← 返回 Skills 市场

doc-illustration-by-gpt-image-2

Name: doc-illustration-by-gpt-image-2
Author: eriklee1895

作者 Erik Lee · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ⚠ suspicious

总下载

当前安装

版本数

在 OpenClaw 中安装

/install doc-illustration-by-gpt-image-2

功能描述

Generate technical-document illustrations, design-note infographics, and repo architecture visuals using OpenAI GPT Image 2. Use when agent needs to turn AI...

使用说明 (SKILL.md)

Doc Illustration

Use this skill to create polished illustrations for technical writing.

Quick workflow

Identify the illustration type:
- architecture diagram
- process diagram
- knowledge card
- repo or module relationship diagram
- technical infographic
Pick a style profile:
- default: flat-tech-infographic
- optional: flat-illustration, sketchnote, soft-tech-diagram, repo-architecture-clean
If the user supplied reference images, treat them as style guidance only.
Prefer document-friendly landscape output unless the user requests another ratio.
Prefer concise bilingual labels and short notes over paragraph-heavy copy.
If the user wants to inspect the prompt first, use --dry-run.
For live generation, run the bundled script.

Script

Use:

uv run scripts/generate_doc_illustration.py \
  --title "RAG Pipeline Overview" \
  --brief "Create a technical infographic showing ingestion, chunking, embedding, retrieval, reranking, and answer synthesis." \
  --style-profile flat-tech-infographic

Use --mode reference+text --reference-image \x3Cpath> when the new image should follow the style of one or more reference images.

Use --dry-run when the user wants the exact prompt and parameters without calling the API.

Default output settings:

--size auto for best compatibility with GPT image providers
--quality auto for high-fidelity default behavior without over-constraining the request
use --size doc-hd for an explicit landscape document illustration size (1536x1024)
use --size doc-2k for a 2K landscape document illustration size (2048x1152)
use --size doc-4k for a 4K landscape document illustration size (3840x2160)

Authentication

Read OPENAI_API_KEY from the current shell first.
Read OPENAI_BASE_URL from the current shell second.
If OPENAI_API_KEY is missing for a live generation run, prompt temporarily in an interactive shell or tell the user to export the environment variable.
Do not write credentials to disk.

Model selection

Use gpt-image-2 for official OpenAI and for https://aihubmix.com/v1.
Use openai/gpt-image-2 for https://api.ofox.ai/v1.
Default back to gpt-image-2 unless a provider requires a namespaced model name.

References

Read references/style-profiles.md when selecting or explaining styles.
Read references/prompt-patterns.md when the requested illustration type needs prompt refinement.
Read references/openai-image-workflow.md when debugging auth, request modes, or output behavior.
Read references/openai-official-links.md when you need the official OpenAI docs for GPT Image, Images API, or Python examples.

安全使用建议

Before installing or running this skill: (1) Be aware you must provide an OPENAI_API_KEY (and optionally OPENAI_BASE_URL) at runtime — the registry metadata incorrectly omits these. (2) Review the script locally: it depends on the OpenAI Python client and will open and transmit any reference images you pass (they will be uploaded to the image provider). (3) The tool saves a JSON sidecar containing the prompt and metadata — avoid including secrets or confidential content in prompts if you don't want them written to disk or transmitted. (4) The script's shebang points at a developer-local path — consider running the script with your own python environment (and inspect/adjust the shebang if needed). (5) Use --dry-run first to inspect the exact prompt and payload without making live API calls, and test in a controlled environment or sandboxed account if you will submit sensitive images or prompts. If you need to proceed broadly: update the registry metadata to list OPENAI_API_KEY/OPENAI_BASE_URL explicitly, and confirm the OpenAI-compatible gateway URL is trustworthy before supplying credentials.

功能分析

Type: OpenClaw Skill Name: doc-illustration-by-gpt-image-2 Version: 1.0.0 The skill bundle is a legitimate tool for generating technical illustrations using the OpenAI API. The Python script (scripts/generate_doc_illustration.py) correctly handles API authentication via environment variables or interactive input without storing credentials on disk. The documentation (SKILL.md and references/) provides clear instructions for the agent and emphasizes secure practices, such as avoiding the modification of shell configuration files. While the script contains a hardcoded shebang path specific to a local environment, there is no evidence of malicious intent, data exfiltration, or unauthorized execution.

能力标签

requires-sensitive-credentials

能力评估

ℹ Purpose & Capability

The name, description, SKILL.md, and included Python script consistently implement an OpenAI GPT Image 2-based illustration generator. However the registry metadata says 'Required env vars: none' while the runtime explicitly expects OPENAI_API_KEY (and optionally OPENAI_BASE_URL). That mismatch is an inconsistency in the package metadata (not necessarily malicious, but important).

✓ Instruction Scope

Runtime instructions and the script remain within the advertised purpose: they build prompts, optionally include reference images as style guidance, call the Images generate/edit APIs, and save PNG + JSON sidecar. The SKILL.md does not instruct the agent to read unrelated files or system secrets beyond the OpenAI credentials. It does, however, instruct saving prompts and metadata to disk (see output sidecar).

ℹ Install Mechanism

There is no install spec (instruction-only), which minimizes install-time risk. The bundled script documents a dependency on the openai Python package but does not autoinstall it. Minor oddity: the script's shebang references a user-specific path ('/Users/eriklee/.local/bin/uv run'), which is likely a leftover from the developer environment and should be reviewed but is not by itself malicious.

⚠ Credentials

The skill requires an OpenAI API key (OPENAI_API_KEY) and optionally OPENAI_BASE_URL at runtime, which are proportionate to image generation. The problem: registry metadata claims no required env vars, creating a blind spot for automated permission reviews. Also note the script will optionally prompt for a temporary key in an interactive session and explicitly writes 'do not write credentials to disk' — but the JSON sidecar stores the generated prompt and metadata (which can include sensitive content), and reference image files are opened and uploaded to the image provider during reference+text mode (so local images will be transmitted).

✓ Persistence & Privilege

The skill is not always:on, does not claim elevated platform privileges, and does not alter other skills. It will write generated PNGs and JSON sidecar files to an output directory (normal for this functionality). It does not persist API keys to disk per the docs.

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 doc-illustration-by-gpt-image-2
安装完成后，直接呼叫该 Skill 的名称或使用 /doc-illustration-by-gpt-image-2 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 doc-illustration-by-gpt-image-2 — a tool to generate polished technical-document illustrations using OpenAI GPT Image 2. - Supports architecture and process diagrams, infographics, repo/module relationship visuals, and knowledge cards. - Allows style customization via predefined style profiles and user-supplied reference images. - Provides both live image generation and dry-run prompt review workflows. - Includes flexible output sizing options optimized for technical documentation. - Handles authentication via environment variables, with interactive fallback guidance. - Features provider-aware model selection and detailed reference/support documentation.

元数据

Slug doc-illustration-by-gpt-image-2

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