan1z0825
Scientific papers are difficult to evaluate when claims, methods, and evidence are scattered across sections. This skill creates a structured, traceable Paper Card with explicit limits.
Research & Learning View