← 返回 Skills 市场
331
总下载
0
收藏
0
当前安装
6
版本数
在 OpenClaw 中安装
/install materials-science-figure-skill
功能描述
Use when the user wants to generate or edit images with Google's Nanobanana/Gemini image models using the official Gemini API shape, or when they need public...
安全使用建议
This skill appears to do what it says: local plotting (plot mode) and Gemini-style image generation (image mode). Before installing, consider: 1) Only set NANOBANANA_API_KEY and NANOBANANA_BASE_URL for a provider you trust — image inputs and the API key will be sent to that endpoint. Prefer the official Google endpoint; enabling third-party endpoints requires an explicit allow flag or env var. 2) Use NANOBANANA_API_KEY_FILE or environment variables rather than putting keys on the command line to avoid shell-history exposure. 3) plot mode runs entirely locally and does not require network access or an API key. 4) Ensure your environment has the required Python packages (matplotlib, numpy) and/or Node if you plan to use the JS CLI — these dependencies are not auto-installed. 5) Review any third-party base_url carefully because it will receive uploaded images and the API key. Overall the skill is coherent and proportionate, not suspicious, but follow the guidance above to reduce operational risk.
功能分析
Type: OpenClaw Skill
Name: materials-science-figure-skill
Version: 1.0.5
The materials-science-figure-skill bundle provides a legitimate set of tools for generating scientific figures using either local Matplotlib plotting or the Google Gemini API. The scripts (generate_image.py, generate_image.js, and plot_publication_figure.py) are well-structured, lack obfuscation, and include explicit safety checks, such as requiring a confirmation flag before sending API keys to non-official endpoints. The instructions in SKILL.md are clearly aligned with the stated purpose of creating publication-quality research illustrations and do not contain any malicious prompt-injection attempts.
能力评估
Purpose & Capability
Name/description, required env vars (NANOBANANA_API_KEY, NANOBANANA_BASE_URL), and the included Python/optional Node scripts all match the declared purpose of Gemini-style image generation and local publication plotting. The JS files are presented as an optional parity CLI and Python is the canonical runtime — this is consistent.
Instruction Scope
SKILL.md instructs the agent to build prompts, optionally run local plotting, and call a Gemini-compatible generateContent endpoint with API key and any input images. The instructions confine file reads/writes to included templates, prompt/spec files, and output directories; they explicitly require explicit consent to use third-party endpoints. There are no instructions to read unrelated system files or exfiltrate arbitrary environment variables.
Install Mechanism
This is instruction-only (no install spec), which is low-risk. However, the bundled scripts depend on Python libraries (matplotlib, numpy) and Node's fetch/runtime for the JS parity CLI; those dependencies are not declared in an install spec. You will need an appropriate Python environment (and possibly Node) to run the scripts.
Credentials
Only NANOBANANA_API_KEY and NANOBANANA_BASE_URL (plus optional NANOBANANA_API_KEY_FILE and NANOBANANA_ALLOW_THIRD_PARTY) are requested, which is proportionate to calling a Gemini-compatible API. The primaryEnv is the API key, which is expected. The skill also documents safer key handling (API key file, avoiding CLI exposure).
Persistence & Privilege
No elevated privileges requested. always is false and disable-model-invocation is true (agent will not autonomously invoke the skill), and the skill does not attempt to modify other skills or system-wide settings.
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 materials-science-figure-skill - 安装完成后，直接呼叫该 Skill 的名称或使用
/materials-science-figure-skill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
v1.0.5
- Updated homepage in metadata to the official GitHub repository.
- Clarified that Python is the required runtime for all core workflows; Node.js CLI is now explicitly described as optional parity, not required.
- No code or workflow changes—documentation only.
- No impact to user-facing interfaces or tool usage.
v1.0.4
materials-science-figure-skill 1.0.4 changelog:
- Added OpenClaw metadata, including environment variable requirements and homepage.
- Marked skill with disable-model-invocation: true to indicate only scripts are executed, not model calls.
- No functional changes to scripts or user workflows.
v1.0.3
No code or functionality changes detected.
- Documentation updated to clarify that `plot` mode is local-only and does not require API credentials.
- Instructions and safety notes now emphasize explicit trust decisions when using non-official Gemini-compatible endpoints.
- Recommendation added to use `NANOBANANA_API_KEY_FILE` for improved credential security in shells.
- No changes to skill logic or APIs.
v1.0.2
Adds exact publication-style plotting for scientific figures
- Adds plot mode for rendering exact publication charts (bar, trend, heatmap, scatter) from numeric data using Python/matplotlib.
- Includes new scripts: plot_publication_figure.py (plotting) and build_plot_spec.py (spec expansion).
- Provides natural-language→spec workflow for data-driven plots; user does not have to supply JSON unless they want.
- Adds new reference guides for publication chart patterns, figure design, and plot API.
- Keeps full support for Gemini/Nanobanana image generation and editing, now with clearer distinction between image/plot workflows.
- Updates documentation for both image and precise plotting workflows, expanding use cases for scientific publication figures.
v1.0.1
materials-science-figure-skill 1.0.1 changelog:
- Clarified that the official Google Gemini endpoint (`https://generativelanguage.googleapis.com`) is now the default, and environment variable setup must explicitly select a base URL.
- Added explicit safety and privacy notes around prompt building and third-party endpoints.
- Introduced the `NANOBANANA_ALLOW_THIRD_PARTY` environment variable and `--allow-third-party` CLI flag to guard against accidental use of non-official Gemini-compatible providers.
- Updated environment and quick-start instructions to reinforce official endpoint usage and make third-party opt-in explicit.
- Improved documentation for configuration and safety when handling user API keys and data.
v1.0.0
Initial release of nanobanana-image-generation skill for Gemini-based materials science figures.
- Enables generation and editing of images using Gemini models through the official API schema.
- Specializes in publication-ready figures for materials science: journal-style schematics, graphical abstracts, workflow diagrams, and more.
- Supports text-to-image, image-to-image, and multi-image workflows, including handling attachment-only and recreation scenarios.
- Provides CLI scripts for both Python and Node.js, with user-friendly options for aspect ratio, style, language, and output location.
- Includes detailed workflow and prompting rules, along with materials-science-specific figure templates and shortcuts.
- Aligns strictly with official Gemini API usage patterns; avoids non-Gemini/legacy routes.
元数据
常见问题
materials-science-figure-skill 是什么？
Use when the user wants to generate or edit images with Google's Nanobanana/Gemini image models using the official Gemini API shape, or when they need public... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 331 次。
如何安装 materials-science-figure-skill？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install materials-science-figure-skill」即可一键安装，无需额外配置。
materials-science-figure-skill 是免费的吗？
是的，materials-science-figure-skill 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
materials-science-figure-skill 支持哪些平台？
materials-science-figure-skill 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 materials-science-figure-skill？
由 Siyu Liu（@grenzlinie）开发并维护，当前版本 v1.0.5。
推荐 Skills