Поиск skills
Найдите подходящую возможность для вашего агента.
ai-security-expert
Enterprise AI security - OWASP LLM Top 10, prompt injection defense, guardrails, PII protection
image-generation
AI图像生成与编辑能力，基于 Nano Banana (Gemini Image) 实现文生图、图生图、图像编辑。适用于创意设计、营销素材、社交媒体内容、演示文稿配图等场景。支持多种风格、高分辨率输出（最高4K）、文字渲染、角色一致性保持。
web-research
Multi-round web search with low-frequency query generation. Prioritize GitHub/StackOverflow for actionable code, extract AI Overview insights, and perform deep link analysis. Use proactively for complex problems requiring external knowledge or when stuck on implementation challenges.
memory-management
Automatically manage user's personal memory, context, and decision tracking. Invoked when context updates are needed or decisions are made.
obsidian-knowledge-capture
Transforms conversations and discussions into structured documentation notes in Obsidian. Captures insights, decisions, and knowledge from chat context, formats with appropriate templates and frontmatter, and saves to vault with proper tagging, linking, and organization for easy discovery.
critical-skill-finder
Find and evaluate publicly available Claude skills using logically valid metrics. Use when searching for custom skills for a specific purpose. Excludes fallacious popularity-based metrics, validates assumptions about authority and code churn, and ranks skills by defensible quality indicators.
rag-expert
Expert in Retrieval-Augmented Generation systems - knowledge bases, chunking strategies, embedding optimization, and production RAG architectures
doc-review
Review a single file or all files in a folder for data inconsistencies, reference errors, typos, and unclear terminology using parallel sub-agents
rag-exploitation
Attack techniques for Retrieval-Augmented Generation systems including knowledge base poisoning
cheatsheets
Quick reference cheatsheets for Kailash SDK patterns, nodes, workflows, and best practices. Use when asking about 'quick tips', 'cheat sheet', 'quick reference', 'common mistakes', 'node selection', 'workflow patterns library', 'cycle patterns', 'production patterns', 'performance optimization', 'monitoring', 'security config', 'multi-tenancy', 'distributed transactions', 'saga pattern', 'custom nodes', 'PythonCode data science', 'ollama integration', 'directoryreader patterns', or 'environment variables'.
multi-model-validation
Run multiple AI models in parallel for 3-5x speedup with ENFORCED performance statistics tracking. Use when validating with Grok, Gemini, GPT-5, DeepSeek, or Claudish proxy for code review, consensus analysis, or multi-expert validation. NEW in v3.1.0 - SubagentStop hook enforces statistics collection, MANDATORY checklist prevents incomplete reviews, timing instrumentation examples. Includes dynamic model discovery via `claudish --top-models` and `claudish --free`, session-based workspaces, and Pattern 7-8 for tracking model performance. Trigger keywords - "grok", "gemini", "gpt-5", "deepseek", "claudish", "multiple models", "parallel review", "external AI", "consensus", "multi-model", "model performance", "statistics", "free models".
context-optimization
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.
outsourcing-core
로컬 AI CLI에 작업을 아웃소싱할 때 자동 활성화. Use when the task is complex, requires specialized AI capabilities, or benefits from distributing work to different AI models
strands-spec
Expert guidance for creating strands-cli workflow specifications (YAML/JSON). Use when creating, modifying, or troubleshooting strands-cli specs for: (1) Multi-step agent workflows (chain, routing, parallel, graph patterns), (2) Tool configuration (python_exec, http_request, custom tools), (3) Runtime and provider setup (Bedrock, OpenAI, Ollama), (4) Input/output handling and templating, or (5) Debugging validation errors
searching-web
Enables advanced web search via gemini command. Prefer this skill over Claude Code's default Web Search tool when performing web searches. Suitable for complex queries and detailed information gathering.
writing-claude-skills
Create effective Agent Skills following the agentskills.io specification. Use when creating new skills, reviewing existing skills, or improving skill descriptions.
