fine-tune
Use when you need to fine-tune(ファインチューニング) and optimize LangGraph applications based on evaluation criteria. This skill performs iterative prompt optimization for LangGraph nodes without changing the...
发现 tools llm ai 相关 Skills,比较来源仓库和用途,查看适合你工作流的技能说明。
Use when you need to fine-tune(ファインチューニング) and optimize LangGraph applications based on evaluation criteria. This skill performs iterative prompt optimization for LangGraph nodes without changing the...
Analyze LangGraph application architecture, identify bottlenecks, and propose multiple improvement strategies
Use when specifying or implementing LangGraph applications - from architecture planning and specification writing to actual code implementation. Also use for designing agent workflows or learning LangGraph patt...
HOL4 interactive proof development. Use when working with HOL4 proofs, .sml theorem files, Holmake builds, or hol-agent-helper.sh sessions. (project)
Manages user preferences and learned knowledge with confidence scoring
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...
Generate images using Google's Nano Banana Pro (Gemini 3 Pro Image) with workflow-based prompting
Multi-LLM parallel research with query decomposition and synthesis
Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx file...
Orchestrate multiple frontier LLMs (Claude, GPT-5.1, Gemini 3.0 Pro, Perplexity Sonar, Grok 4.1) for comprehensive research using LLM Council pattern with peer review and synthesis
Generate content in your authentic voice across emails, blogs, social media, and reports
This skill should be used when the user asks to "create a plan", "plan the implementation", "design the approach", "break down the task", "write an implementation plan", or invokes the rpikit:plan command. Prov...
Deploy agents and skills with full verification. Single command deployment with rollout monitoring, health checks, and automatic rollback.
Create a new AI agent from template using kubani-dev CLI. Use when adding a new agent to the cluster, starting a new monitoring or automation project.
Rollback AI agent to a previous version. Use when reverting a deployment, undoing changes, or recovering from failed deploys.
Voyager-inspired continuous learning system with Critic Agent, Reflection Agent, and Discord-based approval workflow for skill proposals.
Build MCP (Model Context Protocol) servers for Claude Code integration. Use when creating tools, resources, or prompts that extend Claude's capabilities. Supports Python FastMCP and TypeScript implementations.
Run comprehensive agent evaluations using YAML-defined test suites with multiple evaluator types including automated, LLM-as-judge, and human review.
Complete guide for local agent development using kubani-dev CLI, unified configuration, MCP integration, and seamless iteration.
Manage and develop AI agents using kubani-dev CLI. Use for checking agent health, versions, deployment status, running tests, and evaluations.
Author and improve Agent Skills following the agentskills.io specification. Use when creating new SKILL.md files, modifying existing skills, reviewing skill quality, or organizing skill directories with proper...
Scaffolds a structured investigation in scratch/ for empirical research and documentation. Use when the user says "start an investigation" or wants to: trace code paths or data flow ("trace from X to Y", "what...
Execute pre-defined workflows step by step. Use when user wants to run a workflow or mentions "workflow". Each step is executed in isolation to maintain focus throughout multi-step tasks.
Get a specific vector entry by key. Requires authentication. Use for Agentuity cloud platform operations
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。