agentsclimarketplace

Scope validator

Skill genfeedai/skills/bundles/platform-development/skills/scope-validator

Classify feature requests as Genfeed OSS Core or Cloud SaaS scope and explain the contribution or subscription path. Triggers on core vs cloud, OSS contribution, node scope, provider scope, and feature request triage.From its SKILL.md

Install
npx -y skills add genfeedai/skills --skill scope-validator

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

7.0 KB, ~1.7k tokens by cl100k_base, as published. Nobody here has run it

Scope Validator

Helps users and contributors understand whether a feature belongs in:

When This Activates

  • User asks "should this be in core or cloud?"
  • User wants to contribute a new node or feature
  • User requests social publishing features
  • User asks about RSS/Twitter/feed integration
  • Feature request triage
  • PR review for scope compliance

OSS Core Scope

Included Nodes (26 total)

Input Nodes (5)

NodeTypeDescription
Image InputimageInputUpload or reference an image
Audio InputaudioInputUpload an audio file (MP3, WAV)
Video InputvideoInputUpload or reference a video file
PromptpromptText prompt for AI generation
TemplatetemplatePreset prompt template

AI Nodes (7)

NodeTypeDescription
Image GeneratorimageGenGenerate images with nano-banana models
Video GeneratorvideoGenGenerate videos with veo-3.1 models
LLMllmGenerate text with meta-llama
Lip SynclipSyncGenerate talking-head video from image/video and audio
Voice ChangevoiceChangeReplace or mix audio track in a video
Text to SpeechtextToSpeechConvert text to natural-sounding speech
TranscribetranscribeConvert video or audio to text transcript

Processing Nodes (12)

NodeTypeDescription
ResizeresizeResize media to different aspect ratios using Luma AI
AnimationanimationApply easing curve to video
Video StitchvideoStitchConcatenate multiple videos
Video TrimvideoTrimTrim video to a specific time range
Frame ExtractvideoFrameExtractExtract a specific frame from video as image
Luma Reframe ImagelumaReframeImageAI-powered image outpainting
Luma Reframe VideolumaReframeVideoAI-powered video reframing
Topaz Image UpscaletopazImageUpscaleAI-powered image upscaling with face enhancement
Topaz Video UpscaletopazVideoUpscaleAI-powered video upscaling to 4K
Grid SplitimageGridSplitSplit image into grid cells
AnnotationannotationAdd shapes, arrows, and text to images
SubtitlesubtitleBurn subtitles into video using FFmpeg

Output Nodes (2)

NodeTypeDescription
OutputoutputFinal workflow output
PreviewpreviewPreview media with playback controls

Cloud-Only Nodes (EXCLUDED from OSS)

NodeTypeReason
Social PublishsocialPublishRequires OAuth integrations for 7 platforms
RSS InputrssInputContent aggregation is Cloud feature
Tweet InputtweetInputTwitter API dependency, feed feature
Tweet RemixtweetRemixDepends on tweet input, social-focused

Cloud-Only Providers (EXCLUDED from OSS)

ProviderReason
FAL.aiCloud-only provider
HuggingFaceCloud-only provider

OSS Provider: Replicate only

Validation Rules

Rule 1: Node Type Check

IF node.type IN [socialPublish, rssInput, tweetInput, tweetRemix]
THEN FAIL: "Node type '{node.type}' is Cloud-only. Use OSS alternatives or upgrade to Cloud."

Rule 2: Provider Check

IF node.provider IN [fal, huggingface]
THEN FAIL: "Provider '{node.provider}' is Cloud-only. OSS only supports Replicate."

Rule 3: Template Check

IF template contains Cloud-only nodes
THEN FAIL: "Template uses Cloud-only nodes. Remove: {cloud_nodes}"

Rule 4: Feature Request Check

IF request mentions [publish, social, twitter, rss, feed, youtube upload]
THEN WARN: "Social publishing and feed features are Cloud-only."

Validation Examples

Valid OSS Workflow

{
  "nodes": [
    { "type": "prompt" },
    { "type": "imageGen" },
    { "type": "videoGen" },
    { "type": "subtitle" },
    { "type": "output" }
  ]
}

✅ All nodes are within OSS scope.

Invalid OSS Workflow

{
  "nodes": [
    { "type": "rssInput" },
    { "type": "tweetRemix" },
    { "type": "socialPublish" }
  ]
}

❌ Contains Cloud-only nodes: rssInput, tweetRemix, socialPublish

Response Templates

When Cloud Feature Requested

The feature you're requesting ({feature}) is available in Genfeed Cloud.

OSS Core includes:
- 26 nodes for media generation and processing
- Replicate provider for AI models
- Visual workflow editor with queue-based execution
- Gallery asset management

For social publishing and content aggregation features,
consider upgrading to Genfeed Cloud: https://genfeed.ai/cloud

When Suggesting Alternatives

Instead of {cloud_feature}, consider these OSS alternatives:

1. {alternative_1}
2. {alternative_2}

These achieve similar results within the OSS scope.

Common Requests & Responses

"Can I publish to YouTube?"

Response: Social publishing is Cloud-only. In OSS, use the output node to export your video, then manually upload to YouTube.

"Can I fetch RSS feeds?"

Response: RSS/feed aggregation is Cloud-only. In OSS, use the prompt node with manually entered content, or the template node with predefined prompts.

"Can I use FAL.ai models?"

Response: FAL.ai is Cloud-only. OSS uses Replicate provider. Check if the model you need is available on Replicate.

"Can I remix tweets?"

Response: Tweet remix is Cloud-only. In OSS, use the llm node with a custom prompt to rewrite text in different tones.

Integration

When validating:

  1. Parse the request - Identify node types, providers, and features mentioned
  2. Check against scope - Compare with OSS node list
  3. Report violations - List all Cloud-only features found
  4. Suggest alternatives - Provide OSS workarounds when possible
  5. Link to Cloud - Mention upgrade path for full feature access

Quick Reference

OSS Node Types (26):
  Input:      imageInput, audioInput, videoInput, prompt, template
  AI:         imageGen, videoGen, llm, lipSync, voiceChange, textToSpeech, transcribe
  Processing: resize, animation, videoStitch, videoTrim, videoFrameExtract,
              lumaReframeImage, lumaReframeVideo, topazImageUpscale,
              topazVideoUpscale, imageGridSplit, annotation, subtitle
  Output:     output, preview

Cloud-Only (4):
  socialPublish, rssInput, tweetInput, tweetRemix

OSS Provider:
  replicate (only)

Cloud Providers:
  fal, huggingface

What ships with it: 2 files

1.8 KB alongside SKILL.md

Keep looking

Skills are one crate of 326,861. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.