zeon-kun

Use when auditing a repository's uncommitted or messy changes and restructuring them into clean, logical commits. Enforces zero AI co-author footers and groups related files by domain.

Converts a structured decisions document into .claude/rules/ files (frontend.md, backend.md, security.md, infra.md). Called by the rules-writer agent after architect or rules-lock interview completes.

Systematic codebase analysis — architecture, tech stack, code patterns, brand guidelines, and provider doc health. Produces a structured Codebase Digest consumed by other agents.

Validates and updates provider docs (CLAUDE.md, GEMINI.md, AGENTS.md, WARP.md) for staleness after task execution. Also updates CHANGELOG.md and TASKS.md checklist.

Token-aware session planning. Takes a list of goals/tasks and produces a prioritized TASKS.md checklist split across sessions based on estimated token usage and complexity.

Prompt the user to save the current agent output as a markdown spec file. Handles y/n prompt, target directory selection, filename generation, and file writing. Use at the end of any agent workflow.

Write an Architecture Decision Record (ADR) documenting a technical decision with context, options considered, and rationale. Use when a significant technical decision needs to be documented.

Design animations for React/Next.js components using Framer Motion (Motion) or GSAP. Covers entrances, scroll-triggered reveals, page transitions, stagger effects, and interactive micro-animations. Respects user motion preferences.

Use this skill when the user wants to extract or document an existing brand's design system — its tokens, atoms, components, and visual language — from a public source like a website, screenshot, Figma file, or live URL. Triggers include phrases like "extract the design system from X," "document the brand of Y," "reverse-engineer the visual language," "build a style guide from this site," or "capture the design tokens from [URL]." Do NOT use for generating new brands from scratch — this skill only documents what already exists. Output is always a three-file deliverable: tokens.json, preview.html, README.md.

Use this skill when the user wants to build a knowledge graph from a codebase or mixed corpus and view it in Obsidian — e.g. "ionize this repo," "map the code structure," "build a knowledge graph from these files," "visualize the call graph / schema relationships," or "extract the concepts from these docs into a graph." Runs a 3-pass pipeline (Pass 1 code via tree-sitter + SQL, local & free; Pass 2 audio/video via faster-whisper; Pass 3 docs/papers/images via Claude subagents) and emits an Obsidian Canvas plus per-node markdown notes. Do NOT use to write application code or refactor — this skill only produces a graph. Output is always graph.json + graph.canvas + nodes/*.md.