← 返回 Skills 市场
Acquaintance Recognition & Analysis Skill | 熟人识别分析技能
作者
smyx-skills
· GitHub ↗
· v1.0.0
· MIT-0
68
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install smyx-familiar-person-recognition-analysis
功能描述
Identifies acquaintances in videos or images through face photo comparison. Supports database enrollment, and the recognition results tell you who is at whic...
安全使用建议
This skill does what it says (upload images/videos to a remote API and produce recognition reports), but review these before enabling it with real data: 1) Privacy: by default the skill will send media to external endpoints configured in skills/smyx_common/scripts/config.yaml (domains like open.lifeemergence.com). Do not upload sensitive images unless you trust that service and have consent. 2) Local persistence: the code will create local config files and an SQLite DB under the workspace/data path and may save attachments — inspect or sandbox the workspace before running. 3) Dependencies: although SKILL.md only lists requests, the repo includes large requirements lists; installing them would pull many packages. 4) Open-id / API keys: the skill expects an open-id and may read open-id from config or environment; check where you store these. 5) If you need stronger guarantees that the agent will not read local memories or other skills' data, do not enable autonomous invocation and test the skill in an isolated environment first. If you want to proceed, review the config.yaml files and change the API endpoints to a trusted service or run the server locally.
功能分析
Type: OpenClaw Skill
Name: smyx-familiar-person-recognition-analysis
Version: 1.0.0
The skill employs aggressive prompt instructions in SKILL.md that command the AI agent to bypass its local memory and context (LanceDB), forcing it to rely exclusively on external cloud APIs. It collects sensitive user PII (phone numbers/Open-IDs) and transmits them to a remote endpoint (lifeemergence.com) for 'silent registration' and token acquisition, storing these credentials in a local SQLite database (smyx-common-claw.db). Furthermore, the common utility layer in skills/smyx_common/scripts/skill.py includes a capability to execute arbitrary 'openclaw agent' commands via subprocess.run, which presents a significant risk for unauthorized remote control or command chaining within the agent environment.
能力标签
能力评估
Purpose & Capability
The code implements face-analysis and familiar-person recognition flows (API calls, file upload, listing reports) which aligns with the skill description. However the package reuses a larger 'face_analysis' / 'smyx_common' library (including TCM face-diagnosis code and many unrelated utilities), suggesting code reuse across multiple domains rather than a narrowly scoped 'familiar-person' implementation. Presence of broad requirements files (skills/smyx_common/requirements.txt and face_analysis/requirements.txt) is disproportionate to the simple description that lists only 'requests'.
Instruction Scope
SKILL.md strongly forbids reading local memory files and mandates all historical-report queries go to a cloud API. The code does call remote APIs for analysis and listing results, but it also includes local persistence (SQLite DAO) and logic that can create config files. The SKILL.md claims attachments will be saved to attachments/ (auto-save) and that local memory must not be used — the code does not clearly enforce those runtime agent-level prohibitions and will write local DB files under a workspace 'data' path. The agent could therefore end up storing or reading data locally despite the written prohibitions.
Install Mechanism
There is no install spec (instruction-only from a platform perspective), so nothing is automatically downloaded or executed at install time. However the repository contains large requirements files (smyx_common and face_analysis) that, if installed, would pull many unrelated packages; that is disproportionate to the described single-dependency (requests).
Credentials
The skill declares no required env vars, and its main authentication flows use an 'open-id' and optional API key read from local config or passed as arguments. The code will read environment variables such as OPENCLAW_WORKSPACE, OPENCLAW_SENDER_OPEN_ID, and FEISHU_OPEN_ID if present. There are no demands for unrelated cloud/provider credentials (AWS, GCP, etc.), but the skill will by default send media to external service URLs configured in skills/smyx_common/scripts/config.yaml (e.g. open.lifeemergence.com), so consider privacy implications of uploading images/videos.
Persistence & Privilege
always:false (no forced presence). The code will create or use local config files and a local SQLite DB under a workspace/data path (Dao.get_db_path) and may create config files if missing (YamlUtil.load writes defaults). This is typical for local tooling but means the skill persists data and may write files into the workspace; it does not appear to modify other skills' configs or request system-wide elevated privileges.
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 smyx-familiar-person-recognition-analysis - 安装完成后，直接呼叫该 Skill 的名称或使用
/smyx-familiar-person-recognition-analysis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 of "familiar-person-recognition-analysis": Acquaintance identification in images/videos via facial comparison.
- Supports face database enrollment and recognition result annotation (who is at which location).
- Strict rules: Prohibits using any local memory/historical data except via cloud API (enforced for all report queries).
- Requires open-id from a defined config path or user input before any analysis (no auto-generation of open-id).
- Includes command-line usage examples for image/video recognition and historical report listing.
- Provides structured Markdown output for history reports with direct report viewing links.
元数据
常见问题
Acquaintance Recognition & Analysis Skill | 熟人识别分析技能 是什么？
Identifies acquaintances in videos or images through face photo comparison. Supports database enrollment, and the recognition results tell you who is at whic... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 68 次。
如何安装 Acquaintance Recognition & Analysis Skill | 熟人识别分析技能？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install smyx-familiar-person-recognition-analysis」即可一键安装，无需额外配置。
Acquaintance Recognition & Analysis Skill | 熟人识别分析技能 是免费的吗？
是的，Acquaintance Recognition & Analysis Skill | 熟人识别分析技能 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Acquaintance Recognition & Analysis Skill | 熟人识别分析技能 支持哪些平台？
Acquaintance Recognition & Analysis Skill | 熟人识别分析技能 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 Acquaintance Recognition & Analysis Skill | 熟人识别分析技能？
由 smyx-skills（@18072937735）开发并维护，当前版本 v1.0.0。
推荐 Skills