Available on GitHub
Felicity
Felicity’s writing skills help AI assistants revise prose while preserving the author’s meaning. I built separate Review and Write skills, drawing on pragmatics to examine evidence, relevance, common ground, and the force of a statement.
Review or revise
Review flags consequential gaps in meaning, reasoning, structure, and audience fit. Write drafts and revises prose while preserving supported claims, commitments, and the author’s voice. Both run in Codex and Claude Code.
The ideas behind the skills
Grice’s cooperative principle informs checks for evidence, appropriate detail, relevance, and clarity. Speech-act theory distinguishes stating a fact, making a request, and committing to an action. Both skills also examine common ground: what writer and reader can reasonably assume they share.