design-language

Reviews a built interface against its stated design intent — naming how the thing reads before proposing a fix, ranking findings by severity, and treating removal as a first-class verdict. Refuses to critique without a written intent.

Documents every substantive commit into per-commit changelog files plus a rolling CHANGELOG index.

Mines a project for the decisions that were actually made and writes each as a numbered ADR with its evidence — asking when the "why" was never written down, and never inventing one.

Proposes three or four sourced angles worth posting from your material backlog and the record — each with its tension, its reader and its weakest point. Declines when nothing is worth a post yet.

Generates a new skill in this library's conventions — PRD, SKILL.md skeleton, plugin.json, marketplace entry, README row and website entry — from a short interview.

Generates three genuinely distinct design directions from a written visual direction — each committed to a named structural axis, each with its thesis, bet and risk — ending in a comparison matrix you judge by eye. Never records the verdict.

Interviews you into a short, structured design brief — problem, who feels it, jobs to be done, constraints, success criteria and non-goals — and marks what wasn't stated rather than inventing it.

Drafts per-platform copy from a sourced angle in your captured voice, decides how the post breaks into frames, and lists what it refused to claim and why. Never publishes.

Claude / Cursor-compatible agent skills, packaged as installable plugins. Includes handoff-generator for moving work between Claude.ai chat and Claude Code without losing context.

Scaffolds the posts tier and captures how your posts should sound — by interview plus real samples — with personal profiles gitignored by default. The skill ships a template and never a voice.