Use when a tabular dataset (CSV, Excel, Parquet, Stata, SAS) needs a data dictionary. Profiles every variable (type, levels, range, missingness) into codebook.md and codebook.json and flags coded values of unknown meaning as [NEEDS DICTIONARY] instead of guessing.
The English summary is being prepared. Showing the original description.
Review the instructions the agent will receive before you install.
Turn a raw tabular dataset into a structured, citable data dictionary (codebook). This is the
generator side of the dictionary-first workflow: it produces the artifact that /define-variables
and dictionary-first QC later consume. Distributions, types, and missingness are observable and the
bundled script profiles them; the meaning of a coded value (fatty_liver_grade = 0) is not
observable from the data and lives only in the authoritative data dictionary. You generate code and
review output — you do not invent the meaning of coded values.
Run the bundled profiler rather than describing columns from memory:
python "${CLAUDE_SKILL_DIR}/scripts/generate_codebook.py" data.csv --out-dir .
Supports .csv/.tsv/.xlsx/.parquet/.dta/.sas7bdat. Flags: --max-levels N
(categorical cutoff, default 20), --json-only, --md-only. The script is
pandas-only, runs locally, and never sends data anywhere.
Run generate_codebook.py on the dataset. It writes codebook.json (machine-
readable) and codebook.md (review table), reporting per variable: role
(id / continuous / categorical / binary / date / text), dtype, missingness,
unique count, level frequencies or quantile summary, and a needs_dictionary flag.
Read ${CLAUDE_SKILL_DIR}/references/codebook_schema.md (the codebook.json schema, the
role-inference heuristics, the needs_dictionary rule) before interpreting the output. Present
codebook.md and walk the user through it. Gate: role inference is a heuristic, so the user
confirms the inferred roles (e.g., an integer-coded scale mis-read as continuous, or an id column).
Do not proceed to definition work until the user approves the role assignments.
For every variable flagged needs_dictionary: true, the level codes are
uninterpretable without the authoritative source. Gate: ask the user to
supply the meaning of each code from the real data dictionary (file/sheet/row),
or to confirm none exists. Fill label, units, and per-level meanings into the
codebook only from that source, citing file > sheet > row — never from inference. If the user
cannot supply it, leave the [NEEDS DICTIONARY] marker in place; do not erase it.
Example: in a cohort file, sex (levels 1/2) and fatty_liver_grade (0..4) are flagged because
their levels are bare codes; smoking_status (never/former/current) is not. Never write
sex: 1 = male because "that is the usual coding" — if the dictionary is unavailable, the flag stays.
The completed codebook.json becomes the input dictionary for /define-variables
(operationalization) and the citation source for dictionary-first QC. Gate:
confirm with the user that no needs_dictionary flags remain unresolved before
the codebook is treated as authoritative for downstream analysis.
Run /deidentify on the raw data before a codebook is shared externally. Cleaning or transforming
data is /clean-data.
C50.9, S001) are not recognised as
codes, so their column is not flagged needs_dictionary.--max-levels is classed continuous
and is not flagged. The Step 2 role review is where such columns are caught.text column holding number strings: any number value
(45, 88) is read as a measurement, so integer codes exported as strings
with more than --max-levels values are not flagged.codebook.json (schema in references) and codebook.md (review table with a
"Columns requiring dictionary lookup" section). Summarize the counts
(rows, columns, needs_dictionary_count) in chat; do not paste the full JSON.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Use when a medical AI paper should be found and cited by AI search engines and RAG tools. Optimizes the title, abstract, summary box (Key Points, Research in Context), keywords, preprint, GitHub README/CITATION.cff and Hugging Face card, returning a visible pass/fail checklist.
The English summary is being prepared. Showing the original description.
Use when a target journal has no profile yet. Reads the journal's author guidelines and writes a detailed /write-paper profile plus a compact /find-journal profile, public or user-local private, in the canonical format with quality gates.
The English summary is being prepared. Showing the original description.
Use when data needs statistical analysis. Runs reproducible Python/R code for Table 1, diagnostic accuracy, agreement, regression, survival, propensity score, survey-weighted and repeated-measures models, with publication tables. Sample size is /calc-sample-size; pooling studies is /meta-analysis.
The English summary is being prepared. Showing the original description.
Renamed to /model-selection in v6 (removed in v7).
The English summary is being prepared. Showing the original description.
Use when analyzing a researcher's publication record from PubMed. Fetches an author's papers, classifies study types and author position, charts the patterns and writes a strategy report, with an optional trajectory-archetype classification. Works from PubMed metadata only.
The English summary is being prepared. Showing the original description.
Use when one validated cohort analysis must be repeated across many exposure/outcome pairs. Generates one R/Python script per combination from a single methodology template, changing only the variables, and aggregates the results into a summary matrix.
The English summary is being prepared. Showing the original description.