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。
Core Kyora Agent OS workflows for task routing, delegation, handoffs, and recovery. Use when: routing a new task through the OS, delegating work between agents, creating handoff packets at phase boundaries, rec...
Ask the oracle (GPT-5.2 with deep reasoning) strategic technical questions. Use for architecture decisions, complex debugging, security analysis, or when you need a second expert opinion. Supports background ex...
Analyze the current session to extract learnings from mistakes and successes. Creates or updates project skills and CLAUDE.md with actionable patterns. Use after completing a task or when you notice repeated fr...
Create new GitHub Copilot agents with proper structure and frontmatter. Use when asked to create a skill, make a new agent, or scaffold agent files.
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...
Comprehensive reference of Claude Code features. Use when asking about Claude Code capabilities, hooks, skills, agents, plugins, or configuration.
Review, update, and synchronize agent instructions and configs across Codex and Claude (and optionally VS Code/Copilot); use when creating or refactoring agent prompts, skills, or chatmodes (trigger keywords: a...
Browser automation CLI for AI agents. Use this skill to navigate websites, interact with elements, take screenshots, and extract data using a headless browser.
This skill should be used when the user mentions "ideas", "IS", "idea storer", "check my ideas", "what should I work on", "project ideas", "pending features", or asks about brainstorming. Reads and interprets s...
Activates when user requests API design, RESTful conventions, interface specifications, OpenAPI documentation, or API security best practices. Do NOT use for database schema implementation. Examples: 'Design RE...
Scan skill roadmaps and output Web-agent-ready task prompts for autonomous overnight work. Use when "prep overnight tasks", "what can run tonight", "overnight-ready tasks", "autonomous tasks".
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...
Perform comprehensive data analysis, statistical modeling, and data visualization by writing and executing self-contained Python scripts. Use when you need to analyze datasets, perform statistical tests, create...
Get an external senior game developer's critique of the project. Reviews usefulness, identifies issues, and suggests features.
Swagger automation and Generic response documentation.
Use this skill when the user says 'run ralph', 'start ralph loop', 'execute the plan with ralph', '/ralph-plan', 'ralph this plan', or wants to run an approved plan autonomously using the Ralph Wiggum technique...
Execute PhD Pipeline Phase 8 using Claude Code Task tool with dynamic agents per chapter
Generate narrative summaries from git history for onboarding, retrospectives, changelogs, and exploration. LLM-enhanced when available, works without LLM too.
Interact with Google's Gemini model via CLI. Use when needing a second opinion from another LLM, cross-validation, or leveraging Gemini's Google Search grounding. Supports multi-turn conversations with session...
Create event hooks for Claude Code that trigger on specific events. Generate hooks with proper JSON configuration for automating workflows. Use when creating hooks, setting up event triggers, automating on file...
Extracts architectural, business, and operational context from existing systems. Use to build mental models of unfamiliar codebases.
Kyora Agent OS lane workflows: Discovery, Planning, Implementation, Review, Validation, Recovery. Use when routing tasks through lanes, understanding lane-specific outputs, applying lane handoffs, or resuming w...
Generate a structured AI session summary including task info, models used, and actions taken, saved as a Markdown file.
Strategic orchestrator for complex coding tasks. Use when implementing features, refactoring code, or any multi-step development work. Coordinates specialized subagents for file exploration, code search, editin...
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。