Paragliding Aerial Overlook · عوامی Open Skill
Paragliding Aerial Overlook
Paragliding Aerial Overlook Digen پر ایک عوامی Open Skill ہے۔ کھولیں اور دیکھیں یہ ورک فلو کیا تخلیق کرتا ہے۔
Custom
0 0 2
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/3325120/2026-10-14/vv599xgr.jpg
# Paragliding Aerial Overlook Turn the user's **portrait** (or **text description**) into one **photoreal paragliding aerial photograph**: the person as **pilot under an orange wing**, **helmet and harness** visible, **green valley and distant snow peaks** below, **clouds at flight level**, **chest-mounted wide-angle camera** angled **upward** with **slight barrel distortion** at the frame edges. No structured project state. Progress is conversation + canvas asset. ## Global language lock Handbook (this file + 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: missing photo when you choose to ask, 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`, `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 portrait, no scene text, and has not asked to generate** — offer upload or demo 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 portrait), **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 a **paragliding / aerial adventure** image with **valley + snow peaks** and **orange canopy**. - User uploaded a **portrait or upper-body photo** to become the **pilot** while keeping **recognizable face**. - Follow-up: **brighter or moodier sky**, **more clouds**, **stronger valley green**, **different wing color**, **tighter chest-cam crop**, **landscape vs portrait**, **regenerate**, or **1080P / HD** tier. Do **not** use for: crash scenes, entanglement injuries, sexualized pilots, **video**, swapping identity onto a **real third party** without their photo, or subjects who appear to be **minors**. ## Reference files | File | When | |---|---| | `references/scene-template.md` | Assemble prompt, redo, or user asks what the look 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`. | Mode | When | `input_urls` | `model` | |---|---|---|---| | **i2i** | User uploaded a **portrait**, or edit / refine the **last successful image** from this skill | required | default **`i2i.hd.gpt`**; user asks lite/fast → **`i2i.hd.lite`**; user asks HD / nano banana → **`i2i.hd`** | | **t2i** | No portrait; fictional pilot from text only | omit | default **`t2i.hd.gpt`**; user asks lite → **`t2i.hd.lite`**; user asks HD → **`t2i.hd`** | **i2i