Scientific manuscripts with automatic review and a separate editorial handoff.
Write and revise scientific manuscripts from results, materials and ideas. Review paragraphs, reconcile sections and companion files, and deliver clean scientific content with a separate editorial decision record. Supports bounded edits, complete manuscripts and rebuttals across study types; the bundled house DOCX template is optional.
$5.00 one-off
Preview — package delivery is not available yet
A file-reading agent runtime for drafting and review; house templates are optional
The earlier ClinicalSpark draft is now the shared input for complete revisions with 1.0.1 and 1.1.0. Inspect both manuscripts and the AI-assisted comparison. This single retrospective demonstration has no independent human rating.
The earlier ClinicalSpark input draft was revised independently with the frozen 1.0.1 and 1.1.0 skills. Both sessions received the same complete-writing request and the exact same manuscript, including its eight tables and ten supplied references. The Word files below contain the resulting revisions.
Both revisions retain the central estimates and qualify clinical claims. In this pair, 1.1.0 organizes the argument and editorial handoff more clearly; 1.0.1 flags certain numerical inconsistencies more explicitly. The comparison records both strengths and remaining issues.
One retrospective demonstration, with AI-assisted review and no independent human rating. The source describes demonstration analyses; these manuscripts do not establish clinical findings or general performance across studies.
The writing workflow now includes automatic paragraph review and reconciliation across the manuscript and requested companions. Section guidance explains the reader-facing purpose of titles, abstracts, introductions, methods, findings, discussion, displays and back matter. Study-specific review avoids imposing IMRAD or statistical tests on every task.
Editorial decisions and preparation notes are kept in a separate record. Actual null, adverse and opposing findings, essential methods and necessary qualifications remain scientific content. Approved wording and native editable sources are preserved unless a concrete change is warranted.
The original 16-page assembly is retained for historical reference. Its input is the same draft used in the comparison above. The historical output predates these fresh revision sessions and is not their 1.0.1 baseline.
44 files · 461 KiB unpacked · standard Agent Skills layout
Package delivery is not available yet. These instructions describe installation once you have the ZIP. The compatibility table records the actual test date, environment and scope for each agent.
Installation overview. Follow the steps for your agent and check the compatibility table for the tested scope.
Checkout and package delivery are not available yet. These are installation instructions for a future downloaded ZIP.
Preview — package delivery is not available yet
The steps below describe installation once you have the ZIP. Checkout and downloads are not enabled.
Personal scope shown; use <project>/.claude/skills/ for project scope. Claude.ai (web) accepts the zip directly under Settings → Skills, but cannot run the bundled Python tooling.
mkdir -p ~/.claude/skills/scientific-writing
unzip scientific-writing-1.1.0.zip -d ~/.claude/skills/scientific-writingA new session discovers the skill automatically from its SKILL.md description.
claude -p "Do you have the scientific-writing skill available? State its name and what it does."| Agent | Status | Method | Notes |
|---|---|---|---|
| Claude Code 2.1.209 | Untested | Native discovery from ~/.claude/skills / <project>/.claude/skills | Native discovery has not been retested for 1.1.0. Historical scope: The skill was developed in and is used daily in Claude Code; this catalog's curation ran in it. |
| Codex CLI 0.146.0 | Untested | Native discovery from ~/.codex/skills | Native discovery has not been retested for 1.1.0. Historical scope: Smoke test passed: named the skill, quoted its mandated process, and named its bundled script — all read from the installed package. |
| Antigravity (agy) 1.1.8 | Untested | Explicit pointer: tell the agent to read SKILL.md | Native discovery has not been retested for 1.1.0. Historical scope: No native skills-directory injection observed in headless mode; interactive sessions load it by pointer. In the AROS stack, ~/.gemini/skills is surfaced by the AROS layer. |
| claude.ai (web) — | Untested | Zip upload under Settings → Skills | Native discovery has not been retested for 1.1.0. Historical scope: The package matches the upload format, but the web sandbox cannot run the bundled Python tooling. |
| OpenClaw — | Untested | Standard Agent Skills layout | Native discovery has not been retested for 1.1.0. Historical scope: Not available on our test bench. If you verify it, tell us and we'll record it here. |
Organization-use commercial license for Nexitia material; identified K-Dense guides and upstream passages remain MIT. Outputs may be published and used commercially. Earlier grants are preserved.
The displayed price does not change the license. Terms apply to the identified edition; earlier grants and third-party rights are preserved.
Developed from AROS-core manuscript-writing practice. Edition 1.1.0 adds general section principles, automatic finalization and editorial records to the preserved 1.0.1 source. K-Dense-derived guides retain their MIT scope; book-informed section guidance is attributed and no book text is bundled.
SHA-256 of scientific-writing-1.1.0.zip — verify your download against this hash:
59857a1a11769a98070bdda3d594c1e399c143cf7c55f2be365469da13e62d0b