prompts

Agent Skill Validator class

Write the class `LLM::Resources::AgentSkillValidator` in "./lib/LLM/Resources/AgentSkillValidator.rakumod" that has methods for validating the structure, format, and content an Agent Skill directory. 
If you have to refer to the Python package "skills-ref" -- see https://github.com/agentskills/agentskills/tree/main/skills-ref .

The reference behavior is deliberately narrow: extra files/directories are allowed, the body may be empty, and validation centers on SKILL.md plus its YAML metadata. I’ll expose both one-shot validation and separate structure/format/content methods, returning error-message arrays rather than throwing during normal validation.

LLM::Resources v0.0.3

Different subs and CLI scripts for specific but repeatable LLM-based workflows.

Authors

  • Anton Antonov

License

Artistic-2.0

Dependencies

DSL::Examples:ver<0.0.3+>Data::Importers:ver<0.1.7+>Data::Translators:ver<0.1.16+>Graph:ver<0.0.30+>Hash::Merge:ver<2.0.0>:api<2>JSON::Fast:ver<0.17+>LLM::Functions:ver<0.4.1+>LLM::Prompts:ver<0.2.5+>LLM::Graph:ver<0.0.10+>ML::NLPTemplateEngine:ver<0.1.8+>ML::FindTextualAnswer:ver<0.2.8+>Text::SubParsers:ver<0.1.2+>

Test Dependencies

Provides

  • LLM::Resources
  • LLM::Resources::AgentSkillValidator
  • LLM::Resources::DSLTranslation
  • LLM::Resources::Graphs

The Camelia image is copyright 2009 by Larry Wall. "Raku" is a trademark of the Yet Another Society. All rights reserved.

Built with Podlite — the markup and publishing tools behind this site.