All Skills

Agent skill for load-balancer - invoke with $agent-load-balancer

Join a Google Meet call, transcribe live captions, optionally speak in realtime, and do the followup work afterwards. Use when the user asks the agent to sit in on a meeting, take notes, summarize, respond in-call, or action items from it.

Spotify: play, search, queue, manage playlists and devices.

MCP client: connect servers, register tools (stdio/HTTP).

HeartMuLa: Suno-like song generation from lyrics + tags.

Search/download GIFs from Tenor via curl + jq.

Karpathy's LLM Wiki: build/query interlinked markdown KB.

ASCII art: pyfiglet, cowsay, boxes, image-to-ascii.

GitHub auth setup: HTTPS tokens, SSH keys, gh CLI login.

Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs.

DSPy: declarative LM programs, auto-optimize prompts, RAG.

BluOS CLI (blu) for discovery, playback, grouping, and volume.

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

Generate and manage Terraform/Pulumi infrastructure configurations.

Read, search, create, and edit notes in the Obsidian vault.

Apple Reminders via remindctl: add, list, complete.

Benchmark LLM performance across tasks — latency, quality, cost comparison.

Slack tool actions: send/read/edit/delete messages, react, pin/unpin, list pins/reactions/emoji, member info.

Search and analyze your own session logs (older/parent conversations) using jq.

24/7 system health monitoring, auto-restart crashed services, and multi-channel alerting (Discord, Slack, email).

Terminal Spotify playback/search via spogo (preferred) or spotify_player.

每完成一个任务或模块后收尾：多余物检测 + 更新文档 + 写下一轮当前任务 + 提醒 git。

接活分诊 + 新项目初始化。用户说「开始干活」「接个新项目」，或当前代码根没有 CONTEXT.md 时用。

Use this when reviewing code changes for correctness, maintainability, security-sensitive logic, boundary separation, and likely regressions across any supported runtime or framework.

Design user journeys and task flows for a product concept or MVP. Use when the team needs primary flows, branch conditions, edge cases, onboarding paths, and end-to-end user movement before screen planning or UI implementation.

Use this when designing or scaffolding a Python API service, endpoint structure, request validation approach, handler layout, or API-specific service patterns in FastAPI, Flask-style, or similar Python backends.

Use this when planning or refining an Express or Express-style Node.js API with route groups, middleware boundaries, validation, auth, error handling, and service layering.

Use when the team needs reusable UI component patterns, component responsibilities, states, props, and interaction behavior for React, Next.js, or Tailwind-based interfaces. Trigger on requests to design a component system or define a component before coding it.

Design authentication and authorization strategy for a product or MVP. Use when the team needs sign-in methods, session model, user/workspace membership, roles, tenant boundaries, invitation flows, or permission enforcement plans.

Use this skill when implementing any feature that touches user data, auth, APIs, file uploads, pe...

Use this when the team needs to design or refine a backend service, API-facing domain module, internal service, or runtime-specific server component in Python, Node.js, or another backend environment.

Use this when the system needs queue-backed processing design, message handling rules, delivery semantics, dead-letter strategy, or throughput planning. Trigger on requests about queues, brokers, message processing, and consumer coordination.

Use this when reviewing database, storage, config, queue, or integration migrations for rollout safety, rollback feasibility, data correctness, and environment-specific deployment risk.

Use when the team needs a testing plan covering unit, integration, end-to-end, contract, and security-adjacent checks for a product or feature. Trigger on requests to design practical testing strategy before or during implementation.

Use this when the team needs a component breakdown for a screen or feature that may or may not be React-specific. Trigger on requests to plan component responsibilities, composition, states, and boundaries before implementation.

Use this when designing or scaffolding serverless functions for APIs, webhooks, background handlers, or small trusted services across cloud runtimes. Trigger on requests about serverless handlers, event functions, or function-level architecture.