Update to Frameo.AI

SKILL.md text changes

− removed · + added

--- before
+++ after
@@ -1,29 +1,28 @@
 ---
 name: character-sheet
-description: "A consistent character across views and expressions, on the canvas so every later image and video can keep the same face."
+description: "A consistent character across views and expressions, saved in the project so every later image and video can keep the same face. Use before multi-shot work with a recurring person or mascot, such as a series, a brand character or a story cast."
 ---
 
-Needs: a description or a photo; the style (photoreal, anime, 3D, editorial)
-Credits: about 90–130 (5–7 images at ~18 each)
-Time: 10 minutes
-
 ## When
 
-Before any multi-shot work with a recurring person or mascot: a series, a brand
-character, a game or story cast. `script-to-video` calls this for its cast.
+Before any multi-shot work with a recurring person or mascot: a series, a brand character, a game
+or story cast. `script-to-video` calls this for its cast.
 
 ## Ask first
 
-1. **Who** — a photo (`show_upload` for files on the user's device, `import_media_url` for a web link; images attached to the chat do not reach Frameo, and `create_upload_url` is for clients that send the file themselves) or a description: age, build, hair, clothes, one
-   distinguishing detail.
-2. **Style** — photoreal, editorial, anime, 3D, game concept.
-3. **Views** — the default is front, three-quarter, profile, full body, two expressions.
+1. **Who** — a photo (`show_upload` for files on the user's device, `import_media_url` for a web link; images attached to the chat reach Frameo only through `import_attachments`, in apps that pass them such as ChatGPT, and `create_upload_url` is for clients that send the file themselves) or a description: age, build, skin, face, hair, clothes from head
+   to toe, and one distinguishing detail. A real person's likeness only from their own photo, with
+   their consent; otherwise an original character, never a celebrity or an existing copyrighted
+   one.
+2. **Style** — photoreal (the default), editorial, anime/2D, 3D stylized or game concept.
+3. **Views** — the default is front, three-quarter, profile, full body and two expressions.
 
 ## Steps
 
 **Before any paid step.** The project: `list_projects` (or `create_project`) gives the `project_id`
 and, when the project has several modules, the `module_id`; every call below that takes a project —
-`estimate_cost` included — gets that same pair; without it those tools answer `project_needed`. The
+`estimate_cost` included — gets that same pair; without the project those tools answer `project_needed`, and without the
+module of a project that has several, `module_needed`, which lists its modules. The
 quote: one `estimate_cost(items=[…])` prices a stage in one call, with the same project, model,
 size and number of `image_urls` or `reference_image_urls` (`reference_count`) as each generate call, and returns a `quote_id` per item plus the total. Each generate call
 then passes its own item's `quote_id` and `confirmed_by_user=true`. A quote is single-use and lasts
@@ -31,7 +30,7 @@
 comes to more than the user approved is asked about again first. Generate calls return
 `generation_ids`; `wait_task` returns the links, and `show_generations` shows each stage's running
 and finished work in one card where the chat app displays Frameo cards: all the stage's ids at
-once, before its first `wait_task`, and the finished result with `final: true`.
+once, before its first `wait_task`; the card updates itself as the work finishes, so the same ids are not shown again.
 
 **The plan first.** Before the first paid call, the plan goes to the user in the chat as plain
 text: what will be made, in order, one line per generation (for a script, the shot list; for a
@@ -41,17 +40,35 @@
 generated until the user says yes. The user can drop or change lines; a changed line is priced
 again.
 
-**Canvas rows.** Every `generate_image` here takes `placement_kind="character"` and `placement_group=<the character's name>`, so the sheet is one row on the character board, and later shots that use it as a reference get rows of their own.
+**Grouping.** Every `generate_image` here takes `placement_kind="character"` and `placement_group=<the character's name>`, so the sheet is kept together with the project's character references, apart from the later shots that use it.
+
+**0. The prompt (free).** Fill the slots in `get_skill_file(skill_id="character-sheet", path="references/prompt-slots.md")` in order, with the
+style's modules from `get_skill_file(skill_id="character-sheet", path="references/styles.md")`. Every detail is specific (materials, colours,
+cut), never "nice top". For an adult character, the face has adult structure (the rule is in the
+slots file). The physical description is written once and goes word for word into every
+generation below, so nothing drifts.
+
+**Optional preview (~18).** When there is no photo, offer one split-screen sheet first: the
+character standing full body on the left and a chest-up close-up on the right, in one 16:9 image
+(the composition is in the slots file). It settles the look for the price of one image before the
+anchor and the views. Its link can then be the anchor's `image_urls`.
 
 **1. The anchor (~18).** `generate_image`: front view, neutral expression, plain background,
-in the style; `image_urls=[photo]` when given. `wait_task`, show it; this is the face
-everything else follows — iterate here, not later.
+in the style; `image_urls=[photo]` when given (or the preview). `wait_task`, show it; this is the
+face everything else follows — iterate here, not later.
 
 **2. The views (~18 each).** `generate_image` per view, each with its own quote, with
-`image_urls=[anchor]` first and the view in the prompt ("three-quarter view, same person,
-same clothes"). Keep the background plain. `wait_task` for the links.
+`image_urls=[anchor]` first and the full description plus the view in the prompt
+("three-quarter view, same person, same clothes"). Keep the background plain and the light the
+same. Each view is compared with the anchor — face, hair, outfit, accessories — using
+`view_image(url, resolution="high")` for the face when the preview leaves it in doubt; a view that
+drifts is retaken once from the anchor. `wait_task` for the links.
+
+**Changes later.** When the user changes something, every detail already set (face, hair, body,
+outfit, accessories) carries forward unchanged; change only what was asked and restate the rest in
+the prompt.
 
-**3. The references.** The anchor and views stay on the project canvas; their links, anchor
+**3. The references.** The anchor and views stay in the project; their links, anchor
 first, are what later generations take as `image_urls` / `reference_image_urls`.
 
 **4. Save it to the cast (free).** `save_character` with the character's name and the anchor
@@ -61,11 +78,11 @@
 
 ## Done
 
-The anchor and its views on the canvas in one row, with their links for later shots, and the
+The anchor and its views in the project, kept together, with their links for later shots, and the
 character in the project's cast.
-`open_in_frameo` on the result opens the project in the Frameo app, where every take sits on
-the canvas, ready for retakes and edits.
+`open_in_frameo` on the result opens the project in the Frameo app, where every take is ready for retakes and edits.
 
 ## Files
 
-None.
+- `references/prompt-slots.md` — the prompt's slots in order, the realism and adult-structure rules, the compositions and the negative tail.
+- `references/styles.md` — the five styles, each with its render, lighting and quality lines.