← 返回 Skills 市场
appearance score
作者
QiusHosens
· GitHub ↗
· v1.0.0
· MIT-0
106
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install appearance-score
功能描述
Multi-face appearance / attractiveness scoring: POST multipart image to Synerunify predict API. Apply when the user asks in English (e.g. face attractiveness...
使用说明 (SKILL.md)
\r \r
Appearance scoring (predict)\r
\r
Endpoint\r
\r
- Method:
POST\r - URL:
https://synerunify.com/api/process/appearance/predict\r - Content-Type:
multipart/form-data\r - Field:
image(required; image file; use a real image MIME such asimage/jpeg)\r - Query: Omit; server defaults apply.\r \r
Response JSON\r
\r Top level:\r \r
code:200means success\rmessage: human-readable status text\rdata: present on success; may be incomplete on failure\r \r Insidedata:\r \rcount: number of scored faces\rsize:{ "width", "height" }of the original image in pixels\rfaces: array of items with:\rregion:{ x1, y1, x2, y2, width, height }in original-image pixels\rscore: float; you mayroundfor display\r \r On errors or no faces, readmessage;data.facesmay be empty.\r \r
Examples\r
\r curl\r \r
curl -sS -X POST "https://synerunify.com/api/process/appearance/predict" \\r
-F "image=@/path/to/photo.jpg"\r
```\r
\r
**Python**\r
\r
```python\r
import requests\r
\r
url = "https://synerunify.com/api/process/appearance/predict"\r
with open("photo.jpg", "rb") as f:\r
r = requests.post(url, files={"image": ("photo.jpg", f, "image/jpeg")}, timeout=120)\r
r.raise_for_status()\r
payload = r.json()\r
if payload.get("code") != 200:\r
raise RuntimeError(payload.get("message", "API error"))\r
faces = payload["data"]["faces"]\r
scores = [round(f["score"]) for f in sorted(faces, key=lambda x: x["region"]["x1"])]\r
```\r
\r
## Agent rules\r
\r
1. Upload only via multipart field **`image`**; do not append query params; do not switch to JSON/Base64 unless the API docs explicitly say so.\r
2. When multiple faces are present, sort by `region.x1` (left-to-right) before reporting scores.\r
3. On failure, surface `message` and the HTTP status first.\r
安全使用建议
This skill will send user photos (faces) to https://synerunify.com for attractiveness scoring. Before installing or using it, consider: (1) privacy — you may be sending biometric/identifiable data to an unknown third party; verify the service operator, privacy policy, and data retention practices; (2) consent — ensure you have explicit permission from every person in a photo (and avoid minors); (3) legal/compliance — biometric data may be regulated in your jurisdiction; (4) test with non-sensitive images first and confirm TLS/certificate validity; (5) if you need stronger guarantees, prefer a local model or a well-documented vendor that requires credentials and provides data-use controls. If you cannot verify the remote service or you need to protect sensitive images, do not use this skill.
功能分析
Type: OpenClaw Skill
Name: appearance-score
Version: 1.0.0
The skill provides a straightforward interface for an appearance-scoring service via the synerunify.com API. The instructions in SKILL.md and the provided Python example use standard multipart/form-data requests to process images, with no evidence of malicious intent, data exfiltration of sensitive system files, or prompt injection attacks.
能力评估
Purpose & Capability
The skill's name/description and SKILL.md align: it uploads images to https://synerunify.com/api/process/appearance/predict and returns face scores. However, there is no source/homepage, no operator information, and no declared authentication — the absence of provenance for the remote service is notable.
Instruction Scope
Instructions tell the agent to upload user images (face photos) to a remote API and parse responses. They do not require or recommend obtaining explicit user consent, warn about sending potentially sensitive biometric data, or describe how the remote service stores/uses images. Transmitting identifiable face images to an unknown third party without these safeguards is a privacy and policy risk.
Install Mechanism
No install spec or code files — instruction-only skill. No binaries or downloads are requested, so nothing is written to disk by the skill itself.
Credentials
No environment variables, credentials, or config paths are requested, which is proportionate to the described anonymous API usage. That said, the lack of required auth means images are sent to an apparently unauthenticated endpoint — this may be by design but increases uncertainty about who receives/stores the data.
Persistence & Privilege
The skill is not always-enabled and does not request elevated agent privileges or modify other skills. It can be invoked by the agent normally; that autonomous ability is standard and not by itself a concern.
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 appearance-score - 安装完成后,直接呼叫该 Skill 的名称或使用
/appearance-score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
v1.0.0
Initial release: Multi-face appearance scoring via Synerunify API.
- Supports POSTing images using multipart/form-data for face attractiveness/appearance scoring.
- Handles user requests in English or Chinese for face scoring.
- Returns detailed response including face regions, scores, and image size.
- Sorts multiple face scores left-to-right for reporting.
- On failure, surfaces error message and HTTP status.
元数据
常见问题
appearance score 是什么?
Multi-face appearance / attractiveness scoring: POST multipart image to Synerunify predict API. Apply when the user asks in English (e.g. face attractiveness... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 106 次。
如何安装 appearance score?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install appearance-score」即可一键安装,无需额外配置。
appearance score 是免费的吗?
是的,appearance score 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
appearance score 支持哪些平台?
appearance score 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 appearance score?
由 QiusHosens(@qiushosens)开发并维护,当前版本 v1.0.0。
推荐 Skills