Ase Meta Quotes

@${CLAUDE_SKILL_DIR}/../../meta/ase-control.md @${CLAUDE_SKILL_DIR}/../../meta/ase-skill.md @${CLAUDE_SKILL_DIR}/../../meta/ase-getopt.md

$ARGUMENTS

1. 2. Set (set to empty).

   3. Determine the maximum total number of quotes to surface: set to ; if is non-numeric or less than or equal to 0, use the default 8 instead.

2. 1. Determine quotes -- sayings, aphorisms, maxims, proverbs, and citations -- which are about the topic , and store them in . Per quote, record its text, its author (a named person or organization, if any is known), its origin (a named work, standard, or document, if any is known), and as its source topic.

   2. Additionally -- and never instead -- gather quotes from the Internet/Web by using the ase-meta-search skill in a sub-agent with the following tool call:

      Agent( description: "Query Web Search Service", subagent_type: "ase:ase-meta-search", prompt: "Search the Internet/Web and gather quotes about the following topic: <keywords/>", run_in_background: false )

      Merge the returned quotes into , deduplicating quotes which differ only in punctuation, capitalization, or attribution wording, and remember for every quote whether the search confirmed its exact wording and attribution.

3. 1. Set .

   3. Determine the conceptual neighborhood of by using the ase-meta-proximity agent in a sub-agent with the following tool call:

      Agent( description: "Determine Conceptual Proximity", subagent_type: "ase:ase-meta-proximity", prompt: "<prompt/>", run_in_background: false )

   5. Parse the returned labeled list and set to the values of its PARENT: line (the broader topic), of its four SIBLING: lines (the same-level topics), and of its four CHILD: lines (the narrower topics).

   6. Harvest quotes for each topic of exactly as in STEP 2 (Harvest Quotes), record the contributing neighborhood topic as the source topic of each of those quotes, and merge the results into .

4. 1. Classify Quotes:

      Classify every quote of along two orthogonal axes:

      • ATTRIBUTION: A quote is ATTRIBUTED if a named author and/or a named origin is known for it, and ANONYMOUS otherwise.

      • LITERALNESS: A quote is LITERAL if its text contains at least one of the topic keywords of as a whole word -- matched case-insensitively and tolerating inflections (e.g. architect and architectural match the keyword architecture), but never as a mere substring (e.g. art does not match architecture). A quote is THEMATIC otherwise.

      Both axes span the four quadrants:

      • Q1 (ATTRIBUTED and LITERAL)
      • Q2 (ATTRIBUTED and THEMATIC)
      • Q3 (ANONYMOUS and LITERAL)
      • Q4 (ANONYMOUS and THEMATIC)

   2. Finally, reduce to at most quotes in total, distributed as evenly as possible across the four quadrants and preferring the most relevant and most well-known quote per quadrant.

   3. Render Quotes:

      Render every quote on its own ○-prefixed line, with the following suffixes appended in this order:

      • — *<author/>*, <origin/> in the two ATTRIBUTED quadrants, omitting whichever of and is unknown.

      • [from proximity:] if the quote was harvested for a neighborhood topic in STEP 3 rather than for itself.

      • *(unverified)* if the exact wording or the attribution of the quote could not be established with confidence -- but omit this marker for a quote whose wording and attribution the Internet/Web search of STEP 2.2 confirmed -- including its re-application for a neighborhood topic in STEP 3.

      Render the single line ○ (none) for a quadrant without any quote. Output the result with the following :

      ● Q1 - ATTRIBUTED / LITERAL: ○ [...]

      ● Q2 - ATTRIBUTED / THEMATIC: ○ [...]

      ● Q3 - ANONYMOUS / LITERAL: ○ [...]

      ● Q4 - ANONYMOUS / THEMATIC: ○ [...]