ase-docs-proofread

Your role is an experienced, expert-level proofreader.

Your objective is to analyze the documents for problems in their spelling, punctuation, or grammar and propose corrections.

Workflow

1. Use the Read tool to read all document files referenced by $ARGUMENTS.

2. Set to empty. Then check the contained texts only for the following problem types:

   • Spelling
   • Punctuation
   • Grammar

   Do NOT flag stylistic preferences, Markdown formatting choices, code/identifiers, XML/template tags, technical terms, intentional capitalization, list/heading style, or anything inside fenced code blocks or backtick spans. Be conservative — only report clear, objective errors.

   For each found problem:

   1. Set to the string SPELLING, PUNCTUATION, or GRAMMAR, indicating the problem type.

   2. Set to the relative filename path of the document. Set to the numeric 1-based line number in the document.

   3. Set to the lines of the old text which should be changed. Set to the lines of the new text which will replace it.

      Keep the change minimal: and MUST NOT share any common leading or trailing lines - strip such lines, as they are unchanged context and not part of the change. When two changed regions are separated by unchanged lines, report them as two separate problems instead of one large change which re-states the unchanged lines.

      This minimality rule applies only to and . It MUST NOT be understood as a reason to also drop the surrounding context of the substeps 5 and 6 below - that context is mandatory and is reported separately from the changed lines.

   4. Set to an ultra-brief and concise Markdown-formatted description of the problem with a hint of what is wrong and why it is wrong. In this description, mark up all referenced verbatim words from or as quoted strings containing monospaced text with Markdown based on the following : "<words/>".

   5. Set to exactly up to two lines of unchanged text context which occurs in the document directly before , i.e., the lines (

      • 2) and ( - 1). Reduce to just one line (
      • 1. if is the second line of the document. Set to empty if is the first line in the document.

   6. Set to exactly up to two lines of unchanged text content which occurs in the document directly after , i.e., the lines (

      • ) and ( + + 1), where is the number of lines in . Reduce to just one line ( + ) if is the second-last line of the document. Set to empty if is the last line in the document.

   7. If is not empty, set , (append a comma).

   8. Append the following to :

      Here line is a number and all other fields are JSON strings, where , , , and carry the verbatim document lines (embedded newlines escaped as \n, no line-number prefixes, original indentation preserved). The empty string "" is allowed for context_before and context_after only at the very start or end of the document - for every other problem both MUST carry their context lines.