agentleFS
Sign inStart free
Google CloudKnown publisherGoogleCloudPlatform/devrel-demos/agents/skills/video-description/SKILL.md

video-description

Skill397 starsChanged 9 days agoApache-2.0View on GitHub

Generates optimized descriptions for video platforms from transcripts and supplementary material. Use when the user asks for a video description or provides a transcript for video preparation.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Follow these steps to generate a high-quality description:

    line 12
  2. Distinctive:

    Analyze Source Material: Read the video transcript and any supplementary documents.

    line 14
  3. Distinctive:

    Draft Description: Create the description using the selected template.

    line 17
  4. Distinctive:

    Point of View: Always use first-person singular ("I", "my") instead of "we" or "our".

    line 18
  5. Distinctive:

    Relevance: Ensure the first few lines contain the most critical information and keywords.

    line 19
  6. Very specific:

    Validate: Run the scripts/validate.py script to ensure the description meets platform-agnostic formatting standards.

    line 22
  7. Very specific:

    Regression Testing: Run pytest scripts/test_validate.py to check performance against assets/evaluations.json.

    line 29

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Video Description

This skill helps you create engaging, platform-optimized video descriptions. It synthesizes information from a video transcript and any provided supplementary context (like a blog post or technical specifications).

Sequential Workflow

Follow these steps to generate a high-quality description:

  1. Analyze Source Material: Read the video transcript and any supplementary documents. Identify key topics, keywords, and calls to action.
  2. Determine Platform: Identify the target platform (e.g., YouTube, Instagram, TikTok). If not specified, default to a general SEO-friendly format.
  3. Select Template: Choose an appropriate template from TEMPLATES.md based on the video type and platform.
  4. Draft Description: Create the description using the selected template.
    • Point of View: Always use first-person singular ("I", "my") instead of "we" or "our".
    • Relevance: Ensure the first few lines contain the most critical information and keywords.
  5. Add Metadata: Include timestamps (if identifiable in the transcript), relevant links, and social CTA.
    • Hashtags: Limit to exactly 5 of the most relevant ones with broad appeal.
  6. Validate: Run the scripts/validate.py script to ensure the description meets platform-agnostic formatting standards.

Reference Materials

  • Templates: See TEMPLATES.md for standard formats and platform variations.
  • Examples: See EXAMPLES.md for few-shot examples.
  • Validation: Detailed rules in scripts/validate.py.
  • Regression Testing: Run pytest scripts/test_validate.py to check performance against assets/evaluations.json.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free