This repository stores personal AI Agent skills in a scalable directory layout.
This repository also configures its own agents. See what SKILL tells them →
Skill Claude CodeCodex
Use when delivering analysis, assessment, or diagnosis to the person whose work/behavior/decisions are being analyzed, and they push back emotionally, contradict conclusions, or express discomfort — prevents flipping the conclusion to match their mood while staying open to new factual evidence. Covers code review…
Skill Claude CodeCodex
Use when a React page re-renders far more than it should — "everything re-renders on every tick", live-data dashboards, Electron/Vite apps that feel heavy under a 1s push stream. Measures render counts from outside the app over CDP (react-scan injected, no source changes), localizes the exact hook that fires, fixes it…
Skill Claude CodeCodex
Use when an Electron app feels slow to launch — Dock icon bounces too long, blank or late window, long skeleton before the UI — or when someone hands over a generic "Electron startup optimization" checklist and asks what applies to this app.
Skill Claude CodeCodex
A collaborative blog-writing workflow that opens a live editor for starting a post or continuing an unfinished draft.
Skill Claude CodeCodex
Build, lay out, or verify an iOS app on iPhone Duo (foldable, iOS 27.1+). Use when work touches the inner/outer displays, the dual-pane UIArrangementViewController container, the right status safe area and collected back button, hinge or fold/unfold behavior, hosting extra React Native surfaces, or driving the iPhone…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: