Use when manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
日本語の概要は準備中です。原文の説明を表示しています。
Use when acting as the authoritative design lead for all frontend work, enforcing brand discovery, Anti-Slop rules, DTCG design tokens, fluid motion, and data-driven design generation.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
This skill is the single source of truth for all design decisions. It replaces: design-taste-frontend, frontend-design.
Routing: Component lookup order: the project's own design system and sources file first (its components, tokens, DESIGN.md); the BDB library (@bdb registry; version-pinned unpkg entry https://unpkg.com/@hybridlabor-api/ui-motion-library@0.1.0/publish/registry/{name}.json in components.json) only when the project opts in; then the verified registries listed in the UI library's docs/sources.md (link-only entries are documentation links, never code sources).
Look for the project's own design source first: design-tokens.json, tokens.css, the tailwind theme, brand.md or DESIGN.md. Use it if found. If none exists, ask the user; otherwise start from the neutral defaults in design-tokens.json.
Before ANY design work, gather project context. Never assume colors, fonts, or visual direction.
Generate a project-specific DESIGN.md containing:
references/taste-archetypes.md (Utilitarian Minimalist, Industrial Brutalist, High-End Tactile, Ethereal Modern) + all Anti-Slop bans ACTIVEThese pattern rules are ALWAYS active regardless of brand:
Color/Font bans (ONLY when no brand is defined):
Full ban reference: → references/anti-slop-rules.md
All design values MUST come from design-tokens.json (DTCG format).
Never guess spacing values. Never use arbitrary hex colors.
Spring presets: → design-tokens.json > motion Creative arsenal: → references/creative-arsenal.md Bento paradigm: → references/bento-paradigm.md
Silently validate ALL code against this before presenting to user:
Master orchestration skill for UI/UX design, enforcing high-agency design taste and system consistency.
DESIGN.md and Anti-Slop guidelines.| Rationalization | Reality |
|---|---|
| I'll just add this one CSS override to make it fit. | Violates design tokens and creates inconsistent UI; use the designated token. |
| We don't need a loading state here, it's fast. | Network latency varies; missing feedback states cause perceived unresponsiveness. |
| I'll skip the dark mode check since the primary brand is light. | Incomplete dark mode breaks the app for users relying on system preferences. |
まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Use when manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
日本語の概要は準備中です。原文の説明を表示しています。
Use when a hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
日本語の概要は準備中です。原文の説明を表示しています。
Reference for how BDB structures autonomous software engineering work — the seven-node dispatcher graph (Architect, TechLead, UI/UX, Engineering, Media/EventTech, Reviewer, Shipping) that /startcycle-graph actually runs. Use when you need the high-level lifecycle framing without inventing your own process.
日本語の概要は準備中です。原文の説明を表示しています。
Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling.
日本語の概要は準備中です。原文の説明を表示しています。
Harness patterns for coding agents — memory, permissions, context engineering, delegation, skills, hooks, bootstrap.
日本語の概要は準備中です。原文の説明を表示しています。
agenttrail: live map of a multi-agent build in the browser: which plan component is being worked on, by which agent or harness, what is done and what is stuck. Use when a multi-agent pipeline starts (/startcycle, /startcycle-graph, /teamwork-preview) or after a plan-canvas approve, when the user asks to see what the agents are doing ("live map", "build board", "who is running now"), or by yourself whenever a multi-agent run is under way — no user prompt needed.
日本語の概要は準備中です。原文の説明を表示しています。