В каталоге 183 730 навыков в 14 категориях.
Comprehensive guide for deploying LLMs locally using Ollama, vLLM, and llama.cpp. Local deployment offers privacy, cost...
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services...
当使用者说"让 AI 写谱不要直接生成音频"、"做一个 AI 作曲的后端"、"LLM 输出 MIDI 怎么做"、"生成的音符老是越界/被截断"、"要能导出 .mid 给 DAW"时使用。用 LLM（BYOK / OpenAI 兼容接口）从零...
Choosing the right model for the task — power vs. cost vs. speed.
Access Claude, Gemini, Kimi, GLM and 100+ LLMs via inference.sh CLI using OpenRouter. Models: Claude Opus 4.5, Claude So...
Local LLM health checks and cache management. Probe Ollama/vLLM/SGLang endpoints, clean model caches.
Review or plan changes that affect prompts, model output validation, fallback behavior, or LLM-driven decisions.
AI-first application patterns, LLM testing, prompt management
Pydantic-AI agents, RAG, embeddings for Pulse Radar knowledge extraction.
Plan and execute large language model pretraining from data preparation to checkpoint management
Use when improving prompts for any LLM. Applies proven prompt engineering techniques to boost output quality, reduce hal...
Optimize prompts for better LLM outputs through systematic analysis and refinement
Generate multiple LLM responses using diverse system prompt variants to increase reasoning diversity for self-consistenc...
LeeWay-governed LLM Prompting and Engineering workflow. Use when a task requires llm prompting procedures, validation, a...
Set up a new LLM provider connection, discover valid model ids, create and validate a model profile — securely and end-t...
Selects the optimal LLM model and provider for each task based on complexity, cost budget, and capability requirements....
LLM streaming response patterns. Use when implementing real-time token streaming, Server-Sent Events for AI responses, o...
Build production LLM streaming UIs with Server-Sent Events, real-time token display, cancellation, error recovery. Handl...
Entfernt KI-Spuren, Chat-Reste, Platzhalter und LLM-Stilmuster aus fertigen Texten und prüft die AI-Disclosure auf Volls...
See the main LLM Cost Optimization skill for comprehensive coverage of token economics and optimization strategies.
LLM Tuning Patterns
LLM Text Protocol provides standardized patterns for text-based interactions with language models. It encompasses prompt...
LLMOps — RAG 운영, 프롬프트 버전 관리, Ragas 기반 LLM 평가, NeMo 가드레일. Use when LLM 앱을 운영 환경에서 품질 평가하고 프롬프트 변경을 관리하거나 가드레일을 붙일 때.
Generate an llms.txt file for any project or website following the llmstxt.org specification. Use when asked to create l...
Detect and use llms.txt files for LLM-optimized documentation. Use when checking if a site has LLM-ready docs before scr...
Decides and audits what a WordPress site opens to AI crawlers, robots.txt, llms.txt, Content-Signal. Use for robots IA,...
Build and use a persistent, citation-traceable knowledge wiki from documents, research papers, notes, or project documen...
Syncs skills and MCP settings from Claude Code to Gemini CLI and Codex CLI. Use when agent configs need alignment after...
Universal context reviewer: delegates arbitrary context (plans, decisions, documents, architecture proposals) to externa...
Multi-agent context review: delegates plans, decisions, documents, architecture proposals to external agents (Codex + Ge...
Audits CLAUDE.md, AGENTS.md, GEMINI.md for token budget, prompt cache safety, compact instructions, and cross-agent cons...
Creates AGENTS.md canonical and CLAUDE.md @AGENTS.md stub; audits token budget, cache safety, import-pattern compliance....
Meta-orchestrator (L0): reads kanban board, lets user pick ONE Story, drives it through pipeline 300->310->400->500 via...
Drives a Story through full pipeline (tasks, validation, execution, quality). Use when executing a Story end-to-end from...
Extracts procedural content from project docs into .claude/commands skills. Use when docs contain deploy, test, or troub...
Creates .claude/commands from procedural doc sections. Use when transforming documentation prose into executable skill f...
Validates Stories, plans, or context via parallel multi-agent review with GO/NO-GO verdict. Use when changes need cross-...
Worker that runs parallel external agent reviews (Codex + Gemini) on Story/Tasks. Background tasks, process-as-arrive, c...
Use when accepted findings require bounded repair changes and a structured repair summary.
Use when an evaluation run must merge research, findings, documentation, and repair outputs into one verified result.
Use when an evaluation run requires bounded iterative refinement with trace and cleanup evidence.
Orchestrates Story tasks. Prioritizes To Review -> To Rework -> Todo, delegates to ln-401/ln-402/ln-403/ln-404. Sets Sto...
Validates optimization plan via multi-agent review before execution. Use when verifying feasibility of optimization hypo...
Load architecture principles and core conventions for grounding work against project standards - simple context loading...
Auto-load relevant memories at session start from both mem0 and graph. Use when you need session context restored or pre...
