Skip to content

kgraph57/paper-writer-skill

paper-writer

Verified

Medical/scientific paper writing workflow skill. Manages the full pipeline from literature search to submission-ready manuscript. Creates and manages a project directory with IMRAD-format section files, literature matrix, reference management, and quality checklists. Supports both English and Japanese papers. Triggers: 'write paper', 'paper-write', 'start manuscript', '論文を書く', '論文執筆', '論文プロジェクト', 'manuscript', 'research paper', '原稿作成'.

FileKindSize
SKILL.mdskill md77.7 KB
examples/case-studies/discovery-to-draft.mdmarkdown5.3 KB
references/abstract-formats.mdmarkdown5.1 KB
references/adversarial-review.mdmarkdown21.6 KB
references/ai-disclosure.mdmarkdown6.4 KB
references/ai-for-science-model.mdmarkdown12.8 KB
references/citation-guide.mdmarkdown2.4 KB
references/citation-verification.mdmarkdown10.5 KB
references/clinical-trial-registration.mdmarkdown4.7 KB
references/coauthor-review.mdmarkdown14.2 KB
references/coi-detailed.mdmarkdown6.8 KB
references/desk-rejection-prevention.mdmarkdown6.1 KB
references/hook-compatibility.mdmarkdown6.1 KB
references/humanizer-academic.mdmarkdown12.0 KB
references/imrad-guide.mdmarkdown2.5 KB
references/journal-reformatting.mdmarkdown5.6 KB
references/journal-selection.mdmarkdown13.5 KB
references/keywords-guide.mdmarkdown4.6 KB
references/master-reference-list.mdmarkdown11.3 KB
references/multilingual-guide.mdmarkdown12.4 KB
references/novelty-check.mdmarkdown13.8 KB
references/open-access-guide.mdmarkdown4.6 KB
references/pubmed-query-builder.mdmarkdown16.7 KB
references/reporting-guidelines-full.mdmarkdown10.6 KB
references/reporting-guidelines.mdmarkdown3.2 KB
references/section-checklist.mdmarkdown4.5 KB
references/statistical-reporting-full.mdmarkdown8.6 KB
references/statistical-reporting.mdmarkdown22.5 KB
references/submission-portals.mdmarkdown4.1 KB
references/supplementary-materials.mdmarkdown3.9 KB
references/tables-figures-guide.mdmarkdown7.7 KB
references/word-count-limits.mdmarkdown4.6 KB
scripts/analysis-template.pyexecutablescript19.6 KB
scripts/compile-manuscript.shexecutablescript6.9 KB
scripts/forest-plot.pyexecutablescript16.9 KB
scripts/sr-dedup.pyexecutablescript12.5 KB
scripts/sr-pdf-link.pyexecutablescript6.8 KB
scripts/sr-prisma-count.pyexecutablescript8.7 KB
scripts/table1.pyexecutablescript9.7 KB
scripts/word-count.shexecutablescript12.8 KB
templates/abstract.mdmarkdown1.3 KB
templates/acknowledgments.mdmarkdown1.7 KB
templates/analysis-workflow.mdmarkdown5.1 KB
templates/case-abstract.mdmarkdown1.2 KB
templates/case-introduction.mdmarkdown1.7 KB
templates/case-report.mdmarkdown2.2 KB
templates/conclusion.mdmarkdown1.0 KB
templates/cover-letter.mdmarkdown1.3 KB
templates/data-management.mdmarkdown5.7 KB
templates/declarations.mdmarkdown6.1 KB
templates/discussion.mdmarkdown1.8 KB
templates/graphical-abstract.mdmarkdown2.7 KB
templates/highlights.mdmarkdown3.8 KB
templates/human-loop-ledger.mdmarkdown9.4 KB
templates/introduction.mdmarkdown1.8 KB
templates/limitations-guide.mdmarkdown6.2 KB
templates/literature-matrix.mdmarkdown1.2 KB
templates/methods.mdmarkdown1.9 KB
templates/preregistration.mdmarkdown19.5 KB
templates/project-init-case.mdmarkdown3.2 KB
templates/project-init.mdmarkdown3.6 KB
templates/proof-correction.mdmarkdown2.5 KB
templates/research-question.mdmarkdown18.6 KB
templates/response-to-reviewers.mdmarkdown12.5 KB
templates/results.mdmarkdown1.5 KB
templates/review-article.mdmarkdown11.6 KB
templates/revision-cover-letter.mdmarkdown10.3 KB
templates/sr-data-extraction.mdmarkdown9.2 KB
templates/sr-grade.mdmarkdown14.7 KB
templates/sr-outline.mdmarkdown13.5 KB
templates/sr-prisma-flow.mdmarkdown12.9 KB
templates/sr-prospero.mdmarkdown15.9 KB
templates/sr-rob.mdmarkdown18.3 KB
templates/sr-screening-pipeline.mdmarkdown12.1 KB
templates/study-design.mdmarkdown28.5 KB
templates/submission-ready.mdmarkdown2.5 KB
templates/title-page.mdmarkdown3.5 KB

examples/case-studies/discovery-to-draft.md

View on GitHub
# Case Study: Discovery → Draft → Humanize → Adversarial Catch

A two-minute read of one illustrative pass through the skill's pipeline. The clinical spark is **PHI-free and fictional** — built to show the product shape, not a real patient. Every template and checklist named below already exists in this repository.

