learn_skill

To generate reusable agent skills from conversation history, provide chat logs or meeting notes as input. The system parses the context, proposes a snake_case skill name, crafts a Japanese description, and saves a SKILL.md file with YAML frontmatter and Markdown body in a structured directory.

Yes, you can augment existing agent skills from chat workflows. The system appends new functionality to an existing SKILL.md file by parsing additional conversation context, thereby increasing the reusability of the skill for recurring tasks.

Automating routine task codification from meeting memos involves parsing recurring dialogue patterns to generate structured SKILL.md files. This process transforms project planning sessions and support dialogues into reusable agent skills with YAML frontmatter.

No specific dependencies are required to create and save SKILL.md files for workflow automation. The skill operates standalone to parse conversation context and generate files with YAML frontmatter and a Markdown body under a designated directory.

Generated agent skills use the SKILL.md format for skill management. Each file contains YAML frontmatter with metadata and a Markdown body describing the skill, utilizing snake_case naming conventions and Japanese descriptions for structured organization.