feat: add video description skill

[kweinmeister]

…ills

[gemini-code-assist]

Summary of Changes

Hello @kweinmeister, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request significantly enhances the AI agent capabilities by introducing a dedicated skill for generating optimized video descriptions. It provides a comprehensive framework including a structured generation workflow, platform-specific templates, illustrative examples, and robust validation and testing mechanisms to ensure the quality and relevance of the generated content.

Highlights

• New Video Description Skill: A new AI agent skill named video-description has been added, designed to generate optimized descriptions for video platforms from transcripts and supplementary materials.
• Structured Workflow and Guidelines: The skill includes a defined sequential workflow in SKILL.md that guides the AI agent through analyzing source material, determining the target platform, selecting templates, drafting descriptions with specific point-of-view and hashtag rules, and validating the output.
• Comprehensive Templates and Examples: A collection of markdown templates (TEMPLATES.md) for professional/technical, entertainment/educational, and product showcase videos, along with few-shot examples (EXAMPLES.md), are provided to ensure diverse and high-quality output styles.
• Robust Validation and Testing Framework: Python scripts (validate.py) were introduced to check generated descriptions against best practices (length, timestamps, links, hashtags, POV). A Pytest suite (test_validate.py) with evaluation cases (evaluations.json) ensures regression testing and semantic compliance.
• Updated Documentation: The main agents/skills/README.md has been updated to include the new video-description skill, along with detailed installation instructions for Gemini CLI, project-specific setups, and Google Antigravity.

Changelog

• agents/skills/README.md
  • Added video-description to the list of included skills.
  • Updated installation instructions to guide users on how to symlink or copy the new video-description skill.
  • Included a usage example for generating video descriptions.
• agents/skills/video-description/EXAMPLES.md
  • Added two detailed examples demonstrating how to generate video descriptions for technical educational content and industry insights, including input and expected markdown output.
• agents/skills/video-description/README.md
  • Created a new README file specifically for the video-description skill, outlining its purpose, contents, and associated scripts.
• agents/skills/video-description/SKILL.md
  • Defined the core workflow for the video-description skill, detailing steps from analyzing source material to validating the final description.
  • Specified guidelines for drafting descriptions, including using first-person singular point of view and limiting hashtags to exactly five.
• agents/skills/video-description/TEMPLATES.md
  • Added three markdown templates for different video types: Professional/Technical, Entertainment/Educational, and Product Showcase, to guide description generation.
• agents/skills/video-description/evaluations.json
  • Added JSON-formatted evaluation cases with queries and expected behaviors to test the video-description skill's performance and compliance.
• agents/skills/video-description/scripts/test_validate.py
  • Implemented a Pytest script to load evaluation cases, mock LLM responses, and assert that generated descriptions meet both technical validation and semantic expectations.
  • Included a mock_llm_generate function to simulate LLM output for testing purposes.
• agents/skills/video-description/scripts/validate.py
  • Developed a Python script to validate video descriptions based on criteria such as length, presence of timestamps, links, hashtag count, and point of view, returning errors and warnings.

Activity

• No specific activity (comments, reviews, progress updates) has been recorded for this pull request yet.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request introduces a new 'video-description' skill for the agent, which is a great addition. The skill is well-structured, including clear documentation, examples, templates, and evaluation files. The implementation of the validation and testing scripts is a good practice. I've identified a few areas for improvement in these scripts to enhance their robustness and usability, particularly in the validation logic and user feedback from the command-line tool. My comments focus on making the tests more reliable and the validation script more helpful for developers.

[kweinmeister]

/gemini review

[gemini-code-assist]

Code Review

This pull request adds a new 'video-description' skill, including documentation, templates, examples, and validation scripts. The implementation is comprehensive. I've identified a few issues in the new files, including a typo in an example, and some bugs in the Python scripts where validation messages are not being correctly handled or displayed. Addressing these will improve the quality and correctness of the new skill.

[kweinmeister]

/gemini review

[gemini-code-assist]

Code Review

This pull request introduces a new "video description" skill for the AI agent, complete with comprehensive documentation, examples, templates, and validation scripts. The overall structure is well-organized and the new skill is clearly documented. My review focuses on the Python validation script and its tests, where I've identified a few areas for improvement. I found a correctness bug in the hashtag validation logic that should be addressed. Additionally, I've provided suggestions to enhance the script's usability through better error handling and command-line feedback, and recommended adding more thorough unit tests to ensure the validation logic is robust against regressions.

[kweinmeister]

/gemini review

[gemini-code-assist]

Code Review

This pull request introduces a new and well-structured "video description" skill. The documentation, examples, templates, and validation scripts are comprehensive and clearly written. The overall implementation is solid, with good test coverage for the validation logic. I have a couple of suggestions to enhance the robustness of the test suite and simplify the validation logic for better maintainability.

[kweinmeister]

/gemini review

[gemini-code-assist]

Code Review

This pull request introduces a new 'video-description' skill for the agent, complete with documentation, templates, examples, and validation scripts. The overall structure is well-organized and comprehensive. My review focuses on improving the user-friendliness of the validation scripts and fixing some minor documentation formatting. I've identified a bug in the validation script where errors and warnings are not reported, and I've also pointed out several places where error handling and logging could be more informative for the user.

[kweinmeister]

/gemini review

[gemini-code-assist]

Code Review

This pull request introduces a new 'video-description' agent skill, complete with documentation, templates, examples, and validation scripts. The implementation is well-structured. My review includes a few suggestions to improve the clarity of the documentation by correcting list numbering in the main README, and to enhance the user-friendliness of the Python validation script by adding more descriptive error messages.