Hunts complexity in the current diff and APPLIES the simplifications directly to the working tree, then verifies the build. Five angles: reuse (duplicate logic, hand-rolled stdlib, platform features), quality (React/TypeScript hygiene, over-memoisation, exhaustive-deps, any, CLAUDE.md/AGENTS.md violations), efficiency…
Audits web typography against 78 rules in 10 categories: font selection and @font-face setup, sizing and measure, punctuation, spacing and rhythm, hierarchy, alignment and layout, OpenType features, brand identity, typeface pairing, and display type. Reports file:line findings with concrete CSS/HTML fixes ordered by…
Designs, implements, reviews, debugs, and reverse-engineers UI motion, and finds where an interface is missing it: CSS transitions, keyframes, springs, gestures, drag, easing, timing, framer-motion, and animation curves from screen recordings. Use when asked to "add animations", "make this feel smooth", "review my…
Designs, builds, and audits UI in React, Next, and Tailwind: visual direction, Tailwind implementation, dark-mode and responsive retrofits, and a rule-based audit of built frontends covering state gaps, data loss, focus and keyboard failures, accessibility markup, layout resilience, and AI-slop tells, with file:line…
Runs blind, human-labeled baseline-versus-profile evaluations through a locally authenticated Codex or Claude Code CLI. Measures whether the exact ghostwriter skill and private platform profiles improve resemblance to held-out writing. Use when asked to "evaluate my voice", "test my voice profile", compare writing…
Drafts, rewrites, or reviews the user's personal messages, emails, posts, and tickets from a private per-platform profile plus a shared soul.md, strips the machine tells that make prose read as AI, and applies a communication-strategy layer to high-stakes messages. Use when asked to "write this in my voice", "draft a…
Trains private, platform-specific tone profiles from local writing samples with deterministic held-out splits, clean Codex or Claude Code sessions, previews, backups, and atomic writes. Use when asked to "learn my tone", "build my voice profile", "train a writing style", import writing samples, refresh a tone profile…
Instructions for mblode/claude-code-search, covering agents.md — claude-code-search, commands, this is a react app that renders to a terminal, build shape and reading session history.
Search local Claude Code, Codex, and Cursor user-prompt history (read-only). Use when you need a past prompt, want to grep coding-agent session text, or pipe prompt history as JSON.