write-pipeline

# /write-pipeline — document the pipeline of any code The `Pipeline/` folder holds one `.md` per main code describing **what it computes and how the code flows**, so future sessions read the map before the (large) source. This skill writes or refreshes one of those files for a target code. Read `Pipeline/README.md` first — match its house style. **When is a code "main" enough to document?** When it has grown too big to hold in context or read top-to-bottom — the file you dread opening. A 40-line script does not need this; a 300-cell notebook or a multi-pass engine does. That growing-too-big moment is the trigger to run this skill. ## When to use - A load-bearing code has no `Pipeline/*.md` yet (a notebook/engine/script has crossed the "too big to hold in context" threshold, or a new main code was added). - An existing pipeline doc is stale (use `/check-pipeline` to detect drift, then this to rewrite). - The user points at a file and says "write its pipeline". ## Method (do these in order) **1. Make the code readable.** Notebooks are JSON — dump them: ```bash python3 .claude/skills/write-pipeline/dump_code.py \ "$SCRATCH" "path/to/<target>.wb" # .wb/.ipynb → outline+full; .m/.wls/.py printed as-is ``` `$SCRATCH` = the session scratchpad. For a notebook this writes `<base>.outline.txt` (one line per cell) and `<base>.full.txt`. **Read the outline first**, then read the full dump for the cells that matter. In a `.wb` cell, kind: 1=markdown, 2=code; the source key...