全部能力

Prompt 优化助手。适用于用户想优化提示词、改进 AI 指令、为特定任务设计更好的 prompt，或需要选择合适提示框架时使用。会根据任务场景匹配合适框架，必要时先追问关键信息，再输出更清晰、更可执行的提示词版本。

Comprehensive market analyst skill that orchestrates all Octagon stock performance and market data skills. Use when conducting stock analysis, creating market…

Expert blueprint for roguelikes including procedural generation (Walker method, BSP rooms), permadeath with meta-progression (unlock persistence), run state vs…

Build profitable Google Ads campaigns by applying Perry Marshall's 80/20 principles to paid search optimization Use when: **Setting up a new Google Ads…

Full-stack e-commerce marketing strategy builder. Analyzes your product, market, and competitors, then builds a complete omnichannel marketing plan covering…

Optimize an OpenClaw agent setup (model routing, context management, delegation, rules, memory). Use when asked about optimizing agents, improving OpenClaw…

Master game engines - Unity, Unreal Engine, Godot. Engine-specific workflows, systems architecture, and production best practices.

Expert patterns for input handling covering InputMap actions, InputEvent processing, controller support, rebinding, deadzones, and input buffering. Use when…

Generate end-to-end investment proposals covering risk profiling, model portfolio recommendation, fee illustration, projections, and compliance review. Use…

Comprehensive SEO, discoverability, and AI crawler optimization for web projects. Use for technical SEO audits, llms.txt/robots.txt setup, schema markup,…

Expert patterns for Godot AutoLoad (singleton) architecture including global state management, scene transitions, signal-based communication, dependency…

Cost-conscious Claude Code mode. Reduces output tokens 40-70% and overall costs 30-60% by enforcing concise responses, smart model routing, and efficient workflow patterns. Keeps full technical accuracy. Activate with /cost-mode or "enable cost mode". Auto-triggers on mentions of budget, cost, tokens, or spending.

Full-site blog health assessment scanning all blog files for quality scores, orphan pages, topic cannibalization, stale content, and AI citation readiness. Spawns parallel subagents for comprehensive analysis. Produces per-post scores and a prioritized action queue. Use when user says "audit blog", "blog audit", "site audit", "blog health", "audit all posts", "check all blogs".

E-commerce growth strategy advisor. Diagnoses current business health using unit economics (CAC, LTV, AOV, contribution margin), identifies the highest-impact…

Use this skill when writing proposals, responding to RFPs, drafting SOWs, or developing pricing strategies. Triggers on proposal writing, RFP response, statement of work, pricing strategy, win themes, executive summary, and any task requiring business proposal creation or optimization.

Expert blueprint for scene loading, transitions, async (background) loading, instance management, and caching. Covers fade transitions, loading screens,…

[PREREQUISITE] Install and configure Godot MCP server for programmatic scene manipulation via Model Context Protocol. Use when user explicitly requests…

Expert blueprint for RichTextLabel with BBCode formatting (bold, italic, colors, images, clickable links) and custom effects. Covers meta tags, RichTextEffect…

Expert patterns for branching dialogue systems including dialogue graphs (Resource-based), character portraits, player choices, conditional dialogue…

Agent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use…