context-metrics
View session and context metrics for dogfooding optimization. Use when analyzing whether knowledge injection is helping, understanding context usage patterns, or optimizing the knowledge system.
Discover devops llm ai skills, compare source repositories and read the instructions for each workflow.
View session and context metrics for dogfooding optimization. Use when analyzing whether knowledge injection is helping, understanding context usage patterns, or optimizing the knowledge system.
Query the knowledge graph for learnings, patterns, and mistakes. Use when you need to find past learnings, avoid known mistakes, discover established patterns, or search for relevant knowledge before implementi...
Manage session lifecycle, learning extraction, and context metrics. Use when starting/ending sessions, analyzing workflows for learnings, querying knowledge graph, or checking session metrics.
Connect Claude to any app. Send emails, create issues, post messages, update databases - take real actions across Gmail, Slack, GitHub, Notion, and 1000+ services.
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, rou...
Process multimodal documents using Gemini CLI, leveraging Gemini's superior multimodal capabilities. Use for PDFs, scanned documents, image-heavy documents, or any file where visual understanding matters. Ideal...
Apply personal writing style when drafting documents, notes, or any written content. Triggers when user asks to write, draft, create content, or requests style application. Does NOT affect conversation tone - o...
Use when working with embeddings, semantic similarity, vector search, or the operators. Load for pgvector queries, HNSW index creation, embedding storage, or similarity calculations. Covers distance operato...
Use when you notice a pattern that should be in the config. Analyzes current setup, researches best practices, and proposes specific config changes. Also use when asked to improve agent behavior or workflows.
Use when working with trait extraction, place enrichment, or the learning loop. Load for understanding how the system learns from gameplay, how traits are extracted from Nominatim + player sessions, async queue...
Use when orchestrating subagents for implementation. Covers when to dispatch vs recall, how to scope tasks, session management, and handoff patterns. Load this before working with any subagent.
Use this skill when optimizing Leavn's App Store presence, researching keywords, or responding to reviews.
Use this skill when conducting competitor analysis, sentiment monitoring, or user research for Leavn.
Use this skill when creating devotional content, social media posts, or video scripts for Leavn marketing.
Use this skill when delegating complex autonomous tasks to Manus AI - an AI agent that can browse the web, execute code, generate files, and comple...
Design and build Glif AI workflows. Use when creating new glifs, planning workflow structure, or understanding block types.
Work with Leavn search system - UnifiedSearchService, FTS5 database, 50ms debounce, content filtering, search history
You are the podcast RSS feed parsing specialist for Modcaster.
Run Glif workflows via API. Use when executing AI image/text generation workflows or integrating Glif into apps.
Work with Leavn AI features - UnifiedAIService, on-device models, devotional generation, novelization, kids mode, image generation with Stable Diffusion
Work with Leavn audio systems - TTS, sermon recording, guided mode audio, ambient sounds, voice profiles, audio orchestration
AI capabilities in n8n - agents, LangChain, vector stores, LLM providers, RAG, AI workflows
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...
Gerencia embeddings vetoriais do CarInsight para busca semântica
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.