Add Azard/skypool plugin v0.0.1

[Azard]

Plugin Submission Form

1. Metadata

• Plugin Author: Azard
• Plugin Name: skypool
• Repository URL: https://github.com/Azard/dify-plugin-skypool

2. Submission Type

• New plugin submission
• Version update for existing plugin

3. Description

Skypool is a Dify model provider plugin for the Skypool OpenAI-compatible API. It lets Dify users call Skypool chat models with a Skypool Consumer API key and the default endpoint https://a.skypool.xyz/v1.

The Model Provider plugin includes predefined Skypool chat models, streaming output, and tool calling support for compatible models. It is useful for teams that want to route Dify apps, workflows, and agents through Skypool's hosted model gateway while keeping model configuration inside Dify.

4. Checklist

• I have read and followed the Publish to Dify Marketplace guidelines
• I have read and comply with the Plugin Developer Agreement
• I confirm my plugin works properly on both Dify Community Edition and Cloud Version
• I confirm my plugin has been thoroughly tested for completeness and functionality
• My plugin brings new value to Dify

5. Documentation Checklist

• Step-by-step setup instructions
• Detailed usage instructions
• All required APIs and credentials are clearly listed
• Connection requirements and configuration details
• Link to the repository for the plugin source code

6. Privacy Protection Information

Data Collection

The plugin transfers:

• User prompts, conversation context, model parameters, and tool definitions from Dify to the configured Skypool API endpoint for model inference
• Files or multimodal request data only when the user includes them in a Dify model request and the selected model flow supports that input
• Request metadata needed by Skypool for authentication, usage accounting, billing, rate limiting, and operational logs

The plugin stores only provider credentials inside Dify's credential storage. It does not persist prompts, model outputs, files, or API responses in the plugin runtime. The plugin does NOT transfer Dify workspace API keys or workspace member identities to Skypool. Full details are in PRIVACY.md, bundled in the .difypkg.

Privacy Policy

• I confirm that I have prepared and included a privacy policy in my plugin package based on the Plugin Privacy Protection Guidelines

[crazywoola]

✅ LGTM

Decision: Approve

Local Check Results

Check	Status	Detail	Required action
PR content language	✅ Pass	PR title/body CJK ratio=0.0% (zh=0, en=1948, ignored_zh=0, allowed_zh<=0)	None.
Project structure	✅ Pass	All expected files present: manifest.yaml, README.md, PRIVACY.md. _assets/: yes.	None.
Manifest author	✅ Pass	author is valid.	None.
Icon validation	✅ Pass	icon exists: _assets/icon.png	None.
Version check	✅ Pass	version 0.0.1 is available.	None.
README language	✅ Pass	README.md CJK ratio=0.0% (zh=0, en=932, allowed_zh<=0)	None.
PRIVACY.md	✅ Pass	PRIVACY.md exists and is non-empty.	None.
Dependency install	✅ Pass	requirements installed successfully.	None.
dify_plugin version	✅ Pass	dify_plugin version 0.9.0 satisfies >= 0.5.0.	None.
Install test	✅ Pass	plugin install test passed.	None.
Packaging test	✅ Pass	packaging check passed.	None.

[crazywoola]

✅ LGTM

Decision: Approve

Local Check Results

Check	Status	Detail	Required action
PR content language	✅ Pass	PR title/body CJK ratio=0.0% (zh=0, en=1948, ignored_zh=0, allowed_zh<=0)	None.
Project structure	✅ Pass	All expected files present: manifest.yaml, README.md, PRIVACY.md. _assets/: yes.	None.
Manifest author	✅ Pass	author is valid.	None.
Icon validation	✅ Pass	icon exists: _assets/icon.png	None.
Version check	✅ Pass	version 0.0.1 is available.	None.
README language	✅ Pass	README.md CJK ratio=0.0% (zh=0, en=932, allowed_zh<=0)	None.
PRIVACY.md	✅ Pass	PRIVACY.md exists and is non-empty.	None.
Dependency install	✅ Pass	requirements installed successfully.	None.
dify_plugin version	✅ Pass	dify_plugin version 0.9.0 satisfies >= 0.9.0.	None.
Install test	✅ Pass	plugin install test passed.	None.
Packaging test	✅ Pass	packaging check passed.	None.

[Azard]

@crazywoola Hi, could you please help take a look at the failing Pre Check Plugin workflow?

The PR itself appears mergeable, and the failed job is pre-check-plugin at the Check Plugin Install step:

https://github.com/langgenius/dify-plugins/actions/runs/26350267625/job/77994485746?pr=2453

From the job log, the workflow installs the plugin dependencies, but then the dify_plugin version detection returns an empty value:

Found dify_plugin version:
packaging.version.InvalidVersion: Invalid version: ''
Using aws_lambda installation method

Because of that, the workflow falls back to INSTALL_METHOD=aws_lambda. The installed dify_plugin runtime now validates INSTALL_METHOD and only accepts local, remote, or serverless, so the plugin install test fails with:

pydantic_core.ValidationError: 1 validation error for DifyPluginEnv
INSTALL_METHOD
Input should be 'local', 'remote' or 'serverless' [type=enum, input_value='aws_lambda', input_type=str]

The submitted package only contains requirements.txt with dify_plugin>=0.5.0; it does not explicitly set INSTALL_METHOD=aws_lambda. This looks like a CI workflow compatibility issue in the version-detection/fallback logic rather than a plugin package validation issue.

Could the pre-check workflow be updated to detect the installed dify_plugin version reliably, for example via Python package metadata, and use INSTALL_METHOD=serverless for the current runtime?