Christmas Comic Maker · Open Skill 公開技能
Christmas Comic Maker
Christmas Comic Maker
Manhua
1 0 0
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/3949831/2026-10-13/6w9mqrzw.jpg
# Christmas Comic Maker Make **one finished Christmas manga comic page** in a vertical 9:16 collage. There is no project database. Style, panel splits, Christmas motifs, on-image language, and prompt blocks live in `references/christmas-comic-style.md`. Read that file before every generate. Do not invent a different comic look from memory. This skill does **one job**: a festive Christmas **manga page**, not a single character portrait, not a poster with no panels, not Halloween, not a video. **Hard content rule:** the page must read as a Japanese-style shoujo/moe **comic collage** (thick black gutters, overlapping irregular panels, speech bubbles, a title banner). Text-to-image invents the cast. Image-to-image **weaves the uploaded subject into the comic** as the hero (and supporting source people/pets into other panels). Do not paste the photo as a raw inset. Do not drop the user's likeness. ## 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 a reference file; a todo list; tool names (`recognize_image`, `generate_image`, `read_skill`, `read_skill_file`, `write_todos`, `set_guidance`); channel names (`t2i`, `i2i.hd.lite`, `i2i.hd`, `i2i.hd.gpt`); the prompt; `entity_type`; layout codes (A–F). Do not print "step 1 / step 2". **The only user-visible text:** - Need a photo and the wording is clearly "put me / this photo into a comic": ask for an upload, then stop. If they only asked for a Christmas comic from text, do **not** block on an upload. - Starting a make: at most one short line in the user's language, such as `Okay, making your Christmas comic now.` Then only tools until the image is ready. No chatter between tools. - Success: one or two sentences that the comic is ready. Do not paste URLs. Do not repeat the prompt. Same turn: `set_guidance` only, no other tools. - Tool `success=false`: say it did not finish. Do not name the tool or invent a URL. - Refuse: a short polite refusal. Do not generate. If a turn includes tool calls, the text in that turn may only be the allowed making line, the ready line, the ask-for-upload line, the failure line, or the refusal. ## When to use - The user wants a Christmas manga, Christmas comic page, holiday comic strip, Santa/snowman/reindeer comic, or a festive storyboard illustration. - The user uploaded a selfie, portrait, pet, character, or scene and asked to turn it into a Christmas comic / weave it into manga panels. - The user wants to change the last Christmas comic: different panels, different speech, different Christmas look, another layout, or another language on the lettering. Do not use this skill for ordinary photo retouch, non-Christmas comics, Halloween pages, collectible figures, pixel-game restyles, or video. ## Reference file This skill has **one** reference file. Read it before every generate, layout change, or speech rewrite. Do not read files that are not listed. Do not tell the user you are reading it. | File | Tools | When to read | |---|---|---| | `references/christmas-comic-style.md` | `generate_image` | About to generate, change the panel split, rewrite bubbles, restyle the last page, or the user asks what the comic look is | ## Channel Every `generate_image` call must pass `model`. Write a channel only. Never write a physical model name. Never name a channel to the user. `.hd*` channels **do not support NSFW**. | Mode | When | `input_urls` | `model` | |---|---|---|---| | **t2i** | This turn has no reference image (text-to-image) | omit | **`t2i`** | | **i2i default** | The user uploaded an image, or wants to edit the last comic | required | **`i2i.hd.lite`** | | **i2i hd** | The user says hd / nanobanana / higher quality / sharper panels | required | **`i2i.hd`** | | **i2i gpt** | The user says GPT / GPT image / gpt, or wants clearer bubble lettering | required | **`i2i.hd.gpt`** | The two main paths: - **No image → t2i** Ch