AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Image Generation

skill-giantclam-auto-viral-article-writer-image-generation · by GiantClam

This skill should be used when the user asks to "生成图片", "create image", "generate image", "AI画图", "draw", or wants direct image generation outside the article workflow. It uses the local image generation CLI and supports OpenAI-compatible, OpenAI official, and Gemini image providers.

No reviews yet
0 installs
10 views
0.0% view→install

Install

$ agentstack add skill-giantclam-auto-viral-article-writer-image-generation

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-giantclam-auto-viral-article-writer-image-generation)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
1mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Image Generation? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Image Generation

Use this skill for direct image creation or image edits when the user is not asking for the full article workflow.

Use This For

  • standalone image generation
  • reference-image-based restyling
  • provider-specific image runs using the local CLI

Do Not Use This For

  • full article production by itself
  • ViralKB research
  • hot topic collection

Inputs

  • prompt
  • output path
  • optional provider flags
  • optional reference image path
  • optional size, quality, and format overrides

Outputs

  • saved image file
  • provider-used summary
  • output path confirmation

Workflow

  1. Validate required inputs.
  2. Confirm any reference files exist.
  3. Choose the provider in this order unless the user overrides it:
  • OpenAI-compatible
  • OpenAI official
  • Gemini official
  1. Run tools/nanobanana_client.py with the minimal correct arguments.
  2. Return the saved image path.

Fallback Guidance

  • If one provider is unavailable, fall back to another configured provider when possible.
  • If no provider is configured, stop and ask for environment setup rather than guessing.
  • Do not hardcode private gateways, API keys, or provider-specific secrets in committed files.

References

  • references/provider-capabilities.md - provider differences and recommended usage

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.