{"id":67786,"plugin_id":"plugin_asdk_app_6aca99f4ddf481919cb0214e89117cb7","kind":"skill","collection_source":"plugin_package","comparison_source":null,"observed_at":"2026-10-28T13:11:02.374Z","digest":"f8082ee5903b44a93df0e5b2ec90d00d984111c0a0d4cd95411c028a9436dd80","against":null,"payload":{"description":"Read a Tabularia Manuscript against the shape it was built on — the story structure's own part notes — and report where the writing does not yet do what each part is for. Use when the Writer asks about structure, pacing, act breaks, a middle that drags, an opening that does not hook, an ending that does not land, whether a beat lands, or asks for a developmental read.","included_files":[],"name":"structural-read","skill_md_contents":"---\nname: structural-read\ndescription: Read a Tabularia Manuscript against the shape it was built on — the story structure's own part notes — and report where the writing does not yet do what each part is for. Use when the Writer asks about structure, pacing, act breaks, a middle that drags, an opening that does not hook, an ending that does not land, whether a beat lands, or asks for a developmental read.\n---\n\n<what-this-is>\n\nA developmental read, not a line edit. You are answering one question: **does\neach part of this Manuscript do the job its shape says it should?**\n\nYou never rewrite prose here. Everything you find becomes an anchored comment\nthe Writer reads in Studio and acts on themselves.\n\nA novel's job. For a nonfiction book or proposal use `nonfiction-read`, for\nan article or blog post `article-edit`, and for a script `screenplay-read`.\n\n</what-this-is>\n\n<the-shape-is-already-in-the-project>\n\nThis is the part people miss. When a Writer starts a Project from a story\nstructure, Tabularia writes each part's **note** onto that part's Outline Anchor\nas a comment — what that act or beat is meant to do in the progression. It is an\nordinary Anchor comment afterwards, so the Writer may have edited it, replaced\nit, or deleted it.\n\nSo do not bring a remembered version of the Fifteen-Beat Sheet or the Hero's Journey to\nthis. Read what the Project actually says:\n\n1. `tabularia_project_metadata` — how many Books, Acts and Chapters there are,\n   what they are called, and the id that names each Chapter to the Outline\n   tools.\n2. `tabularia_list_anchors` — the Outline: which Anchors are acts, chapters,\n   scenes, and where each sits. A page at a time on a novel: read `anchorCount`\n   and `hasMore`, and ask again with a later `from` rather than assuming the\n   first page is the Outline.\n3. `tabularia_list_comments` — the part notes. These are the standard you are\n   reading against.\n\nIf there are no part notes, the Project was not started from a structure, or the\nWriter removed them. Say so, ask which shape they have in mind, and read against\nthat instead of guessing. The catalogue includes `three-act`, `heros-journey`,\n`story-circle`, `seven-point`, `fifteen-beat` and `romance-beats`, among others.\n\n</the-shape-is-already-in-the-project>\n\n<how-to-read>\n\nWork one structural unit at a time, not the whole book at once.\n\n- `tabularia_list_scopes` tells you what levels this Manuscript has.\n- `tabularia_read_scope` with `act`, `chapter` or `scene` reads one unit around\n  where the Writer is reading. **It does not change what they are looking at.**\n- For a unit that is not the current one, read the Block range the Outline Anchor\n  gives you with `tabularia_read_window`.\n\nCheck `tabularia_list_drafts` first. What you read is the Base Draft plus\nwhichever Scoped Drafts are showing, and a structural judgement about a chapter\nthe Writer has a Draft standing over is a judgement about the Draft.\n\n</how-to-read>\n\n<what-editors-find-most>\n\nThe shape tells you what each part is for. These are what developmental editors\nreport most often whatever the shape, and they are worth checking even when\nthe Project has no part notes at all:\n\n- **An opening that does not start the story.** Backstory, a waking-up, a\n  landscape or a stranger's point of view before the protagonist wants\n  anything. Agents decide in the first pages, so name the Block where the story\n  actually begins and what comes before it.\n- **A goal that fades.** The protagonist wants something clearly in Act One and\n  then drifts from scene to scene. Tension drains out of a book at the point\n  the reader stops being able to say what the character is after, and that is\n  usually what a Writer means when they say the middle drags. Say where the\n  goal was last restated or pressed on.\n- **Stakes that do not rise.** Middle chapters where each obstacle costs no\n  more than the one before. Find the last scene where something got worse.\n- **Exposition delivered in a block.** Several paragraphs of history or\n  world-building with nothing happening. Name it by its Block range; whether it\n  belongs is the Writer's call, where it sits is yours to point out.\n- **Setups without payoffs, and payoffs without setups.** A skill, an object or\n  a secret the ending leans on that was never planted, or one planted with\n  weight and never used. Search for it with `tabularia_search` to confirm both\n  ends before you say either is missing.\n- **An ending that does not answer the opening.** The climax resolves the plot\n  but not the question the first chapter asked of the protagonist.\n\nThese are findings like any other: a verdict, the Blocks it rests on, one\ncomment each. Do not run them as a checklist and report every item.\n\n</what-editors-find-most>\n\n<what-to-report>\n\nFor each part, one of three verdicts, and say which:\n\n- **Does its job.** Name the paragraph that carries it. Say it in one line and\n  move on; a Writer does not need paragraphs of praise.\n- **Does its job late or weakly.** Say where it currently lands, where the shape\n  expects it, and what the gap costs the reader.\n- **Is not there.** Say what is standing in its place instead.\n\nGround every verdict in the text. \"The midpoint is weak\" is useless. \"The\nmidpoint note asks for a reversal that closes the hero's retreat; chapter 14 has\nthe reversal but leaves the retreat open until chapter 19, so the middle reads as\noptional\" is a note someone can act on.\n\nThen leave them with `tabularia_add_comment`, anchored to the paragraph each one\nis about — not a wall of text in the chat that vanishes when the window closes.\nOne comment per finding. Title it with the part name.\n\n</what-to-report>\n\n<what-not-to-do>\n\n- **Do not propose edits.** A developmental note is not a redline. If the Writer\n  asks you to fix something you found, that is a different job — read it again\n  and use `tabularia_propose_edit` for a targeted change, or\n  `tabularia_create_draft` when the fix is a rewrite of the passage.\n- **Take a Snapshot only if you are about to change durable state**, with\n  `tabularia_take_snapshot`. A developmental read changes nothing, so it needs\n  none, and asking for one anyway leaves a row in the Writer's History that\n  answers no question.\n- **Do not restructure the Outline because you found a problem in it.**\n  `tabularia_create_outline_item`, `tabularia_rename_outline_item` and\n  `tabularia_move_outline_item` exist, and a developmental read is not the\n  moment for them: where an act break belongs is the Writer's decision, and\n  your job here was to say what the shape is doing. Offer; do not act. If they\n  ask, make the change they named and read `tabularia_project_metadata` back\n  afterwards to confirm where it landed. From the cloud a Snapshot is kept\n  first; with Tabularia open on their computer, take one with\n  `tabularia_take_snapshot` first. Gathering Chapters into a new Act cannot be\n  done from the cloud, so name that one for the Writer to make in the\n  Outline.\n- **Do not judge a shape the Writer did not choose.** A literary novel that\n  ignores beat placement is not broken. If the structure notes are absent and\n  they do not name one, describe the shape the book actually has and let them\n  decide whether it is the one they want.\n- **Do not comment on every paragraph.** A developmental read that leaves forty\n  comments is noise. Ten findings is a lot. Three good ones is a useful morning.\n\n</what-not-to-do>\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}