← 返回 Skills 市场
itsmebasil

Pattern

作者 itsmebasil · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
214
总下载
1
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install pattern-skills
功能描述
Automates jewellery product marketing using Google Vertex AI (Gemini and Imagen) and Google Drive.
安全使用建议
Do not install or provide credentials until the developer clarifies and fixes inconsistencies. Ask the maintainer to: (1) confirm which LLM will be used (Gemini vs Anthropic) and update SKILL.md/manifest to declare the exact provider and required env vars; (2) explicitly list all required environment variables and minimum permissions (e.g., service account limited to drive.file only, and the exact DRIVE_FOLDER_ID usage); (3) explain the Redis dependency and whether a local/managed Redis is required; (4) ensure the service account has least-privilege (no broader GCP roles) and confirm whether uploaded files are shared publicly or remain private; (5) consider shortening cache TTL and documenting what personal data is retained; and (6) if you must supply keys, run the skill in an isolated environment and rotate credentials after testing. These steps reduce the risk of unintended data exposure caused by the undeclared Anthropic key and service-account usage.
功能分析
Type: OpenClaw Skill Name: pattern-skills Version: 1.0.0 The skill bundle is a legitimate automation tool for jewellery marketing, integrating Anthropic Claude, Google Vertex AI (Gemini/Imagen), and Google Drive. Analysis of the Python code (jewellery_openclaw_skill.py) and pipeline configuration (jewellery_openclaw_skill.json) shows no signs of malicious intent, data exfiltration, or unauthorized command execution. The workflow is consistent with the documentation provided in SKILL.md and the architectural diagram in the HTML file.
能力评估
Purpose & Capability
SKILL.md and the JSON manifest describe using Google Vertex AI Gemini for text and Imagen for images. The Python implementation, however, uses AsyncAnthropic (Claude) for prompt/content generation while still using vertexai for image generation and Google Drive for storage. The presence of an Anthropic API key in the code is not justified by the declared purpose and registry metadata (which claim no required env vars).
Instruction Scope
The runtime instructions (prompt generation → Imagen → Drive upload → caching) are coherent for a jewellery-marketing pipeline. However SKILL.md and registry omit operational details the code relies on (Redis cache, service-account based Drive access, and an LLM provider). The pipeline downloads arbitrary image URLs, hashes them, caches results for 30 days, and uploads outputs to Drive — all expected for the described workflow but not fully declared.
Install Mechanism
No install spec is provided (instruction-only skill), which limits install-surface risk. A runnable FastAPI worker is bundled as source, so deploying it will require installing dependencies and running code; the package doesn't declare how to install those dependencies, which is an operational omission but not an immediate install-time red flag.
Credentials
Registry/skill metadata say 'required env vars: none', but the code expects multiple environment variables: ANTHROPIC_API_KEY, GOOGLE_APPLICATION_CREDENTIALS (service account JSON path), REDIS_URL, GCP_PROJECT_ID, GCP_LOCATION, and optional DRIVE_FOLDER_ID. Requiring a Google service account (drive.file scope) is reasonable for Drive uploads, but requiring an Anthropic API key contradicts the stated use of Gemini and is disproportionate/unexplained.
Persistence & Privilege
The skill uses persistent state: a 4-field memory map (style, tone, background_preference, top_performing_caption) and a 30-day cache in Redis keyed by image hash. always is false and the skill does not modify other skills, but persisted caching and Drive uploads mean it will retain and publish user-provided image/text outputs — review retention, access controls, and Drive share settings before enabling.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install pattern-skills
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /pattern-skills 触发
  4. 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
Pattern Jewellery Automation Skill - Initial Release (v1.0.0) - Automates luxury jewellery product marketing workflows using Google Vertex AI (Gemini & Imagen) plus Google Drive integration. - Accepts raw product image and details, generates lifestyle/model and studio product images, and crafts SEO-optimized captions and hashtags. - Organizes all output assets systematically within Google Drive folders based on product metadata. - Implements persistent memory for style, tone, background, and caption optimization. - Includes intelligent caching to avoid redundant Vertex AI calls and save resources.
元数据
Slug pattern-skills
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Pattern 是什么?

Automates jewellery product marketing using Google Vertex AI (Gemini and Imagen) and Google Drive. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 214 次。

如何安装 Pattern?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install pattern-skills」即可一键安装,无需额外配置。

Pattern 是免费的吗?

是的,Pattern 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Pattern 支持哪些平台?

Pattern 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 Pattern?

由 itsmebasil(@itsmebasil)开发并维护,当前版本 v1.0.0。

💬 留言讨论