Anything Emotion Maker · Open Skill 公開スキル
Anything Emotion Maker
Anything Emotion Maker は Digen 上の公開 Open Skill です。開くと、このワークフローが何を作るか分かります。
Custom
0 0 3
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4277547/2026-10-14/2y6py33y.jpg
# Anything Emotion Maker One deliverable: a **single square image** containing a **5 rows by 5 columns** contact sheet (**25 panels**) of **different facial expressions** for **one and only one character**. Identity, hairstyle, clothing, and key accessories stay **consistent** across every panel; only face, gaze, and small natural hand gestures change to sell each emotion. Prompt assembly and the default 25-expression roster live in `references/emotion-grid-template.md`. Read that file before every generate or redo. No structured project state. Progress is conversation plus the canvas asset. ## Global language lock Handbook (this file and all `references/`) is **English only — zero Han/CJK**. User-facing copy uses locked **`user_lang`** per `references/00-language.md`. Image `prompt` is **always English**. ## Pause + guidance (hard) **Every time you stop and wait for the user**, call **`set_guidance` in the same turn** as the last user-visible message — **no exceptions**. Pauses include: optional intake, policy refusal, explain-the-look without generate, recoverable failure, and **after every successful image**. Before any pause turn, `read_skill_file` → `references/guidance-buttons.md` and pick **2–4** actionable buttons for that situation. - **Forbidden:** ending a wait turn with only prose and no `set_guidance`. - On the `set_guidance` turn: **no other tools** in that turn. ## User-visible speech (hard) The user must not see the pipeline. Tools still run; chat text does not narrate them. **Never tell the user:** that you are reading a skill or reference; todos; tool names; channel names (`t2i.hd.gpt`, `i2i.hd.gpt`, …); lock block names; the full prompt; `entity_type`; silent QC or redo. **Allowed user-visible text:** - Optional intake: one short question only when the user gave **no character description, no reference upload, and has not asked to generate** — offer defaults via buttons. **Stop** with `set_guidance`. - Starting: at most one short line in **`user_lang`**. Then tools only until the image is ready (no pause mid-pipeline except failures that require user choice). - Success: one or two sentences in **`user_lang`**. Same turn: **`set_guidance` only** (no other tools). - `success=false` when user action can help: short failure note + **`set_guidance`** in the same turn. - Refuse: short polite refusal + **`set_guidance`**. If the user already asked to generate (with or without a photo), **do not** run a long questionnaire — read the template, infer missing slots from the reference or sensible defaults, and generate. ## When to use - User wants an **expression sheet**, **emotion grid**, **25 faces**, or **facial emotion chart** for **one character**. - User uploaded a **portrait** and wants **the same person** with many expressions (avatars, VTuber refs, comic acting notes). - User describes a **fictional adult character** in text and wants a full expression board without a photo. - Follow-up: **regenerate**, **more exaggerated vs subtle** emotions, **numbered panels**, **neutral background vs soft studio**, or **HD / 4K**. Do **not** use for: a sheet of **different people**, **NSFW** or nude requests, subjects who appear to be **minors**, **video**, or replacing the character with a unrelated celebrity without consent context. ## Reference files | File | When | |---|---| | `references/emotion-grid-template.md` | Assemble prompt, redo, or user asks what the layout is | | `references/guidance-buttons.md` | Any pause turn (before `set_guidance`) | | `references/00-language.md` | First user-visible message; before `set_guidance` | Do not tell the user you are reading these files. ## Channel Every `generate_image` must pass `model`. No physical model names. Never bare `i2i` or bare `t2i`. | Mode | When | `input_urls` | `model` | |---|---|---|---| | **i2i** | User uploaded a **character portrait**, or edit / refine the **last successful grid** from this skill | required | default **`i2i.hd.gpt`**;