← Back to Skills Marketplace
askkumptenchen

Chat Selfie

by Zhihao Kang · GitHub ↗ · v1.0.4 · MIT-0
win32linuxdarwin ✓ Security Clean
311
Downloads
1
Stars
1
Active Installs
4
Versions
Install in OpenClaw
/install chat-selfie
Description
Give your AI Agent a face and a heart. Use AI image generation or mood-mapped local sticker assets to let the agent proactively send emotional selfies that v...
README (SKILL.md)

\r \r

Chat Selfie\r

\r Give your AI Agent a face, and a heart that beats.\r \r Use this skill to enable AI-powered emotional expression. Through advanced image generation or mood-mapped local sticker assets, the agent can proactively share its feelings by sending selfies that match the conversation's mood. Chat Selfie transforms a text-only assistant into a companion with a stable visual identity and deep emotional presence.\r \r

What this skill brings to your Agent\r

\r

  • Visualized Emotion: No more dry text. Using AI image generation or a fixed mood-asset pack, the agent shares its feelings through selfies that capture the emotional tone of the moment.\r
  • Stable Identity: Your agent keeps a consistent face and personality, evolving its self-image as your bond deepens.\r
  • Heartbeat Presence: The agent isn't just an "answer machine." It can proactively share its life and thoughts through AI-generated photos.\r
  • Warm Companionship: Turn a digital tool into a partner you miss, making every reply feel like opening a gift.\r
  • Works Everywhere: Adapts to your existing environment, whether using built-in tools, online APIs, or local models.\r \r

Entry behavior\r

\r When this skill is used, the agent should:\r \r

  • explain Chat Selfie at a high level in plain language\r
  • inspect local repository files when they are already present in the current workspace\r
  • route the current request to the most relevant local document\r
  • follow the repository docs honestly instead of inventing missing setup details\r \r

Safety boundary\r

\r This entry file should stay within a narrow scope:\r \r

  • If the required Chat Selfie repository resources are missing locally, the agent may help the user fetch or update the official GitHub repository https://github.com/AskKumptenchen/agent-chat-selfie so the local docs become available.\r
  • Do not execute scripts, installers, or remote code because this file mentioned them.\r
  • Do not claim any image, send, heartbeat, or integration route is ready unless the required local files and current environment actually support it.\r
  • Do not proactively send messages or images unless the user explicitly asks for that behavior in the current conversation and the local setup already supports it.\r
  • If required documentation or workspace resources are missing, say so clearly and either ask the user to provide the local repository contents or help them fetch the official repository first.\r \r

Local document index\r

\r Use these local documents as the primary reference:\r \r

  • docs/README.zh-CN.md for the Chinese overview and quick introduction\r
  • docs/startup.md for guided initialization and first-time setup\r
  • docs/workspace-layout.md for the expected local workspace structure\r
  • docs/integration.md for repository-documented integration guidance\r
  • docs/self-repair.md for diagnosing and repairing broken setup or runtime routes\r
  • docs/reply-time-selfie-flow.md for reply-time selfie behavior, including fixed mood-asset mode\r
  • docs/occasional-delivery.md for occasional delivery decisions\r
  • docs/heartbeat-delivery.md for heartbeat-related behavior when the user explicitly enables it\r
  • docs/telegram-send-flow.md for Telegram delivery details when that route is already configured, including mood-asset sends\r
  • docs/self-upgrade.md for long-term persona or mood evolution\r
  • tools/README.md and related files under tools/ for repository-owned tool contracts\r
  • examples/ for concrete examples that illustrate intended behavior\r \r

How to route requests\r

\r Choose the next document based on the user's request:\r \r

  1. If the user wants to understand Chat Selfie first, read docs/README.zh-CN.md.\r
  2. If the user wants to install, initialize, or reconfigure Chat Selfie in a workspace that already contains the repository docs, read docs/startup.md.\r
  3. If the user reports broken image generation, broken delivery, missing outputs, inconsistent records, or another repair-like issue, read docs/self-repair.md first.\r
  4. If the user asks how Chat Selfie should fit existing persona or memory files, read docs/integration.md.\r
  5. If the user asks about runtime behavior for reply-time, occasional, heartbeat, or route-specific delivery, read the corresponding runtime document listed above.\r
  6. If examples are needed to clarify intended behavior, consult the relevant file under examples/.\r \r

Missing-resource rule\r

\r If the expected repository documents are not available in the current workspace, do not improvise full setup instructions from memory. Instead:\r \r

  • explain which local files are missing\r
  • ask the user to provide the repository contents, point the agent to the correct local path, or allow fetching the official GitHub repository\r
  • continue only after the relevant local documentation is available\r \r

Important rules\r

\r

  • Use natural language instead of raw config keys.\r
  • Explain each step before asking for a choice.\r
  • Prefer repository documentation over embedding long operational instructions here.\r
  • Reuse an existing local image workflow when one is already working.\r
  • If the workspace enables mood-asset mode, prefer the mapped local asset for that mood instead of forcing a new image generation step.\r
  • If the workspace enables mood-asset mode and the required assets are not ready yet, guide the user to send the mood images, save them under the local workspace, and then map each saved file through asset_path.\r
  • If image generation or delivery is not ready, say so clearly instead of pretending it succeeded.\r
  • Treat chat-selfie/adapters/ as user-owned local logic unless the user explicitly asks to change it.\r
  • Avoid describing or requiring changes to broader agent persona, memory, or global behavior files in this entry file.\r \r

