itsMay21

writing-for-the-reader

Writes durable text for the person who will use it rather than narrating the session that produced it. Use whenever creating or revising text that remains after the conversation.

DevOps & Infrastructure Listed

deciding-before-you-write

Establishes scope, evidence, uncertainty, and stopping conditions before an agent writes or edits. Use when a request is ambiguous, a change could spread, or several plausible actions compete.

API & Backend Listed

using-agent-expression

Routes agent writing, decision, and reasoning work to the smallest useful Agent Expression skill. Use before producing durable text or making a consequential edit.

writing-code-others-read

Writes simple, scoped code whose names and structure carry intent, with comments reserved for constraints only prose can express. Use when implementing, refactoring, reviewing, or documenting code.

writing-instructions-for-agents

Writes prompts, skills, rules, and agent instructions as compact current conduct rather than historical explanation. Use when creating or editing text that another agent will follow.

writing-plain-prose

Writes clear, concrete prose with human sentence rhythm, supported claims, and only the structure the reader needs. Use for explanatory and technical documents after the content is decided.

Writes product and interface text that helps users understand state, act, and recover while production history stays in its working record. Use for labels, headings, guidance, statuses, errors, empty states, and accessibility text.