В каталоге 185 367 навыков в 14 категориях.
Drive the real GUI against the real engine via the standalone dev HTTP bridge (`npm run dev:bridge`). Use whenever "does...
Laravel Livewire conventions for building interactive UI without custom JavaScript. Components are PHP classes with reac...
Use when the project's frontend stack is Livewire — dispatched by `directives/ui/{apply,review,polish}.ts`. Covers react...
Use for any task or question involving Livewire. Activate if user mentions Livewire, wire: directives, or Livewire-speci...
Build, refactor, secure, optimize, and test Laravel Livewire v2-v4 components, including state, forms, events, uploads,...
Guidelines for developing modular, reusable Livewire components.
Principles for writing simple, maintainable Laravel/Livewire code. Use when writing Livewire components, tests, or Blade...
Build and evolve an AI-native browser stack (Living Codex Browser / AetherBrowse) using existing SCBE infrastructure. Us...
This skill should be used when the user asks about "snapshot.md", "constraints.md", "decisions.md", "debt.md", ".ctx/",...
Create and maintain structured design documentation that drives development. Use for new projects, design decisions, gro...
Usage: /sw:living-docs [options]
프로젝트 지식과 할 일(TODO/todo)을 관리합니다. 문서 작성/업데이트, TODO 생성/완료, 의사결정 기록, 작업 현황 파악 시 사용하세요. (user)
把长期项目的文档当成一个小系统来维护,防止文档腐烂——四份各司其职的脊柱文件(CLAUDE.md 共享章程 / CLAUDE_MAP.md 地图 / PROJECT_STATUS.md 健康仪表盘 / PROJECT_LOG.md 流水账)...
Navigate and load project living documentation for context from .specweave/docs/internal/. Use when implementing feature...
Use when building an animated or interactive widget, explainer or dashboard page: how motion feels, where the eye goes,...
Commit les changements, se synchronise avec main distant, push la branche courante et crée une Pull Request. Refuse de t...
Use when the user wants to measure cyclomatic complexity, find overly complex functions, audit code complexity, or gener...
Run Lizard against production source to enforce per-function cyclomatic complexity (CCN), NLOC, and parameter-count thre...
Content caster (铸). Transforms content into PNG visuals. Six molds: -l (default) long reading card, -i infograph, -m mul...
投资分析, 生成一份深度投资分析报告。不做传统投资分析——核心判断是项目是否是一台「秩序创造机器」。Use when user says '投资报告', '投资分析', '分析这个项目', '写投资报告', 'investment repo...
Deep concept anatomist that deconstructs any concept through 8 exploration dimensions (history, dialectics, phenomenolog...
Paper reader for non-academics. Takes a paper and extracts its ideas for personal use. Focuses on understanding, not aca...
Paper workflow: read papers + cast cards in one go. Takes one or more arxiv links, paper URLs, PDFs, or paper names. For...
Cognitive atom: Plain (白). Rewrites any content so a smart 12-year-old groks it. Structure-free — form follows content....
给一个领域,找出背后真正撑着它的几根独立的力。十几个现象砍到不可再少的生成器——砍完能把现象一个个生回来,才算数。Use when user says '降秩', '找秩', '秩是什么', '这个领域靠什么撑着', '背后是什么', or...
Reading companion agent. Accompanies user through any text (books, articles, essays, papers, news) with translation, str...
Structured roundtable discussion framework with a truth-seeking moderator who invites representative figures for dialect...
Skill map viewer. Scans all installed skills and renders a visual overview — name, version, description, category at a g...
追本之箭——纵向深钻思维工具。给一个观点、现象或问题,像箭一样一路向下钻到不可再分的本质。Use when user says '想透', '追本', '本质是什么', '为什么会这样', '深挖', '钻到底', 'think deep'...
Deep travel research workflow for museums and ancient architecture. Input a city name, auto-generates structured knowled...
Deep-dive English word mastery tool. Deconstructs a single English word into core semantics and epiphany. Use when user...
Word flow: deep-dive word analysis + infograph card in one go. Takes one or more English words, runs ljg-word (generates...
写作引擎。带着一个观点出发,在写的过程中把它想透。
Download images and videos from X (Twitter) posts to ~/Downloads. Use when user shares an X/Twitter link and wants to sa...
Use when redesigning, migrating, or auditing any LKDV application page (clubs, carnets, groupes, evenements, explorer, m...
Typed tick loops with FlowMind validation and parallel tick dispatch. Use when running /ll, recurring pipelines, quality...
Meta Llama open-source LLM family. Use for local AI.
Guidelines optimized for Llama 3 and Llama 3.1 open-weights models.
DeFi fundamentals and cross-chain analytics using DefiLlama-style data. Use when you want to find undervalued protocols,...
Run LLM inference with llama.cpp on CPU, Apple Silicon, AMD/Intel GPUs, or NVIDIA — plus GGUF model conversion and quant...
Run a GGUF model locally with llama.cpp, and find one on the HF Hub.
llama.cpp local GGUF inference + HF Hub model discovery.
Operate, configure, benchmark, and troubleshoot llama.cpp across CPU, Metal, CUDA, HIP/ROCm, Vulkan, SYCL, and hybrid or...
