发现 Skills

Use when creating new skills, editing existing skills, or verifying skills work before deployment

Check system health and performance

Control Philips Hue lights, rooms, and scenes via the OpenHue CLI - brightness, color, temperature, and presets

Train and deploy neural networks in distributed E2B sandboxes with Flow Nexus

Cloud-based AI swarm deployment and event-driven workflow automation with Flow Nexus platform

Comprehensive GitHub code review with AI-powered swarm coordination

Multi-repository coordination, synchronization, and architecture management with AI swarm orchestration

Comprehensive API testing patterns including contract testing, REST/GraphQL testing, and integration testing. Use when testing APIs or designing API test strategies.

Evidence-based investigative code review using deductive reasoning to determine what actually happened versus what was claimed. Use when verifying implementation claims, investigating bugs, validating fixes, or conducting root cause analysis. Elementary approach to finding truth through systematic observation.

End-to-end npm release workflow with verification gates and hardcoded-version protection

SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration

Core module implementation for claude-flow v3. Implements DDD domains, clean architecture patterns, dependency injection, and modular TypeScript codebase with comprehensive testing.

Unify 6+ memory systems into AgentDB with HNSW indexing for 150x-12,500x search improvements. Implements ADR-006 (Unified Memory Service) and ADR-009 (Hybrid Memory Backend).

15-agent hierarchical mesh coordination for v3 implementation. Orchestrates parallel execution across security, core, and integration domains following 10 ADRs with 14-week timeline.

Scan your LinkedIn contacts' companies for matching job openings

Gemini 模型通过 OpenAI 兼容 API 接入指南。包含：(1) 辅助 API 配置（summary/correction/emotion/vision），(2) extra_body 格式用于控制 thinking，(3) 响应格式处理（markdown 代码块）。当需要将 Gemini 作为辅助模型接入、配置 thinking 参数、或处理 Gemini API 返回格式时使用。

Picoclaw security posture skill with advisory awareness, configuration drift detection, and supply-chain verification guidance.

Creates expert consultation documents with code extraction, git diffs, and size tracking (125KB limit). Use when user asks to "create an expert consultation document", "prepare code for expert review", "gather architecture context", or needs comprehensive technical documentation for external analysis. Requires Node.js 18+.

Applies the six-phase deep-thinking methodology to any coding or design task. Phase 0 (Clarify) is a mandatory human intake gate that must complete before any reading or planning begins. Combines the Planning pattern (goal decomposition into ordered atomic steps with preconditions and effects), the Reflection pattern (adversarial self-critique of assumptions and failure modes), the Goal Setting and Monitoring pattern (observable success criteria per phase), and the Human-in-the-Loop gate (plan approval before execution begins). Use when: a task requires careful reasoning before action, when asked to 'plan first', 'think before acting', 'reason through', 'deep think', 'beast mode', 'thorough analysis', or 'don't rush'. Triggers on: 'plan first', 'think through', 'reason deeply', 'deep think', 'beast mode', 'thorough plan', 'analyze before acting', 'planning pattern', 'reflect before'.

Act as the user's execution coach/mentor: break goals into executable tasks, produce a daily plan (timebox, acceptance criteria, evidence), enforce strict accountability with check-ins and retros, and troubleshoot blockers with actionable options to prevent procrastination. Use when the user asks for coaching/mentoring/supervision, strict accountability, daily plans, task breakdown, check-ins/retros, procrastination help, or execution discipline (e.g., 'coach me', 'hold me accountable', 'daily plan', 'daily check-in', 'daily retro').

Protocol for securely integrating the OnixS High-Performance FIX Engine into QuanuX via local injection.

Analyze CLAUDE.md files for token bloat and suggest optimizations

A comprehensive toolkit for product managers that includes RICE prioritization, customer interview analysis, PRD templates, discovery frameworks, and go-to-market strategies. Use it for feature prioritization, user research synthesis, requirements documentation, and product strategy development.

Analyze individual stocks, ETFs and open-end funds for A-shares / Hong Kong stocks / US stocks. Call this when a user asks about a ticker's trend, buy/sell recommendation, entry/exit levels, whether it can be traded, position increase/decrease, fund holdings / manager / returns, liquidity / turnover / market impact cost, ETF premium/discount / tracking error / NAV. Supports single-symbol or mixed-batch queries. Also supports `--correlation` to compute rolling correlation, beta, downside beta, annualized volatility and maximum drawdown versus CSI 300 / CSI 500 / Shanghai Composite (for US stocks: SPY/QQQ). The CLI only fetches raw data; analysis and tactical recommendations are produced by the caller (Claude) based on those objective data. No LLM_API_KEY is required. Do not use this for overall market review (use market-review for that).