agents-md-improver
Keeps repo-local agent instructions consistent by proposing updates to AGENTS.md when a user corrects the coding agent or asks to change AGENTS.md, CLAUDE.md, .claude/CLAUDE.md, or GEMINI.md.
发现 documentation 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。
Keeps repo-local agent instructions consistent by proposing updates to AGENTS.md when a user corrects the coding agent or asks to change AGENTS.md, CLAUDE.md, .claude/CLAUDE.md, or GEMINI.md.
Use to set up Obsidian vault and populate it with existing codebase knowledge. Enables context memory for AI development.
Use to identify and prepare the next logical story based on project progress. Creates comprehensive story files with full technical context.
Create custom Claude Code sub-agents with specialized expertise and tool access. Use when you need to build reusable agents for specific tasks like code review, debugging, data analysis, or domain-specific work...
Build efficient, scalable Claude Code skills using progressive disclosure and token optimization. Use when creating new skills, optimizing existing skills, or learning skill development patterns. Provides templ...
Use to assess and document risk factors for stories or features. Creates risk profiles with mitigation strategies.
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
Multi-agent brainstorming with Critic, Creative, and Pragmatist perspectives
Integrate Claude agents into training and live trading (v3.0). Trigger when: (1) setting up multi-agent training, (2) adding agent consultation to live trading, (3) configuring orchestrator, (4) understanding a...
Expert guidance for Convex backend development including queries, mutations, actions, schema design, and real-time database patterns. Use when working with Convex functions, database operations, or serverless b...
Design patterns for automatic skill activation at plugin or project level. Use when implementing keyword-based skill suggestions.
Virtual test environment for Claude Code hooks, plugins, and agents. Use when testing or validating plugin components without affecting production.
Comprehensive Claude Code hook patterns for automation, state management, and external integration. Use when implementing hooks for validation, workflow gates, MCP integration, or state machines.
Analyze vague user ideas and recommend architecture based on actual needs, not predefined categories. Front-end for clarifying ambiguous requests before routing to appropriate skillmaker tools.
LLM invocation patterns from hooks via SDK. Use when you need background agents, CLI calls, or cost optimization.
U-llm-sdk and claude-only-sdk patterns. Use when working on projects with LLM service, designing LLM integrations, or implementing AI-powered features.
Claude Code Hook system entry point. Guides you to the right skill based on your needs.
Single-skill vs multi-skill subagent architectures. Use when designing subagents.
Smart routing wizard for creating skills, agents, commands with complexity-based skill loading
Context isolation for query-type MCP tools (LSP, search, database) via external CLI. Use when MCP query results consume too many context tokens.
Generate and execute SQL queries against the civitai_records PostgreSQL database to analyze video performance on Civitai. Use when users ask about: video engagement metrics (likes, hearts, comments), content pe...
Generate, edit, or transform images with Gemini Nano Banana using bundled Python scripts (Flash or Pro) including aspect ratio, resolution, image-to-image edits, logo overlays, and reference images. Use when us...
Automatically fetch and summarize the latest AI news, research, and industry developments. Use when users request: (1) Daily AI news updates, (2) Latest AI technology developments, (3) Recent AI research papers...
Session start/end workflows for Claude Family
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。