精选 Skills 索引（第 167 页）
按质量分排序的前 8,000 个 Skills，每个都有可收录的独立页面。需要全库 15.8 万条检索时，请使用 Skills 目录。
- guardrails-ai-setup
Guardrails AI validation framework setup for LLM applications. Implement input/output validation, safety checks, and structured output enforcement.
- haystack-pipeline
Haystack NLP pipeline configuration for document processing and QA
- help-text-formatter
Generate formatted help text with examples, descriptions, sections, and consistent styling for CLI applications.
- homebrew-formula-generator
Generate Homebrew formula for CLI distribution on macOS and Linux.
- hook-management
Session-scoped hook lifecycle management with enable/disable/status controls, execution profiling, and color-coded performance alerts.
- hotfix-triage
Urgent issue classification, root cause analysis, and fast-path routing for production hotfixes
- huggingface-classifier
Hugging Face transformer model fine-tuning and inference for intent classification
- implementation-execution
Execute development tasks to build features, producing code, tests, and configuration artifacts that satisfy specification requirements and comply with constitution standards.
- ink-component-generator
Generate Ink (React for CLI) components for terminal UIs with hooks, state management, and layout components.
- inquirer-prompt-generator
Generate interactive command-line prompts using Inquirer.js with validation, conditional logic, and custom renderers. Creates user-friendly input collection flows for CLI applications.
- interview-problem-bank
Curated bank of interview problems organized by company, pattern, and difficulty. Provides problem recommendations, coverage tracking, weak area identification, and premium problem alternatives for FAANG interview preparation.
- interview-simulator
Simulate realistic coding interview experience
- invariant-analyzer
Identify and verify loop invariants for correctness proofs
- issue-tracking
Track beads as git-backed issues with persistent attribution, supporting Gas Town's bead lifecycle and convoy progress monitoring.
- knowledge-curation
Context priming before work (bd prime) and self-reflection after completion to extract patterns, gotchas, and decisions into the knowledge base.
- knowledge-graph-management
Capture, validate, query, and sync architectural patterns and design decisions in the knowledge graph
- langchain-chains
LangChain chain composition including SequentialChain, RouterChain, and LCEL patterns
- langchain-memory
LangChain memory integration including ConversationBufferMemory, ConversationSummaryMemory, and vector-based memory
- langchain-react-agent
LangChain ReAct agent implementation with tool binding for reasoning and action loops
- langchain-retriever
LangChain retriever implementation with various retrieval strategies for RAG applications
- langchain-tools
LangChain tool creation and integration utilities for agent systems
- langfuse-integration
LangFuse LLM observability integration for tracing, analytics, and cost tracking
- langgraph-checkpoint
LangGraph checkpoint and persistence configuration for stateful workflow management
- langgraph-hitl
Human-in-the-loop integration for LangGraph workflows with approval and intervention points
- langgraph-routing
Conditional edge routing and state-based transitions for LangGraph workflows
- langgraph-state-graph
LangGraph StateGraph builder with state schema design. Create stateful agent workflows with cycles, conditionals, and persistence.
- langgraph-subgraph
Subgraph composition and modular workflow design for LangGraph
- langsmith-tracing
LangSmith tracing and debugging setup for LLM applications. Configure observability, capture traces, and enable debugging for LangChain/LangGraph agents.
- leetcode-problem-fetcher
Fetch and parse LeetCode problems with metadata, constraints, examples, hints, difficulty ratings, and related problems. Integrates with LeetCode API for comprehensive problem data retrieval.
- line-ending-normalizer
Normalize line endings for cross-platform file handling with CRLF/LF conversion and git configuration.
- llamaindex-agent
LlamaIndex agent and query engine setup for RAG-powered agents
- llm-classifier
LLM-based zero-shot and few-shot classification for flexible intent detection
- maintenance-orchestration
Technical debt management including branch cleanup, doc verification, TODO scanning, and dependency auditing
- mcp-app-scaffolding
Scaffolds MCP App project structure with correct directory layout, dependencies, entry points, and framework-specific templates. Handles React (useApp hook), Vanilla JS, Vue, Svelte, Preact, and Solid.
- mcp-app-verification
Comprehensive verification checklists for MCP Apps. Tests with basic-host reference, validates handler-before-connect, text fallback, resource URI linking, single-file bundling, host styling, CSP, and legacy pattern detection.
- mcp-capability-declarator
Generate MCP capability declarations from tool and resource inventory with proper versioning and feature flags.
- mcp-csp-investigation
Comprehensive Content Security Policy audit for MCP Apps in sandboxed iframes. Discovers all network origins, traces them to source, and generates CSP configuration for registerAppResource.
- mcp-error-code-mapper
Map application errors to MCP error codes with proper messages, error types, and recovery suggestions.
- mcp-host-styling-integration
Integrates MCP App UI with host theming system. Applies host CSS variables, handles onhostcontextchanged, safe area insets, display mode detection, and fullscreen configuration.
- mcp-inspector-integration
Set up MCP Inspector for debugging and testing MCP servers with request logging, response inspection, and protocol validation.