提示词
提示词工程与模板
caam
Dicklesworthstone
"Coding Agent Account Manager - Sub-100ms account switching for AI coding CLIs with fixed-cost subscriptions. Vault profiles, isolated profiles for parallel sessions, smart rotation with health scoring, cooldown tracking, automatic failover, TUI dashboard. Go CLI."
cm
Dicklesworthstone
"CASS Memory System - procedural memory for AI coding agents. Three-layer cognitive architecture with confidence decay, anti-pattern learning, cross-agent knowledge transfer, trauma guard safety system. Bun/TypeScript CLI."
agent-fungibility
Dicklesworthstone
"The philosophy and practical benefits of agent fungibility in multi-agent software development. Why homogeneous, interchangeable agents outperform specialized role-based systems at scale."
perplexity
pacphi
Perplexity AI research assistant with real-time web search, source citations, and optimized UK-centric prompts. Access live web data, current events, market research, and comprehensive analysis backed by verified sources.
ui-permission-respond
EdanStarfire
Detect and respond to a permission prompt in the Claude Code WebUI. Use when approving or denying tool permissions, handling permission modals, responding to Claude asking for approval, or unblocking a paused session.
google-flow
oyi77
Use when navigating and operating Google Flow (labs.google/fx/tools/flow) - an AI video generation tool. Helps with project management, scenebuilder interface, prompt entry, preset selection, model configuration, and video generation workflow.
deepseek-reasoning
pacphi
DeepSeek special model reasoning bridge - Advanced multi-step reasoning via MCP, bridging devuser to deepseek-user for complex problem-solving with structured Chain-of-Thought outputs.
lumen-ai
uw-ssec
Master AI-powered natural language data exploration with Lumen AI. Use this skill when building conversational data analysis interfaces, enabling natural language queries to databases, creating custom AI agents for domain-specific analytics, implementing RAG with document context, or deploying self-service analytics with LLM-generated SQL and visualizations.
browser-cc7d3d6d
FuRongJun-1999
安装事件 / PWA-安装事件 / PWA beforein / 展示 / 接受 / 拒绝 / PWA 安 / beforeinstal。用户提到这些词时使用本技能。 场景：对照：PWA beforeinstallprompt——捕获/展示/接受/拒绝（安装事件流）。 【不适用】Not for 以下场景：action 非 {accept, capture, dismiss, prompt} 时
finding-duplicate-functions
obra
Use when auditing a codebase for semantic duplication - functions that do the same thing but have different names or implementations. Especially useful for LLM-generated codebases where new functions are often created rather than reusing existing ones.
Context7 MCP Server
pacphi
ollama - Local LLM runtime
creating-skills
fvadicamo
Guide for creating Claude Code skills following Anthropic's official best practices. Use when user wants to create a new skill, build a skill, write SKILL.md, update an existing skill, or needs skill creation guidelines. Provides structure, frontmatter fields, naming conventions, and new features like dynamic context injection and subagent execution.
sf-ai-agentforce
Jaganpro
Standard Agentforce platform skill. Covers Setup UI-based agent building, topic/action configuration, PromptTemplate metadata, Einstein Models API, GenAiFunction/GenAiPlugin setup, and custom Lightning types. For Agent Script DSL development, use sf-ai-agentscript instead.
inertia-rails-setup
inertia-rails
One-time project initializer for Inertia Rails skills. Detects stack and frontend framework (React/Vue/Svelte) from Gemfile and package.json, offers to install recommended deps (alba-inertia, js-routes, pagy, shadcn), and generates a CLAUDE.md section that configures which skill patterns apply. Use when first installing these skills, bootstrapping a new Inertia Rails project, or when the stack changes.
voice-ai
ScientiaCapital
"Production voice AI agents with sub-500ms latency. Groq LLM, Deepgram STT, Cartesia TTS, Twilio integration. No OpenAI. Use when: voice agent, phone bot, STT, TTS, Deepgram, Cartesia, Twilio, voice AI, speech to text, IVR, call center, voice latency."
project-context
ScientiaCapital
"Maintains project context and progress tracking across Claude sessions. Use at session start to load context, on session end to save progress. Triggers: load project context, save context, end session, what was I working on, switch to project, done for today."
unsloth-training
ScientiaCapital
"Fine-tune LLMs with Unsloth using GRPO or SFT. Supports FP8, vision models, mobile deployment, Docker, packing, GGUF export. Use when: train with GRPO, fine-tune, reward functions, SFT training, FP8 training, vision fine-tuning, phone deployment, docker training, packing, export to GGUF."
agent-teams
ScientiaCapital
"Orchestrate teams of parallel Claude Code sessions working on the same codebase. Handles task decomposition, agent coordination, context isolation, and merge strategies. Builds on worktree-manager for infrastructure."
groq-inference
ScientiaCapital
"Fast LLM inference with Groq API - chat, vision, audio STT/TTS, tool use. Use when: groq, fast inference, low latency, whisper, PlayAI TTS, Llama, vision API, tool calling, voice agents, real-time AI."
extension-authoring
ScientiaCapital
"Comprehensive guide for authoring Claude Code extensions including skills (SKILL.md), hooks, slash commands, and subagents. Use when: creating skills, writing hooks, making slash commands, building subagents, learning Claude Code extensions."
cost-metering
ScientiaCapital
"Track and manage API costs across sessions. Budget alerts, model routing for cost optimization, spend reports. Use when: cost check, budget status, how much spent, optimize costs, cost tracking."
openrouter-skill
ScientiaCapital
"Orchestrate Chinese LLMs (DeepSeek, Qwen, Yi, Moonshot) through OpenRouter API with LangChain. Use when: openrouter, chinese llm, deepseek, qwen, moonshot, yi model, model routing, auto router, llm orchestration."
trading-signals
ScientiaCapital
"Technical analysis patterns - Elliott Wave, Wyckoff, Fibonacci, Markov Regime, and Turtle Trading with confluence detection. Use when analyzing charts, identifying trading signals, or calculating technical levels."
planning-prompts
ScientiaCapital
"Comprehensive skill for project planning and prompt engineering. Covers hierarchical plans (briefs, roadmaps, phases), Claude-to-Claude meta-prompts, and multi-stage workflows. Use when: planning, prompt creation, agentic pipeline work, project roadmap, meta-prompts, research to implement workflow."