yt-skill-mcp-server

compile_cursor_skill

Formats extracted YouTube workflow steps into a Cursor Agent SKILL.md file with YAML frontmatter, turning video instructions into reusable agent skills.

Instructions

Format extracted video frameworks into a Cursor Agent SKILL.md file with YAML frontmatter.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "skillName": "<skillName>",
      "description": "<description>",
      "videoId": "<videoId>",
      "title": "<title>",
      "steps": "<steps>"
    },
    "name": "compile_cursor_skill"
  }
}

Input Schema

Name	Required	Description
`steps`	Yes	Ordered actionable steps extracted from the video
`title`	Yes	Title of the workflow
`videoId`	Yes	Source YouTube video ID
`skillName`	Yes	Kebab-case skill slug
`description`	Yes	One-line trigger description for the agent

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Nov 8, 2026

TDQS

C2.9/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden, and it discloses very little. It says the output is a SKILL.md file but never states where the file is written, whether an existing file is overwritten, whether a path is configurable, or what the tool returns on success. For a tool whose name implies file compilation/writing, these are material omissions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is a single efficient sentence with the action and target artifact front-loaded, and no filler. Its brevity is appropriate in form, though it comes at the cost of the missing details noted elsewhere rather than being tight but complete.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no annotations and no output schema, the description must explain the write behavior and result, and it does not. An agent cannot tell from this definition where the generated SKILL.md lands, whether it is safe to re-run, or what it gets back, which is a real gap for a 5-required-parameter file-producing tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all five parameters are already documented in the schema, which sets the baseline at 3. The description adds only a loose mapping ('extracted video frameworks' → the steps array) and no format or constraint details beyond the schema, such as kebab-case validity or step ordering expectations.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a concrete verb and output artifact: formatting extracted video frameworks into a 'Cursor Agent SKILL.md file with YAML frontmatter'. That is specific enough to distinguish it from the sibling fetch_youtube_transcript, which is evidently the upstream acquisition step. It stops short of naming that relationship explicitly, so it is clear but not fully differentiated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use or when-not-to-use guidance, and no stated prerequisite that the frameworks/steps must already be extracted (e.g. via fetch_youtube_transcript) before calling this. The phrase 'extracted video frameworks' hints at ordering, but the agent must infer it rather than being told.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server