Goal

• Given one or more links <LINKS>, find the file(s) among the following that are related to each link, and add a TODO to the most related file:
  • research/ideas/*.md
  • website/docs/blog/posts/*.md

  // TODO(gp): incorporate the link <LINK> to <TOPIC>
  

Workflow

Collect Material

• Read the title and content of each link in <LINKS> (use WebFetch if the URL alone is not descriptive enough to judge the topic)
• List all candidate files in the two dirs above

Match Links to Files

• For each link, compare its topic with each candidate's title, headers, and first paragraph. Rank candidates by relevance
• Pick the single best match for each link
  • If several files are close, list them and ask the user which to use
  • If no file plausibly matches, do not force a match. Report it instead

Add the TODO

• In the matched file, add one line:

  // TODO(gp): incorporate the link <LINK> to <TOPIC>
  

  where <TOPIC> is a short description (under 15 words) of the relevant part of the link, e.g., a technique, a result, or a quote
• Placement:
  • If the file has a top-of-file // TODO(gp): ... block, add the new line as an adjacent line in that block
  • Otherwise, put it near the most related section, e.g., right above the relevant bullet point or paragraph
• Change no other content in the file
• If several links map to one file, add one TODO line per link

Report

• For each link, print the file it was added to and the exact TODO line inserted
• Report any unmatched link explicitly. Do not skip it silently

Verification

• Each link matches at most one file, with no forced or guessed match
• Each inserted line follows the exact // TODO(gp): incorporate the link <LINK> to <TOPIC> format
• No content other than the new TODO line(s) changed in the matched file
• The report lists every link with its target file or "not matched" status