pr-creator
GitHub Pull Request creation specialist. Analyzes user requirements to create PRs with structured titles and bodies matching the user's query language. Handles git change analysis, PR draft creation, user confirmation, and final PR creation via gh CLI.
contextual-pattern-learning
Advanced contextual pattern recognition with project fingerprinting, semantic similarity analysis, and cross-domain pattern matching for enhanced learning capabilities
claude-plugin-validation
Comprehensive validation system for Claude Code plugins to ensure compliance with official plugin development guidelines and prevent installation failures
validation-standards
Tool usage requirements, failure patterns, consistency checks, and validation methodologies for Claude Code operations
model-detection
Universal model detection and capability assessment for optimal cross-model compatibility
testing-strategies
Provides test design patterns, coverage strategies, and best practices for comprehensive test suite development
ast-analyzer
Deep Abstract Syntax Tree analysis for understanding code structure, dependencies, impact analysis, and pattern detection at the structural level across multiple programming languages
autonomous-development
Comprehensive autonomous development strategies including milestone planning, incremental implementation, auto-debugging, and continuous quality assurance for full development lifecycle management
code-analysis
Provides methodologies, metrics, and best practices for analyzing code structure, complexity, and quality
Decision Frameworks
Decision-making methodologies, scoring frameworks, and planning strategies for Group 2 agents in four-tier architecture
documentation-best-practices
Provides templates, standards, and best practices for writing clear, comprehensive technical documentation
frontend-aesthetics
Distinctive frontend design principles for avoiding generic AI defaults, implementing thoughtful typography/color/animations, and creating polished user experiences based on Claude Code design research
fullstack-validation
Comprehensive validation methodology for multi-component applications including backend, frontend, database, and infrastructure
git-automation
Advanced Git operations automation including intelligent branching, commit optimization, release workflows, and repository health management
Group Collaboration
Best practices for inter-group communication, knowledge sharing, and collaborative workflows in four-tier architecture
gui-design-principles
Comprehensive design principles and best practices for creating beautiful, functional GUI applications including dashboards, web apps, and mobile apps
integrity-validation
Pre/post-operation validation to detect missing components and prevent future issues
pattern-learning
Enables autonomous pattern recognition, storage, and retrieval at project level with self-learning capabilities for continuous improvement
performance-scaling
Cross-model performance optimization and scaling configurations for autonomous agents
Predictive Skill Loading
Anticipates and pre-loads optimal skills before task execution based on pattern matching and historical success rates
quality-standards
Defines code quality benchmarks, standards compliance, and best practices for maintaining high-quality codebases
security-patterns
Comprehensive OWASP security guidelines, secure coding patterns, vulnerability prevention strategies, and remediation best practices for building secure applications
web-artifacts-builder
Modern web development patterns using React + Tailwind CSS + shadcn/ui for building production-quality, accessible, and performant web applications
web-search-fallback
Autonomous agent-based web search fallback for when WebSearch API fails or hits limits
web-validation
Comprehensive web page validation with authentication, screenshot capture, mobile testing, and enhanced error detection
github-repo-skill
Guide for creating new GitHub repos and best practice for existing GitHub repos, applicable to both code and non-code projects
goals-graph
Query and update Lee's goals graph through natural language. Translates conversational questions and updates into goals_query.py commands.
agent-team-orchestrator
|
bilibili-chapter-generator
|
langchain-use
LangChain 1.0 使用指南。提供 Agent、Tool、Memory、Middleware 等核心概念的快速参考。当用户需要创建 AI Agent、集成 LangChain、或解决 LangChain 相关问题时激活。
news-extractor
新闻站点内容提取。支持微信公众号、今日头条、网易新闻、搜狐新闻、腾讯新闻。当用户需要提取新闻内容、抓取公众号文章、爬取新闻、或获取新闻JSON/Markdown时激活。
slides-generator
Generate interactive presentation slides using React + Tailwind. Triggers on keywords like "slides", "presentation", "PPT", "demo", "benchmark".
srt-to-structured-data
|
opal-flow-lld
Create low-level design (LLD) documents for Opal frontend flows using the Flow LLD template. Use when asked to draft, fill out, or update a flow LLD for Opal.
opal-frontend-execplan
Guidance for creating and maintaining ExecPlans. Use when asked to create, update, or discuss an ExecPlan.
opal-frontend-review-guidelines
Automated review rules for opal-frontend PRs. Use when asked to review code, run @codex review, or provide PR feedback; apply severity levels and the required comment format.
thx-boris
Meta-workflow for using Claude Code effectively, based on patterns from Boris Cherny (Claude Code creator). Use when setting up a new project with Claude Code, optimizing an existing workflow, creating CLAUDE.md files, designing subagents, configuring hooks, or running parallel Claude sessions. Triggers on "how should I structure my CLAUDE.md", "create a subagent for X", "set up hooks", "optimize my Claude Code setup".
messages
Fuzzy search and browse Apple Messages/iMessage. Use when user asks to find texts, search messages, look up conversations, find what someone said, who texted recently, or view recent messages.
esphome-devices
>
home-assistant-automation
>
node-red
>
ha-integration-dev
>
agent-workflow
Expert system for designing and architecting AI agent workflows based on proven Meta methodologies. Use when users need to build AI agents, create agent workflows, solve problems using agentic systems, integrate multiple tools into agent architectures, or need guidance on agent design patterns. Helps translate business problems into structured agent solutions with clear scope, tool integration, and multi-layer architecture planning.
prd-writer
Full 5-stage PRD framework for complex features. Use for deep PRD work via /spec --deep full-prd. For quick feature specs, use /spec --feature instead.
context-engineering
[ARCHIVED] Full 4D Context Canvas reference. For new AI features, use /spec --ai. For debugging, use /ai-debug. For quality checks, use /context-check.
prompt-engineering
Expert prompt optimization system for building production-ready AI features. Use when users request help improving prompts, want to create system prompts, need prompt review/critique, ask for prompt optimization strategies, want to analyze prompt effectiveness, mention prompt engineering best practices, request prompt templates, or need guidance on structuring AI instructions. Also use when users provide prompts and want suggestions for improvement.
agency-ladder
Plan the v1→v2→v3 agency progression for AI features. Walk through mapping how autonomy increases over time, define promotion criteria, and generate artifacts for stakeholder alignment. Based on CC/CD framework.
ai-cost-check
Calculate AI feature costs and challenge if you actually need it. Invokes ai-cost-analyzer agent for detailed economics modeling.
ai-debug
Diagnose why an AI feature is underperforming, hallucinating, or behaving inconsistently. Uses 4D audit to work backwards from symptoms to root cause.
ai-health-check
Pre-launch health check that blocks you from shipping broken AI features. Grades 6 dimensions (model selection, data quality, cost, monitoring, failure UX, optimization).
Page 1280 of 1444 · 72183 results