← Back to Skills Marketplace
90
Downloads
0
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install pop-cam
Description
AI image generation in any visual style — photorealistic, cinematic, cartoon, illustration, and more. Transform photos or generate from text prompts via the...
Usage Guidance
This skill appears coherent, but before installing: ensure you trust https://www.pop-cam.com (the skill will ask you to provide and store an API token: POPCAM_API_TOKEN). Keep that token secret — anyone with it can use your credits. Be mindful that webhook usage requires a public HTTPS endpoint you control (if you provide one, results will be POSTed there). Confirm Pop-cam's pricing/credits and content policy because each generation costs credits and may be subject to terms. If you need higher assurance, verify the homepage, developer docs, and that the token behaves as described (pk_ prefix, shown once) before saving it into the agent environment.
Capability Analysis
Type: OpenClaw Skill
Name: pop-cam
Version: 1.3.0
The pop-cam skill is a standard API integration for image generation services. It uses the POPCAM_API_TOKEN environment variable to interact with the pop-cam.com domain via curl, supporting both text-to-image and image-to-image transformations. No evidence of data exfiltration, malicious execution, or prompt injection was found in SKILL.md or _meta.json.
Capability Tags
Capability Assessment
Purpose & Capability
Name/description (image generation) aligns with required pieces: a single POPCAM_API_TOKEN credential and use of curl to call pop-cam.com endpoints. Nothing requested is unrelated to generating images.
Instruction Scope
SKILL.md instructs only on authenticating with Pop-cam, submitting text-or-image payloads, using webhook or synchronous modes, and handling presigned download URLs. It does not instruct the agent to read unrelated files, harvest other environment variables, or call unexpected endpoints.
Install Mechanism
No install spec or external downloads — instruction-only skill. Required binary (curl) matches the provided curl examples. Low risk from installation.
Credentials
Only one required environment variable (POPCAM_API_TOKEN) is declared and used, which is appropriate for an API client. No unrelated secrets or config paths are requested.
Persistence & Privilege
Skill is not forced-always; autonomous invocation is allowed by default (expected). The skill does not request system-wide config changes or unusual persistent privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install pop-cam - After installation, invoke the skill by name or use
/pop-cam - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.3.0
Remove cartoon/illustration bias from all documentation and examples. The model supports any visual style — photorealistic, cinematic, cartoon, illustration, etc. — controlled entirely by the prompt. Added Prompt Tips section with style examples.
v1.2.0
Add presigned download_url to all API responses — fixes private R2 bucket access for external agents
v1.1.0
Add text-to-image generation: send prompt only, no image required. Add webhook async mode, auth-status endpoint, and machine-readable skill definition JSON.
Metadata
Frequently Asked Questions
What is Pop-cam NanoBanana?
AI image generation in any visual style — photorealistic, cinematic, cartoon, illustration, and more. Transform photos or generate from text prompts via the... It is an AI Agent Skill for Claude Code / OpenClaw, with 90 downloads so far.
How do I install Pop-cam NanoBanana?
Run "/install pop-cam" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Pop-cam NanoBanana free?
Yes, Pop-cam NanoBanana is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Pop-cam NanoBanana support?
Pop-cam NanoBanana is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Pop-cam NanoBanana?
It is built and maintained by petagit (@petagit); the current version is v1.3.0.
More Skills