Load frontend design skill from Anthropic
Activates the Pickle Rick persona. Use this ONLY when the user explicitly requests to start the "Pickle Rick" mode or lo...
The one command that takes someone from nothing to a working local AI setup: scans their machine, asks what they want it...
local-finetune
Store AML case evidence in a local or network folder structure that supports audit trail, retention and reviewer access.
Guides users through the process of preparing datasets and fine-tuning local Large Language Models (LLMs) using techniqu...
Local Retrieval-Augmented Generation with vector search.
Set up and manage local skills for automatic matching and invocation
Expert guide for Local Small Language Models (SLMs) and Edge AI execution — WebLLM, Transformers.js v3, ONNX Runtime Web...
Generate speech locally from text using VoxCPM2 (2B params, Apache-2.0). 30 languages, voice design (describe a voice),...
Codex-local role pack for dialectic multi-agent reviews, designed to be compatible with the local vibe skill.
Umbrella/queue: only when queue or PRD in scope; named workflows; impact summary + user confirmation before big/destruct...
Push decisions to Arbiter Zebu for async human review. Use when you need human input on plans, architectural choices, or...
Communication and response guidelines, tool selection and enhancement, periodic context updates. Use for user communicat...
Localsetup v2 framework context - overview, invariants, and skills index. Load first when working in a repo that uses L...
Create or import Agent Skills–compliant skills for this framework; import skills from Anthropic or elsewhere; export fra...
Discover and recommend public skills from external registries (e.g. awesome lists, skill hubs). Use when the user is cre...
Normalize skills already in the tree for Agent Skills spec compliance and platform-neutral wording. Use when the user wa...
Match user tasks to installed Localsetup skills, recommend top matches, and run single-task or batch skill-selection flo...
Run LoCoMo benchmark for long-term conversational memory
Record agent run logs into .tmp/logs/. Use this to maintain an audit trail of agent actions and errors.
Log key learnings to progress.txt during PRD iteration. Use when you discover codebase patterns, encounter gotchas, make...
Use for Pydantic Logfire observability, tracing, and debugging. Query exceptions, spans, logs with SQL. View traces in L...
Guide for training outputs, metrics logging, logtree reports, tracing/profiling, and debugging training runs. Use when t...
Expert-thinking profile for Logician (proof theory / model theory / computability / set theory / formal verification (Le...
Generate logos with AI image tools using effective prompt structures,。Use when 需要设计创作、UI设计、海报制作、品牌视觉时使用。不适用于3D建模和动画制作。适用...
Master multi-agent swarm orchestration — coordinates personas across the 14-phase lifecycle (10-phase core build loop S0...
Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents acr...
Multi-agent autonomous startup system. Triggers on "Loki Mode". Takes PRD to deployed product with zero human interventi...
Multi-agent autonomous startup system - orchestrates 37 AI agents across 6 swarms to build, deploy, and operate a comple...
Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when pr...
Use when processing documents over 50K characters through LLM APIs with section splitting and batch cost reduction.
Multi-session agent harness for complex projects spanning many context windows — initialiser/coding agent cycle
长周期任务管理框架，基于 Anthropic 官方最佳实践，支持多代理协作、进度追踪、强制闭环。触发词：长任务、复杂项目、多会话、团队协作、子代理。
Check how an agent or a working session handles long conversations, covering tool-result clearing, compaction, what gets...
Long short portfolio construction, market neutral positioning, factor-balanced book, gross and net exposure management,...
Initialize or resume a long-running task session. Use when starting a complex multi-session task, resuming work from a p...
Machine-learning prediction strategy framework via Longbridge Securities — walk-forward rolling training with feature en...
Search Mathlib for lemmas by type signature pattern
Weave possible conversations from a session's accumulated context — take everything that has happened (every mood, threa...
Use when beads have tight sequential dependencies or count is small (under 8), or when simplicity is preferred over para...
Start autonomous iteration loop. Triggers on "loop", "keep going", "continue until done", "implement feature", "fix all"...
Execute workflow agents iteratively for refinement and progressive improvement. Use when tasks require repetitive refine...
在此 workspace 内就我想构建的工作流规格对我进行盘问。
Build 3D geological models with implicit surfaces, faults, folds, and stratigraphic constraints from structural geology...
Use when helping users configure LoRA training — select presets, understand parameters, and pick the right settings for...
Base extraction rules for all lore subagents. Governs entity identification, contextual analysis, relationship mapping,...
Extract lore and narrative device entities from text. Use when analyzing codex entries, bestiary entries, journals, drea...
Reference system prompt and tool schemas for Lovable. Use when imitating, comparing, or analyzing Lovable's prompting st...
Generates clickable Lovable.dev build URLs when users ask to build, create, or make any app, website, landing page, dash...
恋爱高手 (dating and relationship coaching) Master OS — automated mastery of dating and relationship coaching: top builders'...
Explain the one or two most relevant low-level runtime, memory, representation, or hardware mechanisms behind a current...
Load: ../shared/assessment/assessment-base-contract.md