메뉴
Use this when a user asks to inspect, summarize, profile, sample, or infer schema for local CSV/TSV-like data using moonrun and the bundled portable datascout WASM artifact from this skill.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Use this when a user asks to convert local Word DOCX files to HTML or Markdown, apply Mammoth-style style maps, extract DOCX images beside converted HTML, or run the native MoonBit bobzhang/docx2html converter.
Use this when a user asks to inspect TOML-style config, inventory tables and keys, find duplicate keys or tables, extract dotted values, normalize simple TOML, or produce JSON config summaries using moonrun and the bundled portable tomlskill WASM artifact.
Use this when a user asks to inspect SVG files, inventory SVG structure, detect risky SVG features, or produce JSON SVG triage using moonrun and the bundled portable svgcheck WASM artifact.
Use this when a user asks to inspect Markdown structure, extract outlines, inventory links/tasks/code fences/front matter, or produce JSON document summaries using moonrun and the bundled portable mdskill WASM artifact.
Use this when a user asks to format, sanitize, inspect, outline, audit links, extract clean text, select nodes with CSS selectors, or convert local HTML to Markdown using moonrun and the bundled portable htmlfmt WASM artifact from this skill.
Use this when a user asks for a small portable ASCII cow text bubble, a playful CLI smoke test, or a minimal moonrun demo using the bundled portable cow WASM artifact from this skill.
| name | portable-datascout |
| description | Use this when a user asks to inspect, summarize, profile, sample, or infer schema for local CSV/TSV-like data using moonrun and the bundled portable datascout WASM artifact from this skill. |
Use this skill to turn a local delimited data file into a compact schema and sample report. It is useful before sending data to an agent because it exposes column names, inferred simple types, empty counts, max lengths, and a bounded sample without loading the full file into the conversation.
moonrun /path/to/portable-datascout/assets/datascout.wasm \
--file data.csv \
--sample 5
Write JSON for automation:
moonrun /path/to/portable-datascout/assets/datascout.wasm \
--json \
--file data.csv
For TSV or semicolon-delimited files:
moonrun /path/to/portable-datascout/assets/datascout.wasm \
--delimiter tab \
--file data.tsv
datascout before pasting or packing large data files.--sample N to keep examples small.--max-rows N to cap scan work for large files.--json when another tool should consume the schema.--no-header when the first row is data.--file PATH: read a guest-visible data file.--json: write compact JSON.--delimiter auto|comma|tab|semicolon|CHAR: select delimiter.--sample N: number of sample rows to include.--max-rows N: maximum rows to scan.--no-header: synthesize column_1, column_2, ...--output PATH: write report to a guest-visible path.This is a lightweight profiler, not a full dataframe engine. CSV quote handling is enough for common files, but it does not stream rows, validate encodings, or run SQL-like queries.