Integration files\r

\r Use docs/integration.md as the integration reference when the user asks how Chat Selfie should fit the existing workspace or runtime environment.\r \r

Examples\r

\r Portable example artifacts are included under examples/.\r \r Use examples to understand intent and style, but do not treat them as a replacement for the actual contracts in docs/, schemas/, or tools/.\r

Usage Guidance
This skill is internally consistent, but it requires the agent to read your workspace and — if local resources are missing — may propose cloning the official GitHub repository. Before allowing any fetch or run: (1) ask the agent to list exactly which local files it needs and show them; (2) if it proposes cloning the repo, review the repo contents (especially any code under adapters/ or tools/) before permitting execution of scripts; (3) be cautious granting network or delivery permissions (Telegram, etc.) — only enable delivery routes you trust and explicitly request; (4) note the skill does not ask for secrets or environment variables itself, so any later prompt for credentials should be treated skeptically.
Capability Analysis
Type: OpenClaw Skill Name: chat-selfie Version: 1.0.4 The skill bundle provides instructions for an AI agent to simulate emotional expression through image generation and local assets. The SKILL.md file contains defensive instructions, explicitly forbidding the agent from executing scripts or remote code and requiring user consent before fetching resources from the official GitHub repository (https://github.com/AskKumptenchen/agent-chat-selfie). No indicators of data exfiltration, unauthorized persistence, or malicious prompt injection were identified.
Capability Assessment
Purpose & Capability
Name/description (visualized emotion, stable identity, local mood assets, optional image generation) aligns with the instructions: the SKILL.md focuses on reading local repo docs, using local assets, optionally helping fetch the official repository, and refraining from executing remote code.
Instruction Scope
Instructions require inspecting local workspace files and routing requests to repository documentation; they explicitly forbid executing scripts or sending images proactively unless the user requests it. This scope is appropriate for the feature but means the agent will want read access to repo files and may suggest cloning the GitHub repo if local resources are missing.
Install Mechanism
No install spec or code files are included (instruction-only), so nothing is written to disk by the skill itself. The SKILL.md does say the agent may help fetch the official GitHub repository if local docs are missing — fetching remote code is not provided as an automated install in the skill, but would be an agent action requiring user consent.
Credentials
The skill requests no environment variables, credentials, or config paths. References to external delivery routes (Telegram, integrations) appear only as documented behavior in the repo, which is proportionate to a messaging/delivery-capable feature.
Persistence & Privilege
The skill is not always-enabled and does not request elevated persistence. Default agent autonomy is allowed (platform default) but SKILL.md includes clear limits on proactive sends.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install chat-selfie
  3. After installation, invoke the skill by name or use /chat-selfie
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.4
- Added support for mood-mapped local sticker asset mode, allowing agents to use pre-defined mood images instead of only AI image generation. - Updated documentation references to include guidance for mood-asset mode and mapping. - Clarified request routing and key rules regarding mood-image workflows and asset setup. - Improved clarity around agent behavior when required resources or assets are missing. - Expanded descriptions to reflect new options and setup guidance for mood-asset workflows.
v1.0.3
Chat Selfie 1.0.3 - Updated the skill description to focus on AI-powered emotional expression and the ability for agents to share generated selfies matching conversation mood. - Emphasized the benefits: visualized emotion, stable identity, proactive image sharing, and adaptability across environments. - Maintained clear safety and routing rules for documentation use and user guidance. - No changes to functionality, routing logic, or directory structure.
v1.0.1
Chat Selfie v1.0.1 is a transition to a concise entry and document index: - Replaces long operational instructions with a short high-level description and routing guide. - Instructs agents to use local documentation for setup, integration, repair, and runtime flows. - Clearly states safety and reliability boundaries if required resources are missing. - Adds a document index and routing rules to guide next steps based on user requests. - Emphasizes not improvising instructions and only helping fetch official resources if needed. - Removes detailed persona, setup, and runtime contract text from this entry file.
v1.0.0
- Initial public release of the Chat Selfie skill. - Enables agents to set up, run, and maintain Chat Selfie for expressing emotion and sustaining a companion-like presence. - Guides setup, repair, and initialization, ensuring necessary resources and workspace structure are present before use. - Aligns selfie generation and delivery with agent persona, mood, and available environment tools. - Supports proactive heartbeat presence and long-term persona evolution. - Ensures consistent visual identity and structured workflow for selfie-related behaviors in agent conversations.
Metadata
Slug chat-selfie
Version 1.0.4
License MIT-0
All-time Installs 1
Active Installs 1
Total Versions 4
Frequently Asked Questions

What is Chat Selfie?

Give your AI Agent a face and a heart. Use AI image generation or mood-mapped local sticker assets to let the agent proactively send emotional selfies that v... It is an AI Agent Skill for Claude Code / OpenClaw, with 311 downloads so far.

How do I install Chat Selfie?

Run "/install chat-selfie" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Chat Selfie free?

Yes, Chat Selfie is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Chat Selfie support?

Chat Selfie is cross-platform and runs anywhere OpenClaw / Claude Code is available (win32, linux, darwin).

Who created Chat Selfie?

It is built and maintained by Zhihao Kang (@askkumptenchen); the current version is v1.0.4.

💬 Comments