TokenPad
Building

Skill File Frontmatter Validator

Check a skill file will actually be selected before you wonder why it never fires.

Your input

114 characters6 lines0 tokensor drop a file

Skill ValidatorExact
0Token change
Token change0no change
Input tokens0what you pasted
Output tokens0what you would send
Token cost of this result
Output tokens0
As input$0.00
× 100K requests$0.00

Everything on this page runs in your browser. Nothing you paste is transmitted, because there is no server here to transmit it to.

Result
 

Skills fail silently

A broken skill does not error. It simply never triggers, and you conclude the mechanism does not work. That makes mechanical validation unusually valuable here — there is no other signal.

The most common cause is a description written as a title rather than a condition. "A tool for reviewing prompts" matches almost nothing, because nobody phrases a request that way.

The two halves have different economics

The description is always in context, on every request, whether or not the skill fires. It must be short and specific.

The body loads only when the skill triggers, so it can afford to be thorough. Getting this split wrong in either direction is what makes skills either useless or expensive.

Frequently asked questions

What makes a description good?
It states when to use the skill, in the words a user would actually type. "Use when the user asks to reduce token usage or estimate monthly API cost" beats "A cost analysis tool" by a wide margin.
Why does the name have to be a slug?
It is an identifier used in file paths and references. Spaces and capitals cause the same problems there as anywhere else in a toolchain.

More building tools