← Back to Skills Marketplace
Generate Image
by
Abigale-cyber
· GitHub ↗
· v1.0.1
· MIT-0
119
Downloads
0
Stars
1
Active Installs
2
Versions
Install in OpenClaw
/install content-system-generate-image
Description
Generate article companion images for the content factory pipeline. Use when Codex needs article images, infographic cards, inline visuals, or a PNG exported...
README (SKILL.md)
Generate Image
Generate the image asset for an article draft as an independent executor. On ClawHub, this skill is published as content-system-generate-image.
Quick Start
Run the default command:
.venv/bin/python -m skill_runtime.cli run-skill generate-image --input content-production/drafts/ai-content-system-article.md
Prepare Source Article
Start from an article markdown draft that already has a stable title, structure, and core message. Use the article content to infer the primary visual theme and the most useful image role, such as header art, infographic card, or inline supporting visual.
The default remote image backend is:
provider: openai
api base: https://new.suxi.ai/v1
model: nano-nx
This is meant for the 香蕉画图 endpoint, which is treated as an OpenAI-compatible image API.
Follow Generation Workflow
- Read the article draft and extract the topic, tone, and the strongest visualizable idea.
- Generate the preferred image through the shared runtime in
skills/generate-image/runtime.py. - Fall back to the local infographic renderer when external generation fails or is unavailable.
- Write the exported PNG to the pipeline output path. If
wechat-studiois involved, let the workbench decide whether and how to ingest the result.
Per-article overrides are supported through Markdown frontmatter fields:
image_providerimage_api_baseimage_model
Write Output
Write the primary exported file to:
content-production/ready/\x3Cslug>-img-1.png
Respect Constraints
- External image generation may fail because of network or API issues
- The skill injects its own provider, base URL, and default model at runtime instead of changing the global
md2wechatconfig - Users with an existing 香蕉制作平台 can use it directly
- Users without one can open job.suxi.ai, generate an
SK, place it into the token field, and log in - When fallback is used, the PNG is still valid but is a local placeholder-style information card
- Treat
content-production/ready/*.pngas the executor's exported artifact; any workbench copy should be managed bywechat-studio, not by this skill
Read Related Files
- Shared runtime:
skills/generate-image/runtime.py - Pipeline entry:
skill_runtime/engine.py - Visual workbench:
skills/wechat-studio/frontend/server.py - Execution guide:
docs/generate-image-execution-spec.md
Usage Guidance
This skill appears to perform the image-generation task described, but note two practical inconsistencies before installing: (1) runtime.py calls the 'md2wechat' CLI (subprocess) — ensure that binary is trusted and available on PATH, because the skill metadata does not declare it as required; (2) the skill defaults to a third-party image API base (https://new.suxi.ai/v1). If you will use that remote provider, confirm you are comfortable sending requests and (if needed) credentials to it. Provide any API token via your md2wechat config or an environment variable you control (e.g., IMAGE_API_KEY) rather than embedding secrets into the skill. If you need higher assurance, inspect or vet the md2wechat tool and the external provider (new.suxi.ai) and consider running the skill in an environment with restricted network access until reviewed.
Capability Analysis
Type: OpenClaw Skill
Name: content-system-generate-image
Version: 1.0.1
The skill is a functional tool for generating article images using a local CLI utility (md2wechat) and a specific third-party API (suxi.ai). While it utilizes potentially risky capabilities such as subprocess execution (runtime.py) and network requests for file downloads (urllib.request), these actions are strictly aligned with the stated purpose of image generation and asset management. No evidence of malicious intent, credential exfiltration, or unauthorized command execution was identified.
Capability Assessment
Purpose & Capability
The name/description align with the code: the skill extracts article frontmatter and generates/export a PNG. However the runtime invokes an external CLI ('md2wechat generate_image') as its primary backend while the skill metadata lists no required binaries. That implicit dependency on an external tool is an inconsistency a user should expect to resolve before use.
Instruction Scope
SKILL.md and runtime.py stay within the stated purpose: read the markdown draft, resolve provider/model (from frontmatter, request args, or defaults), call the generator, and write a PNG to content-production/ready/*.png. The instructions do not request unrelated files or secrets. They do instruct users how to obtain a token for the third-party service (job.suxi.ai), which is consistent with using an external image provider.
Install Mechanism
There is no install spec (lowest disk-write risk). But the runtime relies on invoking an external CLI ('md2wechat') via subprocess.run; if that tool is absent the skill will fail. The skill also fetches image bytes via urllib.request from provider URLs returned by the CLI. The lack of declared binary requirements is a mismatch with actual runtime behavior.
Credentials
The skill declares no required environment variables, yet README and runtime behavior expect tokens/config to be provided to the md2wechat CLI (e.g., IMAGE_API_KEY or existing md2wechat config). It injects IMAGE_PROVIDER/IMAGE_API_BASE/IMAGE_MODEL at runtime (not secrets). The default API base is a non-standard third-party host (https://new.suxi.ai/v1, '香蕉画图'), which means network calls and potentially credentialized access to that service — this should be explicitly acknowledged by an installer.
Persistence & Privilege
The skill does not request persistent 'always' privilege, does not install itself, and does not alter other skill configs. It writes output artifacts to the pipeline path as expected.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install content-system-generate-image - After installation, invoke the skill by name or use
/content-system-generate-image - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
Switch default image backend to Banana nano-nx and document SK login flow
v1.0.0
- Initial release of the generate-image skill for the content factory pipeline.
- Supports generating article companion images, including header art, infographic cards, and inline visuals.
- Reads article drafts to extract topic, tone, and visual themes for image generation.
- Falls back to a local infographic renderer if external image generation fails.
- Exports PNG images to the content-production/ready directory for workflow integration.
Metadata
Frequently Asked Questions
What is Generate Image?
Generate article companion images for the content factory pipeline. Use when Codex needs article images, infographic cards, inline visuals, or a PNG exported... It is an AI Agent Skill for Claude Code / OpenClaw, with 119 downloads so far.
How do I install Generate Image?
Run "/install content-system-generate-image" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Generate Image free?
Yes, Generate Image is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Generate Image support?
Generate Image is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Generate Image?
It is built and maintained by Abigale-cyber (@abigale-cyber); the current version is v1.0.1.
More Skills