An AI skill that turns books into animated, narrated, interactive web experiences
JavaScript ai-agentsai-educationanimationclaudeclaude-codeclaude-skillsedtecheducationinteractive-textbookscormtext-to-video
fix(skill): keep model facts in one place and use launcher names
DozenTwelve9b2f7dec5f3a
diff --git a/.claude/skills/papermorph/assets/templates/documentary/style.json b/.claude/skills/papermorph/assets/templates/documentary/style.jsonindex 6ef0703..dcdb7a6 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-opus-5-5", "beats": "claude-opus-5-5", "checks": "claude-opus-5-5", "director": "claude-opus-5-5" },+ "models": { "script": "opus", "pictures": "opus", "beats": "opus", "checks": "opus", "director": "opus" },"approved": [{ "chapter": "ch01", "why": "close-ups on what is named; few words on screen" }]}diff --git a/.claude/skills/papermorph/assets/templates/picture-book/style.json b/.claude/skills/papermorph/assets/templates/picture-book/style.jsonindex 464ee57..8fe4e1b 100644--- a/.claude/skills/papermorph/assets/templates/picture-book/style.json+++ b/.claude/skills/papermorph/assets/templates/picture-book/style.json@@ -18,6 +18,6 @@"cast": [{ "name": "Bo", "look": "round face, school uniform", "file": "site/jokes/lib/cast.js" }]},"engine": { "source": "DozenTwelve/Papermorph", "ref": "engine-v2.7" },- "models": { "script": "claude-opus-5-5", "kit": "claude-opus-5-5", "scenes": "claude-sonnet-5-5", "sound": "claude-haiku-5-5", "director": "claude-opus-5-5", "reviewers": "claude-sonnet-5-5" },+ "models": { "script": "opus", "kit": "opus", "scenes": "sonnet", "sound": "haiku", "director": "opus", "reviewers": "sonnet" },"approved": [{ "chapter": "ch01", "why": "set-up before the punchline; a close-up on whoever speaks" }]}diff --git a/.claude/skills/papermorph/assets/templates/shorts/style.json b/.claude/skills/papermorph/assets/templates/shorts/style.jsonindex d7d73d1..4eb1862 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-opus-5-5", "beats": "claude-opus-5-5", "checks": "claude-opus-5-5", "director": "claude-opus-5-5" },+ "models": { "script": "opus", "pictures": "opus", "beats": "opus", "checks": "opus", "director": "opus" },"approved": [{ "chapter": "ch01", "why": "what the user liked: the hook's first frame, the pace, the ending" }]}diff --git a/.claude/skills/papermorph/assets/templates/style.json b/.claude/skills/papermorph/assets/templates/style.jsonindex 30b1961..e1e1e92 100644--- a/.claude/skills/papermorph/assets/templates/style.json+++ b/.claude/skills/papermorph/assets/templates/style.json@@ -15,7 +15,7 @@"voice": { "engine": "edge", "voice": "en-US-AndrewNeural", "rate": "-4%" },"pacing": { "minutes": [6, 10], "checks": "one or two quick checks inside the lesson, practice at the end" },"engine": { "source": "DozenTwelve/Papermorph", "ref": "engine-v2.7" },- "models": { "extract": "claude-haiku-5-5", "narration": "claude-sonnet-5-5", "picture": "claude-opus-5-5", "checks": "claude-haiku-5-5", "review": "claude-sonnet-5-5", "rework": "claude-opus-5-5", "register": "claude-haiku-5-5" },+ "models": { "extract": "haiku", "narration": "sonnet", "picture": "opus", "checks": "haiku", "review": "sonnet", "rework": "opus", "register": "haiku" },"scenes": {"art": "pixel scenes on a dark board, characters about a third of the stage tall","cast": [{ "name": "Mia", "look": "short hair, red jacket", "file": "site/physics/img/mia.png" }],diff --git a/.claude/skills/papermorph/references/core/style.md b/.claude/skills/papermorph/references/core/style.mdindex 615a50a..e352137 100644--- a/.claude/skills/papermorph/references/core/style.md+++ b/.claude/skills/papermorph/references/core/style.md@@ -12,14 +12,14 @@ Left to guess what the user wants, an agent's guesses diverge from run to run. S## Models-Which model does which step is the user's choice, among the models the host running the Skill can start; a user who wants another provider's models makes the book in that provider's host. How much animation the book has is already settled by the tier the user chose at intake; the models come after it, as one question the user answers with a click:+Which model does which step is the user's choice, among the models the host running the Skill can start; a user who wants another provider's models makes the book in that provider's host. The models come after the tier the user chose at intake, as one question the user answers with a click:- **Recommended**: the tier's column of the table below, the splits that made approved books.- **Strongest everywhere**: every step on the strong model.-- **Cheaper**: for a lesson, the picture step on the middle model and the rest as recommended, tried on tier 1 only (below). For a picture book, the script on strong, sound on small and every other role on middle. For a film, the builder (a documentary's one agent, a short's worker per episode) on middle, and the fresh director still strong. The tier-2, picture-book and film splits have not been tried yet; say so in the option.-- **Custom**: only then show the table, one row per step of the tier's team ([core/team.md](team.md)), each row offering the host's models to pick; at four questions a round, a lesson's seven rows take two rounds.+- **Cheaper**: for a lesson, the picture step on the middle model and the rest as recommended; on tier 1 this made two maths chapters that were acceptable but monotonous, and tier 2's picture step wants a strong model ([lessons/intake.md](../lessons/intake.md#3-tier)), so offer it there with that warning. For a picture book, the script on strong, sound on small and every other role on middle. For a film, the builder (a documentary's one agent, a short's worker per episode) on middle, and the fresh director still strong. The tier-2, picture-book and film splits have not been tried yet; say so in the option.