readabilitylisted

# Readability Check substantial English prose with the pure-JavaScript analyzer next to this skill. It makes no network requests and has no runtime dependencies. This skill works in any agent that supports Agent Skills and can run Node.js 18 or newer. Do not run it on code, command output, log dumps, non-English text, or short replies. The scores are not meaningful for those inputs. ## Run the analyzer Find the directory containing this `SKILL.md`, then run its adjacent `scripts/check.js` with Node.js. Use the actual absolute path to that script; the current working directory and agent-specific environment variables are not reliable ways to locate it. The script reads stdin, prints JSON, and exits 1 when the Reading Ease score misses `--threshold`: ```bash node "/absolute/path/to/readability/scripts/check.js" --threshold 60 < draft.md ``` To score prose already in the conversation, pass it on stdin. For long drafts, write the draft to a file first. Do not put prose in a shell-quoted `--text` argument. The path above is an example; replace it with the installed skill's actual path. ## Output ```json { "word_count": 174, "sentence_count": 12, "paragraph_count": 4, "avg_sentence_length": 14.5, "avg_word_length": 4.8, "ttr": 0.61, "mtld": 74.2, "flesch_reading_ease": 64.3, "complexity_label": "Moderate" } ``` - `flesch_reading_ease`: 0-100; higher is easier. 70+ is simple, 50-69 moderate, and below 50 complex. - `mtld`: lexical diversity; `null` for f