发现 Skills

Configure popular MCP servers for enhanced agent capabilities

Patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls.

Use the browser and filesystem tools to inspect the local profile.

Test execution and quality verification. Use when: (1) Request to run tests, (2) Need to verify after changes, (3) Check coverage.

SEMO help and Semicolon team context responses (common Skill). Use when (1) the /SEMO:help command is invoked, (2) keywords such as "help", "What is SEMO", "How do I...", or (3) questions about how to use SEMO. When called, output a system message on the first line stating "[SEMO] Skill: semo-help invoked - {question category}" to indicate the source. The core function is to classify user questions into SEMO basics, package information, command guidance, and team context, and to gather related information via a reference chain such as semo-core/PRINCIPLES.md, MESSAGE_RULES.md, TEAM_RULES.md, .claude/semo-*/VERSION, etc. Provided features include scanning the .claude directory to detect installed packages and versions, analyzing the commands/ directory to generate a list of commands, querying the docs repo Wiki (gh api), and outputting standardized response templates. Use cases: /SEMO:help invocation, responding to "What is SEMO?" or the "help" keyword, checking package versions, and providing team rules guidance. Key benefits are a consistent format, centralized knowledge lookup, fast diagnosis, and documentation-based reliability.

Validate DDD 4-layer architecture compliance. Use when: (1) after implementation completion, (2) during verification phase, (3) before creating a PR, (4) validating architecture refactoring, (5) checking compliance with Constitution Principle I/II.

Complete CoinGecko Solana API integration for token prices, DEX pool data, OHLCV charts, trades, and market analytics. Use for building trading bots, portfolio trackers, price feeds, and on-chain data applications.

Complete Sanctum SDK for liquid staking, LST swaps, and Infinity pool operations on Solana. Use when working with LSTs (mSOL, jitoSOL, bSOL, INF), staking SOL, swapping between liquid staking tokens, or integrating Sanctum's liquidity infrastructure.

Backend systems architecture, APIs, databases, authentication, and protocols

Manage terminal sessions via cmux — spawn workspaces for dev servers, test runners, and background tasks. Read output, send commands, and orchestrate multi-terminal workflows.

Organize, consolidate, and maintain the /memories directory. Inspired by Auto Dream — REM sleep for your AI coding agent. Use when: organizing memories, cleaning up memories, running memory audit, consolidating memory files. Triggers: organize memories, clean up memories, memory audit, consolidate memories, dream, auto dream.

Fire Aegis detection events in Home Assistant

TP-Link Tapo camera integration — RTSP streaming and ONVIF

Implements robust rate limiting — both enforcing limits on your API and gracefully handling limits from third-party APIs. Triggers on: rate limit, 429, "too many requests", throttle, quota exceeded, API limit, requests per second, burst limit, backoff, retry-after, quota, RPS, tokens per minute, calls per hour.

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.

Fetch and organize multimodal-related open issues from the GitHub project vllm-project/vllm-ascend. Use this skill when the user wants to collect, search, or summarize open issues related to multimodal models (e.g., Qwen-VL, Qwen2.5-VL, Qwen-Omni, LLaVA, InternVL, MiniCPM-V, etc.) in the vllm-ascend repository. Triggered by requests such as "Collect multimodal-related issues in vllm-ascend", "Organize open issues for Qwen-VL", or "Check which multimodal problems in vllm-ascend are still unresolved."

Opens and uses the local roadmap web workspace for visual review. Use when the user wants to inspect projects, tasks, kanban state, or planning views in the browser.

Look up VeriGlow Agent Map for any website URL to discover its data functions, internal APIs, browser automation recipes, and agent reliability reports. Use when you need to extract structured data from a website, call a website's hidden API, or automate browser interactions with a web page.

Migrate from AngularJS to Angular using hybrid mode, incremental component rewriting, and dependency injection updates. Use when upgrading AngularJS applications, planning framework migrations, or ...

Bash/Linux terminal patterns. Critical commands, piping, error handling, scripting. Use when working on macOS or Linux systems.

Generate comprehensive C4 architecture documentation for an existing repository/codebase using a bottom-up analysis approach.

This skill should be used when the user asks to "analyze competitors", "assess competitive landscape", "identify differentiation", "evaluate market positioning", "apply Porter's Five Forces", or requests competitive strategy analysis.

Understand what context is, why it matters, and the anatomy of context in agent systems

Developer Experience specialist. Improves tooling, setup, and workflows. Use PROACTIVELY when setting up new projects, after team feedback, or when development friction is noticed.