"Skills, or Agent Skills for jargon maximalists, offer a way to instill Claude with specific knowledge that it may not possess in its distillation of training data. Anthropic has already deployed a few of them within Claude to handle common tasks like creating spreadsheets or presentations. Now, paying Claude customers - not the freeloader tier - can create Skills that suit their specific needs. Just make sure to subtract the labor that went into creating them when tabulating time saved by AI."
"A Skill consists of a directory with a SKILL.md file - a mix of YAML and Markdown - and possibly other resources such as text, scripts, and data. This turducken of instructions and executable code can be stored locally (~/.claude/skills/) or uploaded to the cloud for use with the Claude API. Claude's context window when loaded appends metadata from available Skills in the system prompt."
"Thereafter, when Claude is asked to carry out a relevant task, it will launch the appropriate skill by invoking the Bash tool to read the SKILL.md file. Once done, the model should have the data necessary to perform the desired task, such as interacting with content in a third-party application like Box or creating a PowerPoint presentation. The AI model will do so through a process Anthropic calls progressive disclosure."
Paying customers can author custom Agent Skills to give Claude explicit, application-specific abilities that general training may miss. A Skill is a directory centered on a SKILL.md file combining YAML and Markdown, and can include scripts, text, and data; it can be stored locally or uploaded for API access. Available Skill metadata is appended to Claude's system prompt, and the model invokes a Skill by calling a Bash tool to read SKILL.md. Claude loads Skill content progressively, retrieving only needed sections, then uses that information to perform tasks like filling forms, interacting with apps, or producing spreadsheets and presentations.
Read at Theregister
Unable to calculate read time
Collection
[
|
...
]