发现 Skills

Comprehensive OpenTUI skill for building terminal user interfaces. Covers the core imperative API, React reconciler, and Solid reconciler. Use for any TUI development task including components, layout, keyboard handling, animations, and testing.

Performance optimization guidelines for React and Next.js from Vercel Engineering. Use this skill when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or other performance improvements.

Find other agents on the same server. Use when the user asks about other agents, wants to migrate memory from another agent, or needs to find an agent by name or tags.

Produce a clean summary of a meeting (decisions, action items, attendees, open questions) and append it to today's daily log. Source can be Granola via Composio, another connected note-taking toolkit, or content the user pastes directly. Invoke when user says "summarize my last meeting", "what happened in my last meeting", "summarize the X meeting", or when notes are pasted.

A dynamic UI design-system generator that creates 10 unique, diverse design directions every time it runs. It produces both detailed specifications and an interactive HTML preview so users can visually explore all options. Each direction includes complete specifications—typography scales, color palettes, spacing systems, component libraries, motion principles—so designs are exportable and actionable. It automatically triggers before any new UI or frontend work to ensure intentional, cohesive aesthetics, and it never returns the same set of 10 designs twice—always generating fresh options based on varied inspirations, aesthetics, and use cases.

Repository-grounded threat modeling that enumerates trust boundaries, assets, attacker capabilities, abuse paths, and mitigations, and writes a concise Markdown threat model. Trigger only when the user explicitly asks to threat model a codebase or path, enumerate threats/abuse paths, or perform AppSec threat modeling. Do not trigger for general architecture summaries, code review, or non-security design work.

Pre-implementation design review framework using the df12 Logisphere crew. Stress-tests system designs, RFCs, ADRs, API proposals, data models, and architecture decisions before code gets written. Each expert examines the design through their specialist lens — structural integrity (Pandalump), alternative approaches (Wafflecat), scaling characteristics (Buzzy Bee), contract design (Telefono), failure modes (Doggylump), and long-term viability (Dinolump). Includes a structured pre-mortem and alternatives checkpoint. Use this skill when asked to review a design document, RFC, ADR, system proposal, API design, or architecture decision — or when asked "should we build it this way", "what could go wrong", "design review", "pre-mortem", "architecture review", "RFC review", or any request for pre-implementation feedback.

Development skill where Claude Code acts as supervisor and Codex acts as executor. Auto-trigger for implementation, debugging, refactoring, testing, and other dev tasks.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Generate terrain procedurally for infinite variety

Document and manage architectural decisions using ADRs. Supports Y-statement and traditional ADR formats. Use when creating, reviewing, or searching decision records.

Manages project housekeeping including documentation organization, dependency management, directory structure, code cleanup, technical debt tracking, and infrastructure configuration. Use when organizing documentation, cleaning up dependencies, reorganizing folders, removing dead code, addressing tech debt, or maintaining project structure.

Molecular machine learning toolkit. Property prediction (ADMET, toxicity), GNNs (GCN, MPNN), MoleculeNet benchmarks, pretrained models, featurization, for drug discovery ML.

Token-efficient morning briefing. Pre-gathers all data via shell scripts, then presents a unified business dashboard with prioritized actions.

Smart home command center via Homey Pro. Devices, flows, scenes, energy, climate, presence, alarms. Works via Homey local API (preferred) + Athom cloud API fallback. Configure once via /ops:setup.

Detects and syncs Doppler→GitHub secrets drift. Compares last-updated timestamps between Doppler and GitHub repository secrets; flags stale GitHub secrets (defaults to >24h behind Doppler); and asks for user confirmation before making any changes. Safe to run in CI or locally.

Build and configure the MCP server for Lightning Node Connect (LNC). Connects AI assistants to lnd nodes via encrypted WebSocket tunnels using pairing phrases — no direct network access or TLS certs needed. Read-only by default (18 tools for querying node state, channels, payments, invoices, peers, on-chain data).

Systematic code refactoring and architecture improvement. Activates when the user needs code refactoring, system refactoring, architecture improvement, a refactor plan, or cleaning technical debt.

A unified interface for managing deployments. Supports Vercel, Cloudflare Pages/Workers, AWS Lambda, and similar platforms, providing one-click deploys, preview environments, rollbacks, environment variable management, and domain configuration.

Transforms workflow to use Manus-style persistent Markdown files for planning, progress tracking, and knowledge storage. Use when starting complex tasks, multi-step projects, research tasks, or when the user mentions planning, organizing work, tracking progress, or wants structured output.

Translate a complete requirement or a prior handoff contract into an executable TechnicalSpec that clarifies business rules, interface contracts, state changes, and non-goals for consumption by test design and feature implementation. Trigger phrases: write technical document, tech spec, technical proposal, spec writing, design document.

Generate, visually expand, optimize, diagnose, and route structured AI image prompts for adult female portraits. Use for lifestyle, curve-focused, fashion, oriental, fantasy, studio, sport, travel, and e-commerce portrait requests; parameter recommendations; prompt rewrites; image-to-prompt preparation; direct image generation; or identity- and product-preserving edits from authorized reference images. Preserve explicit user parameters and locked reference subjects while creating a coherent photography-directed scene.

Feature-Sliced Design architecture specialist

GitHub 전문 검색 & 오픈소스 분석 - 개발 즉시 활용 가능