发现 Skills

Complete photography system — exposure, composition, lighting, genre-specific workflows, editing, gear selection, portfolio building, and client management. From beginner to professional.

AI-powered diary generation for agents - creates rich, reflective journal entries (400-600 words) with Quote Hall of Fame, Curiosity Backlog, Decision Archaeology, and Relationship Evolution. Generates personal, emotional entries from the agent's perspective. Works best with Claude models (Haiku, Sonnet, Opus).

Advanced Home Assistant control using the official hass-cli tool. Features auto-completion, event monitoring, history queries, and rich output formatting. Alternative to the curl-based homeassistant skill - choose this if you want a more interactive CLI experience with better discovery and formatting.

Draft contracts, review legal documents, and navigate compliance with practical legal patterns.

Generate adult video content using each::sense API with safety checker disabled

Make outbound AI phone calls. Use when asked to call a business, make a phone call, order food by phone, schedule appointments, or any task requiring voice calls. Triggers on "call", "phone", "dial", "ring", "order pizza", "make reservation", "schedule appointment".

Safe command execution for OpenClaw Agents with automatic danger pattern detection, risk assessment, user approval workflow, and audit logging. Use when agents need to execute shell commands that may be dangerous (rm -rf, dd, fork bombs, system directory modifications) or require human oversight. Provides multi-level risk assessment (CRITICAL/HIGH/MEDIUM/LOW), in-session notifications, pending request management, and non-interactive environment support for agent automation.

AI-powered automated QA for web apps. Smoke tests, accessibility, visual regression. Works with Cursor, Claude, ChatGPT, Copilot. Vibe-coding ready.

Discover restaurants with advanced filters (cuisine, price, distance, rating, promotions), place single or group orders on Wolt.com, reorder past favorites, track status in real-time, automatically detect delays and contact support, and push rich updates to Slack or other channels.

Assess repository readiness for promotion through governance states (LOCAL, CANDIDATE, PUBLIC_PROCESS, GRADUATED) with structured checklists, quality gates, and evidence requirements. Triggers on promotion assessment, readiness review, or governance state transition requests.

Specialized knowledge for writing modern high-quality CSS. Trigger this skill when starting a new CSS project/file, when the user asks about new CSS features (e.g. Masonry, View Transitions, Container Queries, Scroll-driven animations), or requests refactoring of legacy styles to modern standards.

Extract full context of the last task from the most recent parent session shown in the session lineage. Strategically uses sub-agents to avoid bloating your own context.

Up-to-date library documentation retrieval using Context7 MCP tools. Process THINK → RESOLVE → FETCH → APPLY. Use when fetching library docs, resolving package names to IDs, getting implementation guides, exploring API references. Provides package resolution strategy, trust score evaluation, token scaling (3K-20K), topic selection patterns.

Use when building AI agents with Google ADK (Agent Development Kit), creating Gemini agents, implementing multi-agent systems, or working with ADK tools and workflows. Covers installation, agent types, function tools, callbacks, sessions, and deployment.

Scaffolds a complete .NET solution following Clean Architecture principles with proper layer separation (API, Application, Domain, Infrastructure). Creates project structure, dependency injection setup, and cross-cutting concerns configuration.

Principles of game audio: sound design, music integration, and adaptive audio systems.

Ni Haixia perspective. Representative of the Hong Kong–Taiwan Five-Arts school (1954–2012), a 'ming/xiang/bu/shan/yi' (fate/physiognomy/divination/geomancy/medicine) lineage acting as a living archive. Provides a decision-making viewpoint of 'cross-arts integration + common origin of fate and medicine + anti-jianghu + anti-academic philology', creating a counterpoint to the single-discipline depth of the Zi Ping school (Shen Xiaozhan / Liang Xiangrun) and the blind-school mnemonic lineage (Duan Jianye). Long-form lectures with among the highest material density in the Chinese-speaking world.

Detect and rewrite AI-like Chinese text using a practical workflow for scoring, humanization, academic AIGC reduction, and style conversion. Use when a user asks to remove AI-like style, reduce AIGC signals, remove AI traces, lower similarity in academic papers (for CNKI/Weipu/Wanfang checks), humanize Chinese, detect AI-generated text, or make Chinese sound more natural.

Use when performing FastAPI validation with Pydantic models. Use when building type-safe APIs with robust request/response validation.

Workflow 3: Full paper writing pipeline. Orchestrates paper-plan → paper-figure → paper-write → paper-compile → auto-paper-improvement-loop to transform a narrative report into a polished, submission-ready PDF. Use this when the user says "full paper writing pipeline", "write paper pipeline", "from report to PDF", "paper writing", or otherwise requests the complete paper generation workflow.

Create comprehensive audio design including music cues, sound effects, Foley, and score direction

This skill should be used when the user asks to find keywords, keyword research, what should I write about, keyword difficulty score, search volume data, identify ranking opportunities, topic ideas, what are people searching for, which keywords to target, content ideas for [topic], or long-tail keyword suggestions. Discovers high-value keywords with search intent classification (informational/commercial/transactional/navigational), keyword difficulty (KD) scoring, monthly search volume (MSV), CPC estimates, and AI citation potential. Produces ranked keyword lists, topic clusters with pillar + cluster page assignments, and priority-scored content calendars. Works with Ahrefs, SEMrush, Google Keyword Planner, Google Search Console, or manual data input. For competitor keyword gaps, see competitor-analysis. For topic coverage gaps, see content-gap-analysis.

Incident Severity Levels provide a standardized framework for classifying incidents based on their impact on users, business operations, and SLA compliance. Consistent severity classification ensures

Deploy and manage security hardening for high-privilege autonomous AI agents (OpenClaw) using a Agentic Zero-Trust Architecture and automated defense matrices.