An AI skill that turns books into animated, narrated, interactive web experiences
JavaScript ai-agentsai-educationanimationclaudeclaude-codeclaude-skillsedtecheducationinteractive-textbookscormtext-to-video
docs(skill): default models are the splits that made approved books
yzre9ad367b21d4
diff --git a/.claude/skills/papermorph/assets/templates/documentary/style.json b/.claude/skills/papermorph/assets/templates/documentary/style.jsonindex 40473be..6ef0703 100644--- a/.claude/skills/papermorph/assets/templates/documentary/style.json+++ b/.claude/skills/papermorph/assets/templates/documentary/style.json@@ -16,6 +16,6 @@"music": "public-domain classical recordings, one per part of the film, changing at the turns","pacing": { "minutes": 10, "turns": "one argument with five or six turns; one idea or picture every two to four seconds" },"engine": { "source": "DozenTwelve/Papermorph", "ref": "engine-v2.7" },- "models": { "script": "claude-opus-5-5", "pictures": "claude-sonnet-5-5", "beats": "claude-sonnet-5-5", "checks": "claude-haiku-5-5", "director": "claude-opus-5-5" },+ "models": { "script": "claude-opus-5-5", "pictures": "claude-opus-5-5", "beats": "claude-opus-5-5", "checks": "claude-opus-5-5", "director": "claude-opus-5-5" },"approved": [{ "chapter": "ch01", "why": "close-ups on what is named; few words on screen" }]}diff --git a/.claude/skills/papermorph/assets/templates/shorts/style.json b/.claude/skills/papermorph/assets/templates/shorts/style.jsonindex 317fba2..d7d73d1 100644--- a/.claude/skills/papermorph/assets/templates/shorts/style.json+++ b/.claude/skills/papermorph/assets/templates/shorts/style.json@@ -24,6 +24,6 @@"music": { "ch01": "one track under the whole episode, and where it came from" },"sources": "which numbers and quotes need a source on screen, and how strict to be about anonymous reports","engine": { "source": "DozenTwelve/Papermorph", "ref": "engine-v2.7" },- "models": { "script": "claude-opus-5-5", "pictures": "claude-sonnet-5-5", "beats": "claude-sonnet-5-5", "checks": "claude-haiku-5-5", "director": "claude-opus-5-5" },+ "models": { "script": "claude-opus-5-5", "pictures": "claude-opus-5-5", "beats": "claude-opus-5-5", "checks": "claude-opus-5-5", "director": "claude-opus-5-5" },"approved": [{ "chapter": "ch01", "why": "what the user liked: the hook's first frame, the pace, the ending" }]}diff --git a/.claude/skills/papermorph/references/core/style.md b/.claude/skills/papermorph/references/core/style.mdindex bb845f2..79d8d0c 100644--- a/.claude/skills/papermorph/references/core/style.md+++ b/.claude/skills/papermorph/references/core/style.md@@ -14,15 +14,20 @@ Left to guess what the user wants, an agent's guesses diverge from run to run. SWhich model does which step is the user's choice; users run the Skill with different models and providers, and a book can mix them. Show the tier's defaults as one table, one row per step of its team ([core/team.md](team.md)), and ask: keep it (recommended), or change some rows. Any model the user names is fine.-| Step | Lesson, tier 1 | Lesson, tier 2 | Picture book | Documentary | Short |-|---|---|---|---|---|---|-| Extract the chapter (or the story) | small | small | strong (script and storyboard with the user) | strong (research, script and storyboard with the user; then voice and music) | strong (script and storyboard with the user; then voice and music) |-| Narration and beats | middle | middle | strong (voices, the episode kit) | middle (pictures found and treated) | middle (pictures generated or found) |-| Picture: storyboard, motion, questions | middle | strong | middle, one worker per scene | middle, one worker per part of the film | middle (the beats) |-| Checks | small | small | small (sound effects too) | small | small |-| Review | middle | middle | strong director, middle picture and sound reviewers | strong director | strong director |-| Rework | strong | strong | middle, per scene | middle, per part | middle |-| Register | small | small | small | small | small |+The defaults are the splits that made approved books; a cheaper split is the user's to try.