Guide for llama.cpp, the C/C++ LLM inference framework by ggml-org. Covers the C API (llama.h), GGUF format, quantizatio...
Run GGUF models directly, load LoRA adapters, benchmark inference speed, and serve models via llama-server using llama.c...
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 M...
Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal...
Use when building RAG or LLM applications with LlamaIndex - data loaders, node parsing, vector stores, retrievers and re...
Llama 3 by Meta — run Llama 3.3, Llama 3.2, and Llama 3.1 across your local device fleet. The most popular open-source L...
Tuning open Llama 3 models under prompt constraints.
Complete llama.cpp C/C++ API reference covering model loading, inference, text generation, embeddings, chat, tokenizatio...
Use when fine-tuning, training, or doing LoRA/QLoRA on LLMs. Triggers on: 'fine-tune LLM', 'LoRA', 'QLoRA', 'llamafactor...
Review a llamafile local inference deployment for unsafe model artifact handling, exposed HTTP server attack surface, lo...
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual con...
Build LLM applications with LlamaIndex. Create indexes, query engines, and data connectors. Use for RAG applications, do...
Build LLM applications with the LlamaIndex framework. Use when working with LlamaIndex or comparing RAG and agent orches...
Use the upstream install or setup path that matches your environment:
LlamaIndex agent and query engine setup for RAG-powered agents
Scaffold a basic LlamaIndex ReAct agent with a tool, wired to any OpenAI-compatible endpoint. Run when the user asks to...
LlamaIndex implementation patterns with templates, scripts, and examples for building RAG applications. Use when impleme...
Review a LlamaIndex retrieval augmented generation stack for ingestion poisoning, node metadata loss, retriever scope fa...
The LlamaIndex Wolfram Alpha tool enables agents to interface with the Wolfram|Alpha LLM API for computational knowledge...
Vision-language chat: VQA, captioning, image dialogue.
Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP visi...
Expert LLC operations management for ID8Labs LLC (Florida single-member LLC). 9 specialized agents providing PhD-level e...
Company formation and LLC setup by country — costs, timelines, requirements, and tax notes. Use when the user asks about...
LLD review, Low-Level Design review, 详细设计评审。Use when: 审查正式 LLD,或评审已批准职责内的有限工程修复方案与整改 delta。Do not use for architecture o...
Write LLD, Low-Level Design, 写详细设计。Use when: PRD/HLD/API Contract 完成后需要写模块设计、接口设计、实现级技术方案。 也用于既有相关文档的有限增量更新。
LLDB debugger skill for C/C++/Swift/Objective-C programs. Use when debugging with LLDB on macOS, FreeBSD, or Linux-clang...
Use when debugging with LLDB on macOS, FreeBSD, or Linux-clang, mapping GDB commands to LLDB, Xcode or VS Code integrati...
List project status - show open issues, recent PRs, commits, and current focus. Use when user types 'lll' or asks for pr...
/LLLL = короткий алиас /LLMs: решить текущий вопрос через адресный ограниченный консенсус других LLM. Триггеры: /LLLL, l...
Build and evaluate LLM prompts. Use when crafting system prompts, comparing variants, estimating tokens, or managing pro...
Universal LLM Router — route prompts to any model across all providers
Large Language Model development, training, fine-tuning, and deployment best practices.
Multi-provider LLM integration. Unified interface for OpenAI, Anthropic, Google, and local models.
Llm subsystem in TTA.dev: execute and related code. 171 symbols | 30 files | Cohesion: 67%
Implement large language model (LLM) chat completions using the z-ai-web-dev-sdk. Use this skill when the user needs to...
Use the LLM Wiki plugin tools to maintain a cited local company wiki.
Orchestrate multiple LLMs as a council, generating collective intelligence through peer review and chairman synthesis
Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmar...
Shared-backbone neural network with actor (policy) and critic (value) heads for grid-based game agent RL training
Hunt vulnerabilities in LLM-powered applications — direct/indirect prompt injection, system prompt extraction, ASCII smu...
Analyze alignment between LLM judge scores and human labels in an eval dataset. Use this skill whenever someone wants to...
PostHog LLM analytics for all supported providers
Automatically applies when building LLM applications. Ensures proper async patterns for LLM calls, streaming responses,...
Build LLM applications: RAG, embeddings, agents, structured outputs, evaluations, fine-tuning, and local inference.
LLM app development with RAG, prompt engineering, vector databases, and AI agents
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLM...
Use when designing LLM-powered applications; Implementing RAG (Retrieval-Augmented Generation)
Production-ready patterns for building LLM applications, inspired by [Dify](https://github.com/langgenius/dify) and indu...
Secure LLM-powered applications with input validation, output controls, tenant isolation, and abuse prevention.
Apply operational controls to applications built on the Anthropic API or similar LLM SDKs. Maps the OWASP LLM Top 10 to...
Building applications with Large Language Models - prompt engineering,
You are an AI assistant development expert specializing in creating intelligent conversational interfaces, chatbots, and...
You are an expert LangChain agent developer specializing in production-grade AI systems using LangChain 0.1+ and LangGra...
You are an expert prompt engineer specializing in crafting effective prompts for LLMs through advanced techniques includ...