+- **Custom**: only then ask one question per `models` key of the tier's template (seven for a lesson, six for a picture book, five for a film; the steps of its team, [core/team.md](team.md)), each offering the host's models, in rounds as [Asking](#asking) allows.-A film's recommended split already is strongest everywhere, so a film offers three options: strongest everywhere (recommended), cheaper and custom. Lessons and picture books offer all four, recommended first and labelled so.+A film's recommended split is already strongest everywhere, so a film offers three options: strongest everywhere (recommended), cheaper and custom. Lessons and picture books offer all four, recommended first and labelled so.| Step | Lesson (tier 1 and 2) | Picture book | Documentary | Short ||---|---|---|---|---|@@ -32,13 +32,13 @@ A film's recommended split already is strongest everywhere, so a film offers thr| 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.--**small**, **middle** and **strong** stand for the user's current fast, balanced and most capable models. Each option names the actual models, not only their strength: Claude Code starts a subagent on `opus`, `sonnet`, `haiku` or `fable`, so a lesson's recommended option reads "opus for the picture and rework, sonnet for narration and review, haiku for the rest". Where you cannot tell which models the host can start, ask the user once which is their strong, middle and small model. A host that cannot choose a subagent's model, or has no subagents, runs every step on the conversation's model, so say that to the user and let the table record it. A model the host cannot start is named to the user, not swapped for another.+**small**, **middle** and **strong** stand for the user's current fast, balanced and most capable models. Each option names the actual models, not only their strength: Claude Code starts a subagent on `opus`, `sonnet`, `haiku` or `fable`, so a lesson's recommended option reads "opus for the picture and rework, sonnet for narration and review, haiku for the rest". Where you cannot tell which models the host can start, ask the user once which is their strong, middle and small model. A model the host cannot start is named to the user, not swapped for another.Every step runs at high reasoning effort unless the user asks for another; effort is not one of the questions.-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`), and the option the user chose, in its wording, in `words`. The user can change a row at any time; later chapters follow the table as it stands.+A host that cannot choose a subagent's model, or has no subagents, runs every step on the conversation's model; one that cannot set a subagent's effort runs it at the host's default. Say so to the user, let `models` record the model that runs, and report what ran at delivery ([core/team.md](team.md#before-delivering)): the conversation's model, and "host default" rather than "high" for effort.++Write into `models` the name the host's launcher takes (in Claude Code, the names above), 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`). The user can change a model at any time; later chapters follow `models` as it stands.## style.json@@ -47,7 +47,7 @@ Start from the tier's template: [lessons](../../assets/templates/style.json), or| Block | What it holds | Present in ||---|---|---|| `schema`, `tier`, `book` | schema version; `1`, `2`, `"custom"`, `"picture"`, `"documentary"` or `"shorts"`; title, slug, language, readers, pilot chapter | all |-| `words` | the user's own words about the look, verbatim, with later feedback that changed the bar, and the models option they chose | all |+| `words` | the user's own words about the look, verbatim, with later feedback that changed the bar | all || `look` | palette, what each colour means, text and maths fonts, notation and rounding | all || `voice` | TTS engine (`edge`; `kokoro` when Edge is unavailable or local audio is wanted; `eleven`, paid, for a film: [core/sound.md](sound.md#voices)), voice, rate | all || `pacing` | minutes per chapter, where checks and practice go | all |diff --git a/.claude/skills/papermorph/references/core/team.md b/.claude/skills/papermorph/references/core/team.mdindex be9ff7a..c993cba 100644--- a/.claude/skills/papermorph/references/core/team.md+++ b/.claude/skills/papermorph/references/core/team.md@@ -4,7 +4,7 @@ A coordinator can hand each step of a chapter to a fresh subagent on the model tWhy: one agent doing a whole chapter carries an ever larger context through every call, and long idle waits let that context expire and be written again; that, more than the model's price, makes a chapter expensive. Small workers that start from the files they need and finish quickly cost far less, and each step can use the cheapest model that does it well. On a physics book this cost about half as much per minute of narration as one strong agent doing everything, at the same quality.-Each step runs on the model the user chose for it (`models` in `style.json`), at the reasoning effort [core/style.md](style.md#models) sets: high unless the user asked for another. Pass both explicitly when you start a worker: the host's subagent tool or launcher takes them, and in Claude Code a subagent's model is `opus`, `sonnet`, `haiku` or `fable`. Where the host reports the model a worker actually got, compare it with the one asked for and tell the user when they differ. Where `models` is silent on a step, use the recommended option's model for it and say which model you picked.+Each step runs on the model and reasoning effort set for it ([core/style.md](style.md#models)); pass both explicitly when you start a worker, as the host's subagent tool or launcher takes them. Where the host reports the model a worker actually got, compare it with the one asked for and tell the user when they differ. Where `models` is silent on a step, use the recommended option's model for it and say which model you picked.## The coordinator