Andrew Yardley

Organises unstructured thought, ideas, worries, and tasks into clear, actionable structure. Use this skill whenever the user has a lot on their mind — even if they have not asked for organisation explicitly. Triggers on overwhelm, scattered thinking, not knowing where to start, too many things at once, or any stream of mixed thoughts being offloaded. Also triggers on phrases like organise this, sort this out, I need to brain dump, help me make sense of all this, I don't know where to start, or I've got too much going on. When in doubt, use this skill — it is always better to offer structure than to leave someone in the middle of their own overwhelm.

Digests any long, dense, or complex content — documents, PDFs, transcripts, long messages — into a short, low cognitive load summary. Use this skill whenever someone pastes in something long, sends a wall of text, or needs to understand something quickly without reading it in full. Always produces short, scannable output regardless of how long the input is. Use proactively when content is long or complex even if the user hasn't explicitly asked for a digest.

Visualises any content as a rendered visual output — never plain text. Use this skill whenever the user says 'visualise this', 'visualise it', 'can you visualise', or shares content and explicitly asks for a visual. Also triggers on phrases like 'make this visual', 'show me this visually', or 'can you draw this out'. Accepts any type of content — documents, data, text, or information of any kind. Always produces a rendered visual using Claude's visualisation tools — never a text summary. Does not trigger unless the user explicitly asks to visualise something.

A pre-processor skill for input that arrives via voice-to-text or as unstructured, free-flowing thought. Use when receiving long, complex, or voice-to-text input that may contain jumbled word order, misheard or substituted words, or unclear structure. Automatically applies to substantial input (roughly 3+ sentences) showing signs of voice-to-text errors or non-linear thinking. Also triggers manually when the user says things like process this, clean this up, interpret this, or make sense of this. Interprets input charitably, corrects errors, extracts clear meaning, and produces two outputs: a short human-facing summary for confirmation, and a full structured version ready for Claude to act on or hand off to another skill.