prompt-writing
Use when writing or editing ALTO prompts - templates/CLAUDE.md.*, agents/*.md, or skills/*/SKILL.md. Rules for explicit tool references, paths, and user interactions.
orchestration
Coordinates other skills and agents. ALWAYS use this skill on startup.
rag-service
高性能 RAG 多路检索服务。集成 Milvus 向量数据库进行语义检索，并结合 Rerank 模型进行精准重排序，支持海量文档的高效存储与历史内容召回。
ai-integration
Specialized skill for integrating AI features using OpenAI API. Use when implementing chatbots, content generation, or AI-powered educational features.
bulk-generate-concepts
Use when generating multiple curriculum-aligned concept files in parallel (5+ concepts) - researches curriculum, creates concept list, spawns parallel generation agents, orchestrates review loop until all pass
agent-development
Use when the user wants to design Codex agent equivalents (specialized workers/profiles/prompt files), define triggering conditions, or build reusable agent prompts and validation tools.
ml-researcher
ML research for RAN with reinforcement learning, causal inference, and cognitive consciousness integration. Use when researching ML algorithms for RAN optimization, implementing reinforcement learning agents, developing causal models, or enabling AI-driven RAN innovation.
using-beadpowers
Use when starting any conversation - establishes how to find and use beadpowers skills
never-guess
Behavioral principle ensuring Claude never guesses when uncertain. Use when Claude's response involves facts it cannot verify, technical claims, or any statement where accuracy matters. Complements resolve-ambiguity skill.
wolf-archetypes
Behavioral archetypes for automatic agent adaptation based on work type
orchestrator-agent
Advanced orchestration agent for managing subagents, commands, MCP servers, and skills with parallel execution capabilities
agentdb-learning-plugins
Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more. Use when building self-learning agents, implementing RL, or optimizing agent behavior through experience.
startupo-lite
RAG-first ORCHESTRATOR startup. Minimal context (~500 tokens), queries RAG on-demand. Token-efficient alternative to startupO.
vector-search-designer
Design vector similarity search systems for semantic retrieval at scale
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). | Sử dụng khi: tạo MCP server, xây dựng tool server.
code-discovery
Helpers to discover, rank, and invoke repository symbols from natural language with minimal context.
ekkos-preferences
Capture user preferences as permanent directives. Activate when the user says "always", "never", "I prefer", "I like", "don't", "avoid", expresses a coding style preference, states a workflow requirement, or corrects you about how they want things done. These become rules that apply to all future sessions.
abductive-repl
Hypothesis-Test Loops via REPL for Exploratory Abductive Inference
skills-sync
Sync Claude Code skills from the ChillSkills GitHub repository
claude-hooks
Guide for creating hooks that trigger actions in response to Claude Code events
openapi-toolkit-ollama-dart
Automates updating ollama_dart when Ollama OpenAPI spec changes. Fetches latest spec, compares against current, generates changelogs and prioritized implementation plans. Use for: (1) Checking for API updates, (2) Generating implementation plans for spec changes, (3) Creating new models/endpoints from spec, (4) Syncing local spec with upstream. Triggers: "update api", "sync openapi", "new endpoints", "api changes", "check for updates", "update spec", "api version", "fetch spec", "compare spec", "what changed in the api", "implementation plan".
