Amplify safe or boring designs to make them more visually interesting and stimulating. Increases impact while maintaining usability.
Skills(SKILL.md)は、AIエージェント(Claude Code、Cursor、Codexなど)に特定の能力を追加するための設定ファイルです。
詳しく見る →Amplify safe or boring designs to make them more visually interesting and stimulating. Increases impact while maintaining usability.
**Name:** `base-ui`
Creates and manages git worktrees for isolated plan execution. Use when setting up a worktree for a plan, syncing with base branch, rebasing, or cleaning up worktrees. Never modify the main repo for plan work—all work happens in the worktree.
>-
This skill implements a proven product management framework. The approach combines best practices from industry leaders and is designed for practical application in day-to-day PM work.
Use this skill when working with Conductor's context-driven development methodology, managing project context artifacts, or understanding the relationship between product.md, tech-stack.md, and workflow.md files.
When the user wants help creating, scheduling, or optimizing social media content for LinkedIn, Twitter/X, Instagram, TikTok, Facebook, or other platforms. Also use when the user mentions 'LinkedIn post,' 'Twitter thread,' 'social media,' 'content calendar,' 'social scheduling,' 'engagement,' 'viral content,' 'what should I post,' 'repurpose this content,' 'tweet ideas,' 'LinkedIn carousel,' 'social media strategy,' or 'grow my following.' Use this for any social media content creation, repurposing, or scheduling task. For broader content strategy, see content-strategy.
Implement Clean Architecture patterns for Flutter - domain/data/presentation layers
Continuous Vibe loop runner for Codex.
Codex-native deep work mode for protoLabs Studio. Use when the user wants autonomous backlog processing, PR flow supervision, board grooming, and sustained operational work until the system is quiet.
When a GDD is revised, scans all ADRs and the traceability index to identify which architectural decisions are now potentially stale. Produces a change impact report and guides the user through resolution.
Orchestrate frontend concept generation across 5 style families with up to 4 passes each, dispatching isolated Claude Code Task agents per pass with deliberate interaction design, optional media assets, and CDN libraries, then running uniqueness and visual validation.
Build applications powered by GitHub Copilot using the Copilot SDK. Use when creating programmatic integrations with Copilot across Node.js/TypeScript, Python, Go, or .NET. Covers session managemen...
>
>
Execute codeagent-wrapper for multi-backend AI code tasks. Supports Codex, Claude, and Gemini backends with file references (@syntax) and structured output.
Search for products on Chinese e-commerce platforms (Taobao, JD, Vipshop, PDD, Meituan, Ele.me, etc.) using web search. This skill helps users find products, compare prices, and get recommendations from major shopping platforms.
Recommend suitable Chinese shopping platforms based on product category and shopping intent.
Use constraint compilation in healthcare operations with emphasis on safety, dignity, equity, and long-term societal benefit.
>-
Use when the user requests research, investigation, best practices, comparisons, or evidence-backed recommendations.
🎀 AgenticMail — Full email, SMS, storage & multi-agent coordination for AI agents. 63 tools.
Use for habit loops, progression systems, gamification mechanics, behavioral nudges, freemium funnel design, activation mechanics, and PLG conversion flows that must increase product value without becoming manipulative. Use when designing retention loops, streaks, badges, or onboarding flows.
>
**Display Name:** Local SEO Rank Checker
|-
Create a new Claude Code skill with proper SKILL.md structure, frontmatter, and best practices. Use when user wants to create, write, build, or add a new skill.
Use —
- **Skill ID:** `u08069-creative-ideation-facilitation-for-sales-and-client-success`
- skill_id: `u06250-community-feedback-harvesting-for-entrepreneurship-operations`
Structured messaging protocols for agent team communication including message type selection, plan approval, shutdown procedures, and anti-patterns to avoid. Use this skill when establishing team communication norms, handling plan approvals, or managing team shutdown.
Guidance for coordinating work across Pi terminals using pi-link. Use when delegating tasks, choosing between link_prompt and link_send, planning async vs sync work, batching parallel jobs, or avoiding busy/conflict patterns.
>-
Agent-first workflow and design rails for building X07 programs with the released toolchain (no repo-only dependencies). Canonical execution is via `x07 run`.
brainstorm
> This file defines every tool the Elec-AI agent ("Mate") can call via the Elec-Mate MCP server. The agent cannot call anything not listed here.
You manage Linux servers via a REST API. Each server runs the Linux Server Bot API (port auto-detected on startup, default 8120), optionally exposed via Cloudflare Tunnel.
outloop-runner
Revisa una app/landing, detecta problemas típicos, propone mejoras y aplica correcciones con un checklist fijo para dejarlo listo para enseñar o publicar.
数据浏览技能:浏览 ADDP 平台中可用的存储引擎和数据目录。当用户想了解平台有哪些数据库、存储引擎、schema、表或数据文件时使用。
Use this skill when working with Conductor's context-driven
Master on-call shift handoffs with context transfer, escalation procedures, and documentation. Use when transitioning on-call responsibilities, documenting shift summaries, or improving on-call processes.
Explain how something works in this codebase by exploring code and producing a clear architectural explanation. Optionally critique the architecture for issues.
Rules for how and when to call tools — general tool use, chaining, error handling, webhook sessions, cron sessions, and loop prevention
Find leaked secrets, API keys, tokens, and credentials in local git repos and GitHub repositories.
Gunakan skill ini setiap kali diminta untuk:
Use this skill when the operator wants to define or refresh an agent identity before deployment.
Use **bash** (with optional background mode) for all coding agent work. Simple and effective.
You are implementing a fix or feature from a detailed task description. Create a PR and report back.
>