plain
Re-expresses a dense response in plain English while preserving its substance. Use for /plain, "say that in plain English", "de-jargon this", "unpack that", or "explain that like a normal person". Targets the previous assistant message unless the user supplies another passage. Picture mode, only when asked (/plain show, or "show me" about an answer), re-explains with the smallest plain-text picture - pseudocode, a call tree, a component or file tree, or a diff of a tree.
dtiger1889-ops · 已有静态检查记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add dtiger1889-ops/claude-harness-toolbox --skill plain技能说明
name: plain description: >- Re-expresses a dense response in plain English while preserving its substance. Use for /plain, "say that in plain English", "de-jargon this", "unpack that", or "explain that like a normal person". Targets the previous assistant message unless the user supplies another passage. Picture mode, only when asked (/plain show, or "show me" about an answer), re-explains with the smallest plain-text picture - pseudocode, a call tree, a component or file tree, or a diff of a tree.
Plain English
- Identify the target passage; ask only if the target is ambiguous.
- Look up unfamiliar project codes, tags, acronyms, and phase names in their source files. Do not guess. If a meaning is unavailable, say that explicitly.
- Re-express all the substantive content in ordinary sentences. Expand compressed clauses and define unavoidable technical terms at first use.
- Use short paragraphs or a clear list. Preserve qualifications, uncertainty, and actionable details; add no new analysis or next steps.
Example with fictional terminology:
- Dense: "The F027 gate blocks the B13 rung until the file hashes reconcile."
- Plain: "A check prevents the next build step until the two copies of the file match. They currently differ."
Use enough space to explain the meaning; brevity must not erase it.
Picture mode (only when asked)
Runs only on /plain show or when the user says "show me" about an answer; otherwise the output stays prose. Adapted from the show-me skill in humanlayer/skills (MIT).
- Resolve every code first (step 2 above). Labels inside a picture are words too; a tree node named
F027fails the same way a sentence does. - Pick the smallest picture that makes the point, usually one, rarely two:
- steps or logic: pseudocode in plain words, numbered or indented
- what runs what, in order: an indented call tree
- how parts or files are arranged and who owns what: a shallow component or file tree
- what changes: a
diffblock of the tree or list (-removed,+added) when the shape already exists; show the whole thing when most of it is new
- Put one or two plain sentences before each picture saying what it shows. Keep only the parts that answer the point.
- Use plain monospace text in a fenced block: ASCII only (
|--,`--, indentation), lines under about 60 characters so a phone terminal does not wrap them. - No Mermaid in a terminal or phone session, because it prints as raw text there. Do not write an HTML file or open a viewer. If plain text cannot carry the point (a screen layout, a dense comparison), say so and offer a rendered diagram instead.
- Everything above still holds: what the picture cannot hold goes in plain sentences under it, so no substance is lost and no new shorthand or analysis comes in.