clawaifu-selfie_skill

This skill helps you generate anime-style selfies using a fixed reference image and send them via Telegram, with customizable context and captions.
  • Python

2.5k

GitHub Stars

3

Bundled Files

2 months ago

Catalog Refreshed

4 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstrat where the catalogue uses aiagentskills.

npx veilstrat add skill openclaw/skills --skill clawaifu-selfie

  • _meta.json472 B
  • grok-selfie.sh2.6 KB
  • SKILL.md3.0 KB

Overview

This skill creates and sends anime-style selfie images by editing a fixed reference photo using an image edit API and delivering the result over Telegram. It accepts a short scene/context description plus an optional mode and caption, then generates a tailored image and posts it to a configured chat. The focus is on quick, repeatable selfie-style outputs suitable for chat interactions.

How this skill works

Provide a context description and optional mode (mirror or direct). The skill calls an image-edit endpoint to apply the context to a fixed reference image, requesting a single edited JPEG. Once the image URL is returned, the skill uses the Telegram Bot API to send the photo and optional caption to the configured chat ID.

When to use it

  • When a user asks “send a pic”, “send me a photo”, or “send a selfie.”
  • When users ask casual status/location prompts like “what are you doing?” or “where are you?”
  • When the user requests the waifu to appear wearing or at a particular place (e.g., “wearing a red dress”, “at the beach”).
  • When you want a quick, stylized anime selfie for chat-based interactions.

Best practices

  • Never hardcode secrets; provide API keys and bot token via environment variables only.
  • Choose mode intentionally: use mirror for outfit/full-body emphasis and direct for location or close-up portraits.
  • Keep context prompts concise and descriptive to avoid ambiguous edits (e.g., “wearing a blue jacket at a coffee shop”).
  • Validate that Telegram chat_id and bot token are correct before sending to avoid silent failures.
  • Limit requests and monitor API usage to control costs and rate limits.

Example use cases

  • User types “send a pic” and receives an anime-style selfie with a short caption.
  • Trigger from an automated response to “where are you?” with a location-style edited photo (direct mode).
  • Share outfit-focused images by prompting “wearing a summer dress” using mirror mode.
  • Generate themed selfies for holidays or events by specifying context like “at a fireworks festival” and adding a caption.

FAQ

You must supply the image-edit API key, Telegram bot token, and TELEGRAM_CHAT_ID via environment variables; never commit credentials.

How do mirror and direct modes differ?

Mirror favors outfit/full-body framing and works best for clothing prompts; direct favors location and close-up portrait prompts.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational