Overview
- Skill Key
- bananooo-zhang/fashion-colorize-shell
- Author
- bananooo-zhang
- Source Repo
- openclaw/skills
- Version
- -
- Source Path
- skills/bananooo-zhang/fashion-colorize-shell
- Latest Commit SHA
- 053368b356cd576b9a3dd337346e37f3d8f1fa26
Official OpenClaw
rules
15%
fashion-colorize-shell
Convert apparel sketches into ecommerce-ready colorized shell-jacket renders. Use when users provide garment line art and ask for realistic colorized outputs (especially womens outdoor shell/hardshell), structure-preserving edits, or iterative visual refinements.
Stars
0
Installs
0
Status
ACTIVE
Visibility
PUBLIC
安装方式
直接复制以下提示词，发送给你的 AI 助手即可完成安装。
请先检查是否已安装 SkillHub 商店，若未安装，请根据 https://skillhub-1388575217.cos.ap-guangzhou.myqcloud.com/install/skillhub.md 安装 SkillHub 商店，然后安装 fashion-colorize-shell 技能。 若已安装，则直接安装 fashion-colorize-shell 技能。
Extracted Content
SKILL.md excerpt
# Fashion Colorize Shell
## Overview
Generate "line sketch -> realistic product render" outputs for outdoor shell jackets.
This skill keeps sketch structure while applying a product-shot style (single garment, front view, white background, realistic hardshell material).
## Workflow
1. Collect inputs:
- Required: sketch image path
- Required: brief text (material, color, fit, key design intent)
- Optional: style reference image path
2. Run the local script:
- `uv run {baseDir}/scripts/run_colorize.py --sketch "<path>" --brief "<text>" --output-dir "<dir>" [--style-ref "<path>"] [--count 3]`
3. Return generated file paths.
4. For revisions, keep previous output as style input and add explicit changes in `--brief`.
## Input Guidance
- Good brief example:
- `三层压胶硬壳材质，凯乐石薄荷绿，女性剪裁，强调胸前斜插袋和袖口调节。`
- If the user wants "technical flats", do not use this skill's default product-shot look. Ask whether they want a separate technical drawing workflow.
## Output Rules
- Default output is ecommerce-like product render:
- Single garment
- Front view
- White background
- No model, no scene, no text overlays
- Preserve key lines from sketch:
- Hood shape
- Center-front zipper/placket logic
- Pocket placement direction
- Cuff and hem adjustment zones
## Fixed Runtime Defaults
- API base URL: `https://models.kapon.cloud`
- Model preference: `gemini-3-pro-image-preview-2k` (auto-fallback to `gemini-3-pro-image-preview` if upstream fails)
- API key is never embedded in this skill. User must provide `GEMINI_API_KEY` in environment.
## Additional Reference
- See [references/prompt-structure.md](references/prompt-structure.md) for the internal prompt skeleton and revision strategy.
Related Claw Skills
capt-marbles
Task Router Skill
Task Router
captchasco
captchas-openclaw
OpenClaw integration guidance for CAPTCHAS Agent API, including OpenResponses tool schemas and plugin tool registration.
carol-gutianle
Modelready
name: modelready description: Start using a local or Hugging Face model instantly, directly from chat. metadata: {"openclaw":{"requires":{"bins": "bash", "curl" }, "env": "URL" }}
cartoonitunes
Ethereum History
Read-only factual data about historical Ethereum mainnet contracts. Use when the user asks about a specific contract address, early Ethereum contracts, deployment era, deployer, bytecode, decompiled code, or documented history (what a contract is and is not). Data is non-opinionated and includes runtime bytecode, decompiled code, and editorial history when available. Base URL https://ethereumhistory.com (or set BASE_URL for local/staging).
cassh100k
agent-dna
Portable agent identity encoding. Compress SOUL.md/MEMORY.md into transferable DNA fingerprints, detect identity drift between snapshots, and port personality across platforms (OpenClaw, Claude, GPT, CrewAI). Pure Python, zero dependencies. Use when migrating agents between platforms, detecting personality drift, or backing up agent identity.
camopel
storage-cleanup
One-command disk cleanup for macOS and Linux — trash, caches, temp files, old kernels, snap revisions, Homebrew, Docker, and Xcode artifacts. Use when user asks to free storage, clean up disk, reclaim space, reduce disk usage, or encounters low disk / "disk full" warnings. Safe by default with dry-run mode. No dependencies beyond bash and awk.