llm-ai
2
langfuse-observability
LLM observability with self-hosted Langfuse 3.x - tracing, evaluation, monitoring, prompt management, and cost tracking
yonatangross
data-ai
sorting
stars
current ordering strategy
query
all entries
refine the visible subset
llm-ai
2
random-walk-fusion
Navigate skill graphs via deterministic random walks. Fuses derivational chains, algebraic structure, color determinism, and bidirectional flow for skill recombination.
plurigrid
data-ai
llm-ai
2
orchestrate
When orchestrating tasks, load this core skill first to understand the general methodology.
djgrant
data-ai
llm-ai
2
mcp-pal-usage
Ensures proper use of PAL MCP tools (thinkdeep, debug, codereview, consensus, planner) for complex tasks requiring deep analysis, multi-model collaboration, or systematic investigation. Auto-activates when: - User requests debugging, code review, or planning assistance - Complex problems require systematic investigation - Multi-model consensus needed for architectural decisions - Deep thinking required for root cause analysis Provides guidance on: - When to use each PAL MCP tool - Proper continuation_id management - Model selection strategies - Workflow orchestration patterns
jukasdrj
data-ai
llm-ai
2
elevenlabs-voice-cloning
ElevenLabs voice cloning techniques, audio quality requirements, recording best practices, and training data optimization for professional-quality voice clones. Use when creating custom voices, cloning voices, or optimizing voice clone quality.
onesmartguy
data-ai
llm-ai
2
instruction-optimizer
Use when instruction files (skills, prompts, CLAUDE.md) are too long or need token reduction while preserving capability. Triggers: "optimize instructions", "reduce tokens", "compress skill", "make this shorter", "too verbose".
axiomantic
data-ai
llm-ai
2
parallel-fanout
Metaskill that fans out on every interaction, using interaction entropy
plurigrid
data-ai
llm-ai
2
moai-context7-lang-integration
Enterprise-grade Context7 MCP integration patterns for language-specific documentation access with real-time library resolution and intelligent caching
AJBcoding
data-ai
llm-ai
2
claude-agents
Guide for creating custom agents for Claude Code with specialized behaviors and tools
vinnie357
data-ai
llm-ai
2
skills-authoring
Creates or updates skills with proper YAML frontmatter, progressive disclosure, and best practices per the open Agent Skills specification. Supports simple, tool-restricted, multi-file, and script-based skills. Use when creating new skills, authoring skills, extending agent capabilities, or when `--create-skill` or `--new-skill` flag is mentioned.
galligan
data-ai
llm-ai
2
finetune-design
Use when preparing to fine-tune an LLM for multi-turn conversations, before generating any training data. Triggers - starting a fine-tuning project, need to define evaluation criteria, designing conversation data generation.
marcgreen
data-ai
llm-ai
2
crawl4ai
This skill should be used when users need to scrape websites, extract structured data, handle JavaScript-heavy pages, crawl multiple URLs, or build automated web data pipelines. Includes optimized extraction patterns with schema generation for efficient, LLM-free extraction.
basher83
data-ai
llm-ai
2
langgraph-patterns-expert
Build production-grade agentic workflows with LangGraph using graph-based orchestration, state machines, human-in-the-loop, and advanced control flow
frankxai
data-ai
llm-ai
2
update-inst
user-level指示の更新。Claudeが間違いを犯した際に、再発防止のためCLAUDE.md/context/を更新。`/update-inst <間違えた内容>` で使用。
ukwhatn
data-ai
llm-ai
2
incentive-prompting
Research-backed prompting techniques for improved AI response quality (+45-115% improvement). Use when optimizing prompts, enhancing agent instructions, or when maximum response quality is critical. Invoked by /ai-eng/optimize command. Includes expert persona, stakes language, step-by-step reasoning, challenge framing, and self-evaluation techniques.
v1truv1us
data-ai
llm-ai
2
wechat-chat-tool
微信小程序聊天工具开发指南。当开发聊天工具分包、配置 chatTools、发送消息到群聊、动态消息、获取群成员信息、wx.openChatTool、wx.getChatToolInfo 时使用。
dafang
data-ai
llm-ai
2
instruction-engineering
Use when: (1) constructing prompts for subagents, (2) invoking the Task tool, or (3) writing/improving skill instructions or any LLM prompts
axiomantic
data-ai
llm-ai
2
sequential-thinking
Use for atypically complex problems requiring explicit step-by-step reasoning. Skill autonomously decides if sequential-thinking MCP overhead is justified based on problem complexity.
Shavakan
data-ai
llm-ai
2
moai-mcp-builder
Enterprise MCP (Model Context Protocol) server development using FastMCP 2.0 with production-grade tools, resources, prompts, and intelligent agent-first design. Use when building MCP servers, integrating with LLMs, creating agent tools, implementing RAG systems, or developing protocol-based AI integration solutions.
AJBcoding
data-ai
llm-ai
2
generate-llms
Generate llms.txt and llms-full.txt files for AI agent consumption following the llmstxt.org standard. Use when updating site content that should be reflected in the llms files, or when building/deploying the site.
jonmagic
data-ai
llm-ai
2
sdv-session-start
ALWAYS invoke this skill FIRST at session start, after context reset/compaction, or when user mentions "reset", "new session", "where were we", "what was I working on". Do NOT skip this for specific task requests—orient first, then execute. This is Rule 0.
liminalwarmth
data-ai
llm-ai
2
checkpoint-trigger
Natural language wrapper for checkpoint commands - automatically triggers /checkpoint:create, /checkpoint:restore, /checkpoint:list when users request checkpoint operations
grandinh
data-ai