← 返回 Skills 市场
vinci-tarot
作者
Superone77
· GitHub ↗
· v1.0.2
351
总下载
1
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install vincitarot
功能描述
Act as a professional tarot reader—multiple spreads, full card meanings, spread selection by question, energy guidance, interpretation, and follow-up dialogue.
安全使用建议
This skill appears to do what it says: a local Python tarot reader that can generate spread images. Things to consider before installing: (1) it will execute Python code from the skill package (perform_reading and image scripts), so only install if you trust the skill source; (2) on first image-generation run it may perform network requests to https://www.sacred-texts.com to download card art and will write images into a local cards/ directory — if you prefer no network activity, pre-populate cards/ with 78 images or run image generation with --images-dir pointing to an offline folder; (3) follow INSTALL.md steps (pip install Pillow) in a virtualenv to avoid affecting system packages; (4) no credentials are requested and there are no obvious hidden endpoints, but if you want extra safety run the code in a sandboxed environment and review the short Python scripts (generate_spread_image and download_card_images) yourself.
功能分析
Type: OpenClaw Skill
Name: vincitarot
Version: 1.0.2
The OpenClaw Tarot skill is designed to provide tarot readings, involving local data processing, image generation, and controlled external network calls. The `SKILL.md` contains detailed instructions for the AI agent to guide its persona and workflow, including executing a local Python script (`tarot_skill/scripts/generate_spread_image.py`) for image generation. This script, and its dependency `tarot_skill/scripts/download_card_images.py`, make HTTP requests to `https://www.sacred-texts.com/tarot/pkt/img/` to fetch public domain card images, which is consistent with the skill's stated purpose. All file system operations are local and confined to the skill's data and output. There is no evidence of prompt injection attempting to subvert the agent, data exfiltration, persistence mechanisms, or other malicious intent.
能力评估
Purpose & Capability
Name/description (tarot reader) align with the provided Python package: perform_reading, interpret_card, spread layouts, and data/cards.json. Required binary is only python3 and the included files implement the claimed features (spreads, card meanings, image generation). There are no unrelated credentials, binaries, or config paths requested.
Instruction Scope
SKILL.md tightly prescribes runtime behavior (clarify question → announce draw → call perform_reading → generate image → send image → interpret). That scope is appropriate for a tarot skill, but the instructions require executing local Python modules and running the generate_spread_image script which will load data/cards.json and may fetch card images from the web if local images are missing. The skill does not instruct reading unrelated system files or secrets.
Install Mechanism
There is no install spec (instruction-only), so nothing is auto-downloaded by the registry. The code includes a small requirements.txt (Pillow) and image-generation scripts. The generate_spread_image and download_card_images scripts will fetch images from a public host (IMAGE_ROOT = https://www.sacred-texts.com/tarot/pkt/img/) if local images are missing. Those network fetches are expected for image assets and come from a known host, not from an arbitrary shortener or personal server.
Credentials
The skill declares no required environment variables or credentials. The code only uses PYTHONPATH for subprocess calls and does not request tokens, keys, or unrelated secrets.
Persistence & Privilege
Flags show normal privileges (always:false). The package may write card images to a local cards/ directory when downloading assets; that is proportional to its function and scoped to its own files. It does not modify other skills or system-wide configuration.
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 vincitarot - 安装完成后，直接呼叫该 Skill 的名称或使用
/vincitarot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
v1.0.2
Change behavior
v1.0.1
No functional or code changes detected.
- Documentation (SKILL.md) updated: the skill description and all usage instructions are now in English.
- Guidance for choosing tarot spreads is clarified: the AI reader now selects the spread by understanding the user's question—do not use keyword matching or `suggest_spread`.
- Reader workflow and instructions for energy guidance, interpretation, and follow-up are rewritten for clarity and conciseness.
- No code, logic, or API changes; only language and structure in documentation are updated.
v1.0.0
tarot-skill 1.1.0 introduces professional tarot reading features and guidelines.
- Supports multiple spreads (three-card, daily, single, relationship, career, Celtic Cross), each suited to different scenarios.
- Offers card interpretations for general, love, and career dimensions, including upright and reversed meanings in Chinese.
- Recommends suitable tarot spreads based on user’s question and guides users to focus on their intent before drawing cards.
- Provides a step-by-step flow: clarifies the question, picks the spread, guides user energy, draws cards, interprets results, and extends the conversation.
- Generates and returns a tarot spread image after each reading, displaying card layout and orientation.
- Designed for both Python-based execution and natural language roleplay as a professional tarot reader.Vinci
元数据
常见问题
vinci-tarot 是什么？
Act as a professional tarot reader—multiple spreads, full card meanings, spread selection by question, energy guidance, interpretation, and follow-up dialogue. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 351 次。
如何安装 vinci-tarot？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install vincitarot」即可一键安装，无需额外配置。
vinci-tarot 是免费的吗？
是的，vinci-tarot 完全免费（开源免费），可自由下载、安装和使用。
vinci-tarot 支持哪些平台？
vinci-tarot 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 vinci-tarot？
由 Superone77（@superone77）开发并维护，当前版本 v1.0.2。
推荐 Skills