Skip to main content
ClaudeWave
Skill146 estrellas del repoactualizado yesterday

add-journal

>

Instalar en Claude Code
Copiar
git clone --depth 1 https://github.com/Aperivue/medsci-skills /tmp/add-journal && cp -r /tmp/add-journal/skills/add-journal ~/.claude/skills/add-journal
Después abre una sesión nueva de Claude Code; el skill carga automáticamente.

SKILL.md

# Add Journal Skill

You are helping a medical researcher add a new journal to the MedSci Skills profile database.
You generate two reference profiles per journal -- a detailed write-paper profile (~100-150 lines)
and a compact find-journal profile (~30 lines) -- using the journal's author guidelines as
the primary data source.

## Communication Rules

- Communicate with the user in their preferred language.
- Journal names, profile content, and URLs are always in English.
- Medical terminology and field names are always in English.
- Section headings within profiles must exactly match the canonical format defined below.

## Key Directories

Profiles live in one of two tiers — public (shipped with the skill) or user-local private
(per-user, never pushed to git). Pick the correct target in Phase 0 before any extraction.

### Public (shipped, must meet verification bar)
- **Write-paper:** `${CLAUDE_SKILL_DIR}/../write-paper/references/journal_profiles/`
- **Find-journal:** `${CLAUDE_SKILL_DIR}/../find-journal/references/journal_profiles/`

### User-local private (per-user override, optional)
- **Write-paper:** `$HOME/.claude/private-journal-profiles/write-paper/`
- **Find-journal:** `$HOME/.claude/private-journal-profiles/find-journal/`

Promotion workflow (private → public) is documented in
`${CLAUDE_SKILL_DIR}/../find-journal/POLICY.md`.

---

## Phase 0: Input Collection

### Required
1. **Journal name** -- full official name (e.g., "Journal of Clinical Oncology")
2. **Target tier** -- `public` (shipped) or `private` (user-local only)

### Strongly Encouraged
3. **Author Guidelines URL** -- primary data source for metadata extraction

### Optional
4. **Field focus** -- e.g., cardiology, oncology, surgery, general medicine, medical education, methodology
5. **Tier estimate** -- Q1 / Q2 / Q3 (user's best guess)
6. **ISSN** -- if known

If the user provides only a journal name without a URL, ask for the Author Guidelines URL
before proceeding. The guidelines page is the single most important data source for accurate
profile generation.

### Public vs. Private target selection

If the user does not state the target tier, ASK explicitly before proceeding. Use these
defaults and criteria to guide the question:

- **Default to `private`** for any journal outside the user's stated area of deep
  expertise. Private profiles only live on the user's machine and do not need to clear
  the public verification bar line-by-line — but the journal's Author Guidelines page
  must still be the primary source (no inference from adjacent journals, no AI policy
  copy-paste from the publisher family).
- **`public` is appropriate only when all of the following hold:**
  1. The user intends to contribute the profile upstream for other researchers.
  2. The user has opened the journal's homepage and author guidelines page and can
     attest to each field against the live source, OR can paste the relevant sections.
  3. AI policy wording is transcribed from the journal/publisher's own policy page,
     not inferred from a sibling journal.
  4. The user has completed or will complete the promotion checklist in
     `../find-journal/POLICY.md` before commit.

If the target is `public` but the user cannot attest to (2) and (3), switch the target
to `private` and tell the user: promotion to public can happen later after the checklist
is cleared.

---

## Phase 1: Duplicate Check

Before any data extraction, check whether the journal already exists:

1. **Glob all four directories** (public + private across both skills):
   ```
   ${CLAUDE_SKILL_DIR}/../write-paper/references/journal_profiles/*.md
   ${CLAUDE_SKILL_DIR}/../find-journal/references/journal_profiles/*.md
   $HOME/.claude/private-journal-profiles/write-paper/*.md
   $HOME/.claude/private-journal-profiles/find-journal/*.md
   ```

2. **Filename match:** Normalize the journal name (spaces to underscores, remove special characters)
   and check for an exact filename match.

3. **Abbreviation match:** Grep existing profiles for the journal's common abbreviation
   (e.g., "JCO" for Journal of Clinical Oncology).

