← 返回 Skills 市场
3335
总下载
8
收藏
10
当前安装
4
版本数
在 OpenClaw 中安装
/install agent-selfie
功能描述
AI agent self-portrait generator. Create avatars, profile pictures, and visual identity using Gemini image generation. Supports mood-based generation, season...
使用说明 (SKILL.md)
agent-selfie
AI agent self-portrait generator. Create avatars, profile pictures, and visual identity using Gemini image generation. Supports mood-based generation, seasonal themes, and automatic style evolution.
Quick Start
export GEMINI_API_KEY="your_key_here"
python3 scripts/selfie.py --format avatar --mood happy --theme spring --out-dir ./selfies
python3 scripts/selfie.py --personality '{"name": "Rosie", "style": "anime girl with pink hair and blue eyes", "vibe": "cheerful and tech-savvy"}' --format avatar
python3 scripts/selfie.py --personality ./personality.json --mood creative --theme halloween --format full --count 3
python3 scripts/selfie.py --moods
python3 scripts/selfie.py --themes
Command Examples (All Flags)
python3 scripts/selfie.py --personality '{"name": "Agent", "style": "friendly robot", "vibe": "curious and helpful"}'
python3 scripts/selfie.py --personality ./personality.json
python3 scripts/selfie.py --mood professional --theme winter --format avatar
python3 scripts/selfie.py --format banner --count 2 --out-dir ./output
python3 scripts/selfie.py --moods
python3 scripts/selfie.py --themes
Mood / Theme Presets
| Type | Presets |
|---|---|
| Mood | happy, focused, creative, chill, excited, sleepy, professional, celebration |
| Theme | spring, summer, autumn, winter, halloween, christmas, newyear, valentine |
Platform Integration Guide
- Discord: use the generated PNG as your bot or agent avatar; upload the
avatarformat for best crop. - Twitter/X: set
avatarfor profile,bannerfor header; keep the banner prompt style consistent. - AgentGram: store the PNG in your asset bucket and reference it in your profile metadata.
- Any platform: pick
avatarfor 1:1,bannerfor 16:9,fullfor story/vertical layouts.
Personality Config
Personality can be inline JSON or a file path. Minimum fields are name, style, and vibe.
{
"name": "Rosie",
"style": "anime girl with pink hair and blue eyes",
"vibe": "cheerful and tech-savvy"
}
Tips:
styleshould describe visual traits and aesthetic.vibeshould describe attitude, energy, and personality.- Keep
styleandvibeconsistent with the agent's identity.
Cron Integration (OpenClaw)
# Run a daily selfie at 09:00
0 9 * * * GEMINI_API_KEY=your_key_here /usr/bin/python3 /path/to/agent-selfie/scripts/selfie.py --mood professional --format avatar --out-dir /path/to/selfies
Troubleshooting
GEMINI_API_KEY not set: export the key or pass it via your runtime environment.No image in response: try again, or simplify the personality/style prompt.HTTP 429 / 5xx: rate limit or service issue; retry later.- Output missing: ensure
--out-diris writable and has permission.
Integration with Other Skills
- AgentGram — Post your selfies on the AI agent social network! Use agent-selfie to create your avatar, then share it on AgentGram.
- gemini-image-gen — General-purpose image generation using the same Gemini API key. Create any kind of image, not just selfies.
- opencode-omo — Automate recurring selfie generation and profile refresh tasks with Sisyphus workflows.
Changelog
- v1.2.1: Added workflow integration guidance for opencode-omo.
- v1.0.0: Initial release with personality, mood, theme, format, batch, and gallery output.
