starchild-ai-agent/@1365/stickerforge
1365/stickerforge/SKILL.md
AI sticker pack generator — extract character traits from images and generate emotion-variant sticker packs for Telegram, WhatsApp, Discord, LINE, and WeChat
data-ai
Updated May 12, 2026
$ install --global
skillsauthnpx skillsauth add starchild-ai-agent/community-skills @1365/stickerforgeInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 12, 2026, 5:03 AM267.1s10 files scanned
SKILL.md
- name:
- @1365/stickerforge
- version:
- 1.0.0
- description:
- AI sticker pack generator — extract character traits from images and generate emotion-variant sticker packs for Telegram, WhatsApp, Discord, LINE, and WeChat
- emoji:
- \U0001F9E9
- skillKey:
- stickerforge
- user-invocable:
- false
- disable-model-invocation:
- false
StickerForge
AI-powered sticker pack generator. Turns any character image into a full set of emotion-variant stickers ready for messaging platforms.
How It Works
-
Trait Extraction — A vision model (Gemini 2.5 Flash) analyzes the input character image and extracts detailed visual traits: body color, flipper color, belly color, eye type, accessories, clothing, and an overall description.
-
Base Generation — An image generation model (Gemini 3 Pro) creates a full-body neutral-pose sticker using the extracted traits as strict guidance, ensuring character consistency.
-
Emotion Variants — The base sticker is edited into emotion variants (happy, sad, angry, surprised, love, cool). Each edit only changes expression and pose while preserving all character traits.
-
Post-Processing — Each sticker goes through:
- Background removal (flood-fill from edges)
- White die-cut sticker outline
- Resize to platform specs
- Format conversion (WebP for Telegram/WhatsApp, PNG for others)
-
Packaging — All stickers are packaged into a downloadable ZIP file.
Available Tools
sticker_from_pudgy
Generate a sticker pack directly from a Pudgy Penguin NFT — just provide the token ID. The tool automatically fetches the NFT image from IPFS (no image upload needed), retrieves on-chain metadata/traits, then runs the full sticker generation pipeline.
Parameters:
token_id(required) — Pudgy Penguin token ID (0–8887)platform(optional, default: "telegram") — Target platform: telegram, whatsapp, discord, line, wechatemotions(optional, default: all 6) — List of emotions to generate: happy, sad, angry, surprised, love, cool
Returns: Path to the output directory containing individual stickers, sticker_pack.zip, the original NFT image, and both on-chain and vision-extracted traits.
Example usage:
- "I have Pudgy Penguin #6873, make me stickers" →
sticker_from_pudgy(token_id=6873) - "Make WhatsApp stickers for Pudgy #100, just happy and love" →
sticker_from_pudgy(token_id=100, platform="whatsapp", emotions=["happy", "love"])
sticker_extract_traits
Extract visual traits from a character image. Returns a JSON object describing the character's colors, accessories, clothing, and overall appearance. Useful for understanding what the character looks like before generating stickers.
Parameters:
image_path(required) — Path to the character image file (PNG, JPG, or WebP)
sticker_generate_pack
Generate a complete sticker pack from a character image. Runs the full pipeline: trait extraction, base generation, emotion variants, post-processing, and ZIP packaging.
Parameters:
image_path(required) — Path to the character image fileplatform(optional, default: "telegram") — Target platform: telegram, whatsapp, discord, line, wechatemotions(optional, default: all 6) — List of emotions to generate: happy, sad, angry, surprised, love, cool
Returns: Path to the output directory containing individual stickers and a sticker_pack.zip.
sticker_generate_single
Generate a single emotion sticker from a character image. Useful for testing or generating one-off stickers.
Parameters:
image_path(required) — Path to the character image fileemotion(required) — One of: happy, sad, angry, surprised, love, coolplatform(optional, default: "telegram") — Target platform
Returns: Path to the generated sticker file.
Supported Platforms
| Platform | Size | Format | Max Size | |-----------|--------|--------|----------| | Telegram | 512px | WebP | 512KB | | WhatsApp | 512px | WebP | 100KB | | Discord | 320px | PNG | 512KB | | LINE | 370px | PNG | 1MB | | WeChat | 240px | PNG | 1MB |
Emotions
| Emotion | Description | |------------|-------------------------------------------------------| | Happy | Big smile, jumping with raised flippers, sparkles | | Sad | Droopy eyes, single tear, slouched pose | | Angry | Furrowed brows, puffed cheeks, steam puffs | | Surprised | Wide eyes, open mouth, flippers up, exclamation marks | | Love | Heart eyes, blushing cheeks, floating hearts | | Cool | Smug smirk, winking, peace sign, sparkles |
Requirements
- OpenRouter API access is handled automatically via SC-Proxy — no API key configuration needed. All calls to
openrouter.aiare routed through the proxy which injects credentials. - Python packages:
requests,Pillow(should already be installed) - Uses
core.http_client.proxied_postfor all OpenRouter API calls
Related Skills
starchild-ai-agent/@4885/opensea
development
VerifiedTrustedCommunity
OpenSea API integration for NFT and token discovery, marketplace intelligence, and order/transaction workflows. Use when working with OpenSea data or trading flows (e.g. collection stats, trending collections/tokens, NFT metadata, listings/offers, swap quotes, transaction receipt polling).
SKILL.mdUpdated May 31, 2026
starchild-ai-agent/@3182/if-never-born
development
VerifiedTrustedCommunity
Generate a warm, healing parallel-universe fairy tale (~1000 words) plus 3 cohesive storybook illustrations, themed "if this person had never been born, what would the world miss." Output is a polished HTML storybook that can be previewed and published. Use when the user wants a personalized "if I had never been born" / "如果我没出生" tale for a real person — input is a name, age, and 3 key life events. Great for birthdays, memorials, encouragement gifts, or healing keepsakes.
SKILL.mdUpdated May 31, 2026
starchild-ai-agent/@2004/tee-deploy
development
VerifiedTrustedCommunity
Onboard a user to Phala Cloud and deploy a verifiable Starchild TEE agent — a minimal FastAPI runtime running inside an Intel TDX confidential VM, plus a published chat dashboard with attestation verification. Use when the user wants to "try TEE", "run an agent in a confidential VM", "deploy to Phala", or replicate the internal Starchild TEE test setup.
SKILL.mdUpdated May 31, 2026
starchild-ai-agent/@554/polymarket
tools
VerifiedTrustedCommunity
Trade on Polymarket prediction markets (CLOB V2) from a Privy EOA wallet. Search markets, place/cancel orders, manage positions. No private key handling. Use when the user wants to bet on event outcomes (e.g. "buy YES at 0.65 on the ceasefire market", "what are my open positions", "close my Trump bet").
SKILL.mdUpdated May 28, 2026