发现 tools llm ai 相关 Skills，比较来源仓库和用途，查看适合你工作流的技能说明。
Transform content through eight cognitive lenses for different kinds of understanding. Use when the same concept needs exploration through story, debate, simulation, uncertainty, fiction, embodiment, ritual, or...
Apply optimization techniques to extend effective context capacity. Use when context limits constrain agent performance, when optimizing for cost or latency, or when implementing long-running agent systems.
Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.
Recognize, diagnose, and mitigate patterns of context degradation in agent systems. Use when context grows large, agent performance degrades unexpectedly, or debugging agent failures.
Design and evaluate context compression strategies for long-running agent sessions. Use when agents exhaust memory, need to summarize conversation history, or when optimizing tokens-per-task rather than tokens-...
Determines appropriate agent routing based on task type, scale, and agent capabilities
Common workflow patterns and coordination strategies for multi-agent orchestration
Set up AI inference servers on cloud GPUs. Create private LLM APIs (vLLM, TGI), image generation endpoints, embedding services, and more. All with OpenAI-compatible interfaces that work with existing tools.
Process audio, video, and media on cloud GPUs. Transcribe with Whisper, clone voices, generate videos, upscale images, and run batch media processing. All results sync back to your Mac.
Specialized skill for ML training workflows on cloud GPUs. Fine-tune LLMs with LoRA/QLoRA, train image LoRAs, build classifiers, and run custom training jobs. Generates production-ready training pipelines with...
Transform natural language requests into complete GPU CLI workflows. The ultimate skill for Mac users who want to run NVIDIA GPU workloads without configuration complexity. Describe what you want, get a working...
This skill should be used when the user asks to "build an AI assistant", "create a chatbot", "make an agent that does X for me", "design a copilot feature", "automate this workflow with AI", or requests delegat...
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 to...
Manage markdown work-session files in .agent/work-sessions to save, resume, search, and update progress across Copilot or LLM sessions.
How to create new Agent Skills following the open standard. Use when authoring new skills, extending agent capabilities, or packaging specialized knowledge into reusable formats.
Execution skill for delegated tasks. Use this skill when you are a subagent that has been delegated a task by the tech lead. You must be diligent, hygienic, and deliver work that is "done" and "stable" accordin...
Project-agnostic guidance for continuing work across Claude sessions. Ensures context recovery, task resumption, and state reconciliation.
Project-agnostic skill for delegating execution work to subagents with skill activation, parallel execution, and quality verification.
Orchestrate a Ralph loop of sequential sub-agent runs using codex exec. Use when a user asks for /ralph N , a ralph loop, or a multi-pass review where a controller agent composes subprocess prompts, collects ou...
Facilitate structured idea exploration and product/design specification. Use when a user wants to talk through an idea, refine it via iterative questions, and converge on a clear design/spec (and later an imple...
When the user asks about [TRIGGER WORDS], wants to [ACTION], or needs help with [TOPIC], use this skill to provide [CAPABILITY]
Analyze feature requests, refactor plans, or technical decisions to determine investment value and provide recommendations. Use when user mentions investigating, analyzing, or asks "should we build this".
Automatically analyze project plans and generate comprehensive task breakdowns. Use when user describes a project, feature set, or asks to build/implement something complex requiring multiple tasks.
Transforms AI pain points into working skills. Use when creating new skills from identified patterns.
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。