++| Step | Lesson (tier 1 and 2) | Picture book | Documentary | Short |+|---|---|---|---|---|+| Extract the chapter (or the story) | small | strong (script and storyboard with the user) | strong: one agent researches, writes the script and storyboard with the user, voices, finds the music and pictures | strong: one worker per episode writes the script with the user (or the coordinator), voices, makes or finds the pictures |+| Narration and beats | middle | strong (voices, the episode kit) | strong (the same agent) | strong (the same worker) |+| Picture: storyboard, motion, questions | strong | middle, one worker per scene | strong (the same agent) | strong (the same worker) |+| Checks | small | small (sound effects too) | strong (the builder runs its own) | strong (the worker runs its own) |+| Review | middle | strong director, middle picture and sound reviewers | strong director, fresh: contact sheets, then the exported MP4 | strong director per episode, fresh, on the exported MP4 |+| Rework | strong | middle, per scene | strong (the builder) | strong (the episode's worker) |+| Register | small | small | strong (the coordinator) | strong (the coordinator) |+| Made this way | physics ch14, at about half the cost of one strong agent | *Joke Collection* episodes 5–6 | *Madness and Civilization*, *The Pandemic* | *Madness and Civilization* shorts 2–4, *The Pandemic* shorts 1–6 |++A middle model on a lesson's picture step made two maths chapters that were acceptable but monotonous: a cheaper choice for tier 1 when the user wants it. No cheaper split of a film has been tried.**small**, **middle** and **strong** stand for the user's current fast, balanced and most capable models; write the actual names into `models`, keyed by step as in the [lesson](../../assets/templates/style.json) or [picture-book](../../assets/templates/picture-book/style.json) template (a picture book's keys name its roles: `script`, `kit`, `scenes`, `sound`, `director`, `reviewers`; a [documentary](../../assets/templates/documentary/style.json)'s and a [short](../../assets/templates/shorts/style.json)'s: `script`, `pictures`, `beats`, `checks`, `director`). Without subagents one agent does every step on its own model, and the table only records that. The user can change a row at any time; later chapters follow the table as it stands.diff --git a/.claude/skills/papermorph/references/films/films.md b/.claude/skills/papermorph/references/films/films.mdindex 61998fe..21daeba 100644--- a/.claude/skills/papermorph/references/films/films.md+++ b/.claude/skills/papermorph/references/films/films.md@@ -74,8 +74,8 @@ The mechanics are in [core/sound.md](../core/sound.md). For films:The general shape is in [core/team.md](../core/team.md); the director passes are as in [core/review.md](../core/review.md#review-rounds).-- **Documentary**: split by part of the film (a turn of the argument, often one music track). The **strong** coordinator researches and writes the script and storyboard with the user, then builds what every part shares: the voice and `timings.js`, the music, the film's recurring pieces. A **middle** worker finds and treats the pictures from the storyboard (`commons.py`, `prep.py`, and `trace.py` or `frames.py` where asked), recording each source. One **middle** worker per part builds its beats, given the storyboard rows, the marks to land on, the kit's API (to read, not edit), the first and last frame of the neighbouring parts, and how to look at its own frames; it replies with contact sheets of its beats and what they showed.-- **Short**: the **strong** coordinator writes the script and shot-by-shot storyboard with the user and builds what the beats share: the voice and `timings.js` at one level, the music, the series' own pieces. A **middle** worker makes or finds the pictures and records each prompt or source and its cost. One **middle** worker builds the beats (two, split at a turn, when the episode is long), given the script, the marks, the kit's API to read and not edit, the safe area, and how to look at its frames: `strip.py` sheets of every beat and the first frame upright with `shot.py --clean`.+- **Documentary**: one **strong** agent makes the whole film with the user (research, script and storyboard, voice and `timings.js`, music, pictures, the film's recurring pieces, the beats, its own checks), and a fresh **strong** director reviews it ([below](#review-rounds)); *Madness and Civilization* and *The Pandemic* were made this way. A long film can be split by part (a turn of the argument, often one music track), each part's builder given the storyboard rows, the marks to land on, the kit's API (to read, not edit) and the first and last frame of the neighbouring parts; that split has not been tried yet.+- **Short**: one **strong** worker per episode, in its own worktree when several run at once ([core/team.md](../core/team.md#workers-in-parallel)), writes the script beat by beat with the user (or the coordinator standing in), voices it, makes or finds the pictures, recording each prompt or source and its cost, builds the beats and runs its own checks: `strip.py` sheets of every beat and the first frame upright with `shot.py --clean`. A fresh **strong** director per episode reviews the exported MP4, and the same worker fixes. A series recut from a long film first gets one worker for what every episode shares (the series card, a globe or map, the voice settings). The *Madness and Civilization* and *The Pandemic* shorts were made this way.## Review rounds