Update to Tabularia

{
  "description": "Edit an article, essay, blog post or newsletter in Tabularia — its headline, opening, structure, length and ending — for the reader who will decide in a few seconds whether to keep reading. Use when the Writer asks to improve, tighten or review an article, blog post, essay, newsletter or column, or asks about its headline, opening, length or structure.",
  "included_files": [],
  "name": "article-edit",
  "skill_md_contents": "---\nname: article-edit\ndescription: Edit an article, essay, blog post or newsletter in Tabularia — its headline, opening, structure, length and ending — for the reader who will decide in a few seconds whether to keep reading. Use when the Writer asks to improve, tighten or review an article, blog post, essay, newsletter or column, or asks about its headline, opening, length or structure.\n---\n\n<what-this-is>\n\nAn article is read on a screen by someone who can leave at any line. Most of\nwhat makes one work is in the headline, the first two paragraphs and the\nshape, so that is where this job spends its attention. Sentence work is\n`line-edit`, and it applies here unchanged.\n\nFindings are comments; changes go in a Draft, as everywhere else.\n\n</what-this-is>\n\n<read-it-whole>\n\nArticles are short, so read the whole piece with `tabularia_read_scope`\n(`book`) or `tabularia_read_window`, and `tabularia_statistics` for its length.\nQuote that count, not your own.\n\n`tabularia_list_anchors` and `tabularia_list_comments` show whether it was\nstarted from an article shape — Inverted Pyramid, Feature, Argument or Review\n— and what each heading is for. Read against that shape if it is there; ask\nwhich the Writer intends if it is not.\n\nAsk where it will run and for how many words, if they have not said. A\nnewsletter, a magazine feature and a blog post have different lengths and\ndifferent readers.\n\n</read-it-whole>\n\n<what-to-check>\n\n- **The headline.** Does it say what the piece gives the reader? Clever is\n  fine when it is also clear. Offer two or three alternatives, never more.\n- **The opening.** By the end of the second paragraph the reader should know\n  what the piece is about and why to keep going. A slow warm-up — background,\n  definitions, \"in today's world\" — is the most common fault. Name the\n  paragraph where the piece actually starts.\n- **The shape.** For news, the most important thing first. For an argument,\n  the claim early, then the case, then the objection answered. For a feature,\n  a scene or person that carries the idea. Point to where the piece leaves its\n  shape.\n- **Headings.** On a long piece, do the headings alone tell the story? A\n  reader skims them before reading.\n- **Length.** Against the target they gave. Name the section that could go,\n  not a percentage.\n- **The ending.** It should land the point or send the reader somewhere —\n  not summarize what they just read.\n- **Links.** A read gives each Block's links. Check that each one says where\n  it goes, and flag any link text that reads \"here\" or \"this\".\n\n</what-to-check>\n\n<how-to-deliver>\n\nUp to five findings, each as a comment with `tabularia_add_comment` on its\nparagraph. Headline alternatives go in a comment on the title. If the Writer\nasks you to make the changes, put a restructured opening or ending in a Draft\nwith `tabularia_create_draft` and `tabularia_write_draft`; small fixes go\nthrough `tabularia_propose_edit` as `line-edit` describes.\n\n</how-to-deliver>\n\n<what-not-to-do>\n\n- Do not write for search engines over readers. If the Writer asks about\n  search, a clear headline and a first paragraph that says what the piece is\n  about are most of it.\n- Do not change the Writer's opinion or soften an argument they meant to make.\n- Do not invent facts, quotes or figures to strengthen a point.\n\n</what-not-to-do>\n"
}