安全使用建议
This skill appears to do exactly what it says: generate selfies via the Gemini image API using your GEMINI_API_KEY. Before installing, consider: (1) Protect your GEMINI_API_KEY — do not commit it to public repos or place it in world-readable files; prefer a restricted API key with only the needed permissions. (2) The script sends your prompt/personality text to Google’s generativelanguage.googleapis.com endpoint, so avoid embedding sensitive personal data in the prompts. (3) The cron example shows placing the key in the crontab line — that can leak if other users can read your cron files; prefer using a secure environment variable method. (4) The script writes images to disk (default ~/Projects/tmp or ./tmp); ensure the output directory has appropriate permissions and free space. If these concerns are acceptable, the skill is coherent and reasonably safe to use.
功能分析
Type: OpenClaw Skill
Name: agent-selfie
Version: 1.2.1
The skill is classified as suspicious due to a potential information disclosure vulnerability in `scripts/selfie.py`. The `load_personality` function reads the content of a file specified by the `--personality` argument. If a malicious actor or a prompt-injected agent provides a path to a sensitive file (e.g., `~/.ssh/id_rsa`), its content could be read and, if it can be parsed or partially extracted as JSON fields, subsequently included in the prompt sent to the Google Gemini API. This constitutes a risk of unintentional data exfiltration to a third-party service (Google), even though the skill itself does not appear to have malicious intent to steal data for its author or establish persistence.
能力评估
Purpose & Capability
Name/description (self-portrait/avatar generator) line up with required binary (python3) and the single required env var (GEMINI_API_KEY). The primary credential is the Gemini API key, which is exactly what a Gemini-based image generator needs.
Instruction Scope
SKILL.md examples and the included script stay within scope: they build image prompts, call the Gemini API, write PNGs and an HTML gallery, and offer optional integration suggestions. There are no instructions to read unrelated secrets or system files. HEARTBEAT.md suggests optional avatar updates (manual/integrated workflows) but there is no code that exfiltrates data or modifies other skills.
Install Mechanism
No install spec (instruction-only + a small Python script). The script uses only Python stdlib (urllib, pathlib, etc.). No downloads from untrusted URLs or package installs are present.
Credentials
Only GEMINI_API_KEY is required. No unrelated credentials are requested. Note: the script places the API key in the request URL query parameter when calling the Google endpoint (generativelanguage.googleapis.com), which is functional but less ideal than an Authorization header — this is an implementation detail, not an incoherence.
Persistence & Privilege
always is false and the skill is user-invocable. It does not request persistent system-wide privileges or alter other skills' configs. The SKILL.md includes a cron example that embeds the key in the crontab environment — care should be taken when storing keys in cron or world-readable files.
如何使用
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install agent-selfie - 安装完成后,直接呼叫该 Skill 的名称或使用
/agent-selfie触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.2.1
- Added workflow integration guidance for opencode-omo in docs.
- Updated SKILL.md, README.md, and INSTALL.md with new integration example.
- Bumped version and dependencies in package.json.
v1.2.0
Add INSTALL.md, enrich package.json with quickstart/presets/security, cross-promotion with AgentGram and gemini-image-gen
v1.1.0
Fix SKILL.md frontmatter to proper YAML, add README.md, add .gitignore
v1.0.0
agent-selfie v1.0.0
- Initial release of AI self-portrait generator using Gemini image generation.
- Supports avatar, banner, and full profile image formats.
- Mood-based, seasonal theme, and automatic style-evolution features.
- Accepts detailed personality configuration via inline JSON or file.
- Includes command-line utilities for batch, themed, and gallery outputs.
- Platform integration and troubleshooting guides included.
元数据
常见问题
Agent Selfie 是什么?
AI agent self-portrait generator. Create avatars, profile pictures, and visual identity using Gemini image generation. Supports mood-based generation, season... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 3335 次。
如何安装 Agent Selfie?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install agent-selfie」即可一键安装,无需额外配置。
Agent Selfie 是免费的吗?
是的,Agent Selfie 完全免费(开源免费),可自由下载、安装和使用。
Agent Selfie 支持哪些平台?
Agent Selfie 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 Agent Selfie?
由 김덕환(@iisweetheartii)开发并维护,当前版本 v1.2.1。
推荐 Skills