SureForge
SkillAn instruction-only skill that makes agents research before they ask, plan before they build, and verify before they call anything done.
- workflow
- verification
- quality
- skill
ray-sticker-shop
A sticker-workshop Claude skill: one reference image locks the character across the whole set, and out comes the full WeChat sticker-platform kit — 240x240 GIFs auto-squeezed under 500KB
ray-sticker-shop (titled Sticker Workshop in its README) is a Chinese-language Claude Code skill that turns a consistent sticker set from per-image luck into a pipeline: one photo or character art locks the design for the whole set; GIFs are generated at 240x240 and auto-compressed under WeChat's 500KB cap; the cover, chat icon, banner and appreciation image ship together; outputs are checked against WeChat's spec automatically, and the listing copy plus a client-delivery package come with the batch. A single clone into your agent's skills directory (~/.claude/skills/) completes the install; actually rendering images also needs Python 3.9+ with Pillow (pip install pillow) and an OPENAI_API_KEY — without one, take the prompts the agent writes, generate the images in ChatGPT, and feed them back per the README's fallback. 294 stars as of writing (2026-11-07).
What it does
- One reference image locks the character design across the entire set
- 240x240 GIFs auto-compressed under WeChat's 500KB per-sticker cap
- Full platform kit in one run: cover, chat icon, banner and the appreciation image (赞赏图)
- Automatic checks against WeChat's sticker spec before hand-off
- Listing copy and a client-delivery package generated alongside the assets
When to use it
For creators and commissioned artists shipping to WeChat's sticker platform: when a character IP already has reference art and you need a full compliant animated set, the skill batch-runs compression, spec checks and asset assembly.
Getting started
# from the README: put the folder into your agent's skills directory git clone https://github.com/imraywang/ray-sticker-shop ~/.claude/skills/ray-sticker-shop
Things to know
WeChat-ecosystem first: aligned to WeChat's sticker spec, other platforms need your own re-checks. Only make stickers for characters you have the rights to — WeChat rejects unauthorized derivative and fan works; approval is WeChat's call, and the tool guarantees neither approval nor revenue (the README's own notice). Generation runs through OpenAI's image channel (GPT Image 2.6 per the repo's SKILL.md) and needs OPENAI_API_KEY (OPENAI_BASE_URL for relays); 8 stickers plus 5 companion assets run about $0.7 at OpenAI's official prices per set, re-rolls extra, spend logged to costs.jsonl. MIT. 294 stars as of writing (2026-11-07).
Repository
imraywang/ray-sticker-shopCharted
Related on the map
Guizang's agent skill turns your repo's recent updates into a finished promo video — real components, code-rendered animation, an original code-written soundtrack — no video editor involved.
- agent-skill
- video
- promo
- marketing
geo-sleuth
SkillAn agent skill that geolocates a photo with nothing readable in it — OSM geometry, elevation skylines and satellite tiles turn “where was this taken?” into a measured answer with an error radius.
- agent-skill
- geolocation
- osint
- openstreetmap