### If found:
- Report which directory/directories already have the profile, with file paths.
- If present in only one directory, offer to create the missing counterpart.
- If present in both, offer to update the existing profiles or abort.
- Do NOT proceed to Phase 2 without user direction.

### If not found:
- Confirm to user: "No existing profile found. Proceeding with data extraction."

---

## Phase 2: Data Extraction

### Path A: WebFetch Available

1. Attempt to fetch the Author Guidelines URL.
2. Parse the page for metadata fields listed in the extraction checklist below.
3. If the page is insufficient (login-gated, JavaScript-heavy, or sparse), fall back to Path B.

### Path B: User-Provided Content

1. Ask the user to paste the Author Guidelines content (or key sections).
2. Accept pasted content and extract metadata from it.

### Extraction Checklist

Extract the following. Mark any field that cannot be determined as `[TODO: verify at journal site]`.

**For write-paper profile:**

| Field | Example |
|-------|---------|
| Full name | Journal of Clinical Oncology |
| Abbreviation | J Clin Oncol |
| Publisher | Wolters Kluwer (ASCO) |
| ISSN (print/online) | 0732-183X / 1527-7755 |
| Frequency | 36 issues/year |
| Impact Factor (with year) | ~45.3 (JCR 2023) |
| OA model | Hybrid |
| Acceptance rate | ~10-15% |
| Peer review type | Single-blind, 2-3 reviewers |
| Manuscript types with limits | Table: type, word limit, abstract, references, figures |
| Abstract format | Structured/unstructured, headings, word limit |
| Required sections | For Original Article |
| Statistical requirements | p-value format, CI, effect sizes |
| Figure specs | DPI, format, color, max count |
| Cover letter requirements | What to include |

**For find-journal profile:**

| Field | Example |
|-------|---------|
| Scope paragraph | 1-2 sentence scope description
skillsSkill
academic-aioSkill

Medical AI paper optimization for AI search engines (Perplexity, ChatGPT web, Elicit, Consensus, SciSpace) and RAG-based literature tools. Applies when drafting or reviewing titles, abstracts, structured summary boxes (Key Points / Research in Context / Plain-Language Summary), manuscripts for high-impact medical AI journals (Lancet Digital Health, Radiology, Radiology-AI, npj Digital Medicine, Nature Medicine), preprints (medRxiv/arXiv), GitHub README + CITATION.cff + Zenodo archives, and Hugging Face model/dataset cards. Integrates TRIPOD+AI, CLAIM 2024, STARD-AI, TRIPOD-LLM, DECIDE-AI reporting requirements with generative engine optimization (GEO) principles. Produces a visible pass/fail checklist.

analyze-statsSkill

Statistical analysis for medical research papers. Generates reproducible Python/R code with publication-ready tables and figures. Supports diagnostic accuracy, inter-rater agreement, meta-analysis, survival analysis, survey data, group comparisons, regression, propensity score, and repeated measures.

author-strategySkill

PubMed author profile analysis. Author name → PubMed fetch → study type classification → visualization → strategy report.

batch-cohortSkill

Generate N analysis scripts from a single methodology template × multiple exposure/outcome combinations. The "80-person team" pattern — same validated method, swap variables only. Produces batch R/Python code + summary matrix.

calc-sample-sizeSkill

>

check-reportingSkill

Check manuscript compliance with medical research reporting guidelines. Supports 32 guidelines including STROBE, CONSORT, STARD, STARD-AI, TRIPOD, TRIPOD+AI, ARRIVE, PRISMA, PRISMA-DTA, PRISMA-P, CARE, SPIRIT, CLAIM, MI-CLEAR-LLM, SQUIRE 2.0, CLEAR, MOOSE, GRRAS, SWiM, AMSTAR 2, and risk of bias tools (QUADAS-2, QUADAS-C, RoB 2, ROBINS-I, ROBINS-E, ROBIS, ROB-ME, PROBAST, PROBAST+AI, NOS, COSMIN, RoB NMA). Generates item-by-item assessment with PRESENT/MISSING/PARTIAL status.

clean-dataSkill

Interactive data profiling and cleaning assistant for medical research. Three-stage workflow (profile, flag, code-generate) with user approval gates at each step. Handles missing values, outliers, duplicates, and type mismatches in CSV/Excel clinical data. Does NOT auto-clean — all decisions require researcher confirmation.