> **The loop:** Input → Discovery → Weak path → Gated path → Humanize → Adversarial → Proof

## 1. Input — the spark a clinician actually has

Illustrative, de-identified notes (entire input; no cleanup):

```text
Want a CARE case report.
Non-diabetic adult started a GLP-1 agonist for weight management.
Within 3 weeks: recurrent symptomatic hypoglycemia, workup otherwise unrevealing.
Stopped the drug; events resolved.
Have labs timeline + meds list (de-identified). IRB waiver for single case on file.
Target journal leaning BMJ Case Reports. Language: English.
```

## 2. Discovery — forge questions, then lock the IDEA

Phase −1 does not open a blank Methods section. It forges FINER-scored candidates, runs a novelty skim against live literature, and stops at the human gates:

| Candidate | FINER sketch | Novelty skim (illustrative) |
| --- | --- | --- |
| Q1. Mechanism review of GLP-1 and glucose in non-diabetics | Broad; weak "case" fit | Crowded review space |
| **Q2. CARE report: temporal association + negative workup + dechallenge** | Feasible with on-hand data | Room for a well-documented single case |
| Q3. Series protocol for prospective capture | Needs resources not available | Wrong product for this spark |

**Human locks Q2** (💡 IDEA). **Human confirms** the lab/meds extract is real and de-identified (📊 DATA). The skill does not invent glucose values or a patient.

Artifacts used: `templates/research-question.md`, `templates/project-init-case.md`, `references/novelty-check.md`, `references/ai-for-science-model.md`.

## 3. Weak path — "just write the paper"

If you skip gates and ask a generic model for an abstract, you often get significance inflation and promotional language (patterns the repo's humanizer is built to kill):

```text
This landmark case underscores a pivotal challenge in the evolving
therapeutic landscape of GLP-1 agonists, highlighting the crucial need
for heightened clinical vigilance in non-diabetic populations.
```

Accurate vibe, useless science writing. No timeline. No CARE structure. No limits stated.

## 4. Gated path — outline, exhibits, then prose

With gates on:

1. **Literature matrix** (≥10 sources, DOIs checked) before outline approval.
2. **Outline** mapped to CARE sections; human approval required.
3. **Tables/figures before prose** — e.g. Table 1 timeline of glucose / meds; Figure 1 clinical course.
4. **Draft in writing order** (Case presentation → Discussion → … → Abstract → Title).
5. Stage-gates refuse to proceed on FAIL (feedback → fixer → re-check, max 3).

Relevant templates: `templates/case-report.md`, `templates/case-abstract.md`, `templates/literature-matrix.md`, `references/reporting-guidelines.md` (CARE).

## 5. Humanize — two real pattern fixes

From `references/humanizer-academic.md`:

| Pattern | Before | After |
| --- | --- | --- |
| Significance inflation | "represents a pivotal challenge in the evolving landscape" | "is uncommon but clinically important when hypoglycemia appears after GLP-1 initiation in a non-diabetic adult" |
| Superficial -ing analysis | "glucose normalized after cessation, highlighting the drug's role" | "glucose normalized after cessation (dechallenge); rechallenge was not performed." |

Phase 4's gate requires high-priority AI patterns = 0 before references/quality review.

## 6. Adversarial review — catch the overclaim

`references/adversarial-review.md` red-teams the central claim. Illustrative finding:

> **Overclaim:** Abstract implies causality ("GLP-1 caused hypoglycemia") from a single uncontrolled case.
> **Fix:** Frame as temporal association + dechallenge; state that causality cannot be proven; list alternative explanations considered and why they were less likely.
> **Verdict:** Revise (not KILL) — the IDEA is intact; the wording overreached.

A true **KILL** (fatal design/ethics/data problem) would return to Phase −1 instead of polishing a bad paper.

## 7. Proof — what already ships in-repo

You do not need to trust a staged "accepted paper." Reproduce the workflow pieces that exist today:

| Piece | Where |
| --- | --- |
| Operating model (IDEA/DATA sovereignty) | `references/ai-for-science-model.md` |
| Novelty + adversarial guides | `references/novelty-check.md`, `references/adversarial-review.md` |
| CARE / case templates | `templates/case-report.md`, `templates/case-abstract.md`, `templates/case-introduction.md` |
| Humanizer patterns | `references/humanizer-academic.md` |
| Data rules (raw gitignored, no PHI in chat) | `templates/data-management.md`, `SECURITY.md` |
| Compile / word-count utilities | `scripts/compile-manuscript.sh`, `scripts/word-count.sh` |

```bash
# after install / clone
npx skills add kgraph57/paper-writer-skill
# then in Claude Code / your agent:
# "Start a CARE case report from these de-identified notes…"
```

## What this case study deliberately does *not* claim

- No journal acceptance, impact factor, or "N doctors use this."
- No real patient identifiers or real lab dumps.
- No promise that the skill replaces IRB review or auto-submits to journals.
writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 322kUpdated Claude CodeCodexVerifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 118kUpdated Claude CodeCodexVerifiedInstall