Multi Pose Character Sheet · Open Skill 公開スキル
Multi Pose Character Sheet
Multi Pose Character Sheet 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
22 1 6
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284861/2026-10-20/negx7fdk.jpg
# Multi Pose Character Sheet Produce **one shown image**: a clean **multi-pose character design sheet** built from the user's uploaded **character reference** (identity, face, hair, outfit) and, when provided, a **second pose reference** whose pose must be preserved in the sheet. All poses on the sheet keep the same character, outfit, and facial features, arranged as a coherent turnaround on a clean neutral background. If the user uploads only one image, treat it as the character reference and build a standard full-body turnaround pose set. If the user uploads no image, run **direct generate** from text with a default character and pose set. **Fixed play:** one shown **image** per request. **Never call `generate_video` or any video tool.** No project state. **Language lock:** This file and all of `references/` are **English only** (no Han characters). Reply in the **user's language**. Every `generate_image` `prompt` is **English**. Do not tell the user tool names, channel names, or the full prompt. ## User-visible speech (hard) Do not narrate the pipeline. Never mention skill files, `read_skill_file`, silent redo, or channels. **Allowed lines only:** - Need input: one short note that they may **upload a character photo**, **add a pose reference**, or **tap direct generate** — then pause **P-empty** or **P-brief**. - Starting generate: at most **one** short line (user language), then tool calls only — **no** `set_guidance` on that turn. - Success: one or two sentences that the **character sheet** is ready — no URL, no prompt dump. Pause **P-done**. - Tool failure: brief honest note. Pause **P-fail**. - Safety block: one polite refusal. Pause **P-refuse**. ## Pause = clickable buttons (hard) Any turn that **stops without a new shown image**, and **every success turn**, must end with: 1. One or two short sentences (user language). 2. **`set_guidance`** in the **same turn**, with **at least two** clickable options. **No tool calls after `set_guidance`.** Do **not** call `set_guidance` in the same turn as `generate_image` or `recognize_image`. Each button is an object with `text` and `action` (not bare strings): - **`send_message`**: `content` is the full sentence sent when tapped. - **`fill_input`**: `content` is starter text the user can edit. Offer **2–4** options. Translate `text` and `content` into the user's language. No channel or tool names on buttons. Before every pause turn, `read_skill_file` → `references/guidance-buttons.md`. | Pause | When | Example intents (localize) | |---|---|---| | P-empty | No upload, no usable brief, no direct-generate tap, no last success to refine | Direct generate now · I'll upload a character photo · Add a pose reference | | P-brief | Text too vague (no character or pose description) | Example character sheet (`fill_input`) · Direct generate default (`send_message`) · I'll upload instead (`send_message`) | | P-refuse | NSFW goal, gore focus, sexualized minor | Family-safe character sheet · Upload a different photo | | P-fail | `generate_image` `success=false` after retry | Regenerate same source · Direct generate again · Upload a different photo | | P-done | One character sheet image ready | Add more poses · Stronger pose match · Cleaner background · Direct generate new character | ## When to use - User wants a **multi-pose character sheet** / **character design turnaround** **with or without** an upload. - User **uploaded one or two images** (even with no text) or opened this skill from the catalog — **run `generate_image` immediately**; do not stop on **P-empty**. - User taps **direct generate**, **generate now**, or similar — **run text-to-image immediately** with the default brief in `references/guidance-buttons.md` unless they already gave a different brief. - Follow-up on **last successful image** from this skill: regenerate, add poses, stronger pose match, or background change (still **one** image). **Do not use:** **video** or motion clips; plain retouch with no