Loading...
Loading...
Found 845 Skills
Resolve queries or URLs into compact, LLM-ready markdown using a low-cost cascade. Prioritizes llms.txt for structured docs, uses web fetch/search tools for extraction. Use when you need to fetch documentation, resolve web URLs to markdown, search for technical content, or build context from web sources.
Update AGENTS.md and agent_docs/ following best practices. Use when modifying agent guidelines, adding new documentation, or restructuring agent instructions.
Dynamically validate that the implemented codebase matches architectural decisions documented in plan files. Use when validating implementation matches planning documents, checking for architecture drift, or preparing for architecture reviews.
Validates YAML syntax and structure for all .yml and .yaml files in the project. Identifies common issues like invalid syntax, indentation errors, missing keys, type mismatches, and provides fixes. Use when editing, creating, or debugging YAML configuration files.
Domain-specific testing patterns for episodic memory operations. Use when testing episode lifecycle, pattern extraction, reward scoring, or memory retrieval.
Create new Claude Code skills with proper structure, YAML frontmatter, and best practices. Use when creating reusable knowledge modules, adding specialized guidance, or building domain-specific expertise.
Complete and score a learning episode to extract patterns and update heuristics. Use when finalizing a task to enable pattern extraction and future learning.
Cheat sheet + workflow for launching interactive coding-agent CLIs (Claude Code, Gemini CLI, Codex CLI, Cursor CLI, and pi itself) via the interactive_shell overlay or headless dispatch. Use for TUI agents and long-running processes that need supervision, fire-and-forget delegation, or headless background execution. Regular bash commands should use the bash tool instead.
Use when designing domain error handling. Keywords: domain error, error categorization, recovery strategy, retry, fallback, domain error hierarchy, user-facing vs internal errors, error code design, circuit breaker, graceful degradation, resilience, error context, backoff, retry with backoff, error recovery, transient vs permanent error, 领域错误, 错误分类, 恢复策略, 重试, 熔断器, 优雅降级
Coordinate multiple specialized Skills and Task Agents through parallel, sequential, swarm, hybrid, or iterative execution strategies. Use when orchestrating multi-worker workflows, managing dependencies, or optimizing complex task execution with quality gates.
This skill should be used when the user asks to "draw an architecture diagram", "create architecture diagram", "generate architecture", "画架构图", "生成架构图", "绘制架构图", or mentions architecture, microservice architecture, frontend architecture (Vue/React), system architecture, deployment architecture, technology architecture, or needs to visualize system structure with components and connections.
Use when user describes a complex project goal, wants to set up multiple skills at once, asks "what skills do I need for X", or needs to manage installed skill bundles. Triggers on multi-skill setup, skill combination, project bootstrapping, or batch skill management.