GitHub
gemini-memory-lifecycle
strategies for the agent memory lifecycle (Extraction, Consolidation, Retrieval). Use this to implement long-term learning and personalization beyond a single session.
☆ 0View skill
Browse skills
Explore AI skills for development, content, data and productivity. Compare the description and repository popularity before opening a skill.
Categories
Browse skills
GitHub
api-usage
How to use the OpenAI-compatible API server
☆ 0View skill
GitHub
agent-invocation
Agent invocation syntax and boundary rules
☆ 0View skill
GitHub
langchain-agent-builder
基于 LangChain 框架构建 AI Agent 机器人的技能。当用户需要创建 LangChain agent、选择 agent 框架、实现工具调用、管理对话记忆或构建复杂工作流时使用此技能。涵盖 LangGraph、CrewAI、AutoGen 等热门框架，提供最佳实践、...
☆ 0View skill
GitHub
minimax-mcp
MiniMax MCP server integration with token-efficient AI delegation. Use for web search, image analysis, MCP server integration in terminal/desktop Claude, and Claude-MiniMax collaboration patterns. Provides work...
☆ 0View skill
GitHub
team-comm-style
Process team communication style assessments at the individual level. Use when analyzing "What's My Communication Style" results, creating individual profiles, or preparing coaching notes.
☆ 0View skill
GitHub
kpi-calculation
Calculate and track key performance indicators (KPIs) from pilot data and defined metrics. Use when deriving success metrics, benchmarking performance against objectives, or preparing quantitative reports and d...
☆ 0View skill
GitHub
agent-handoffs
Agent parameter passing, memory files, and data handoffs between agents
☆ 0View skill
GitHub
template-skill
Replace with description of the skill and when Claude should use it.
☆ 0View skill
GitHub
pr-comment-auto
Wait for PR review comments, fix issues raised, summarise, and respond to reviewers automatically.
☆ 0View skill
GitHub
ralph-spec
Write Ralph specification documents - structured feature specs with clear requirements, acceptance criteria, and implementation guidance for autonomous task execution
☆ 0View skill
GitHub
multiplicity-orchestration
Run multiple AI instances in parallel, coordinate their execution, manage timing and dependencies
☆ 0View skill
GitHub
mcp-python-design
A strict protocol for architecting Model Context Protocol (MCP) servers using FastMCP Python SDK, enforcing Tools vs Resources separation, type safety for LLM schema generation, and context-first thinking.
☆ 0View skill
GitHub
bias-and-fairness-auditing
Audit pilot data, models, and workflows for bias and inclusivity issues. Use when evaluating fairness across demographic groups, identifying algorithmic biases, and recommending mitigation strategies to ensure...
☆ 0View skill
GitHub
think-ahead
AI thinking partner for strategy and planning. Reads the current work state, analyzes progress, and helps you plan the next phase while the worker instance builds. Triggered by "think ahead".
☆ 0View skill
GitHub
agent-framework
Build agentic AI solutions using Microsoft Agent Framework (Python). Use when creating AI agents, multi-agent workflows, chatbots, or assistants that need tool calling, streaming, orchestration patterns (sequen...
☆ 0View skill
GitHub
tooling-strategies
decision matrix for agent tools. Use this to choose between Extensions, Functions, and Data Stores based on security, execution location, and data type.
☆ 0View skill
GitHub
performance-monitor
自动监控 Claude Code 性能指标，包括操作耗时、失败率、效率评分，并提供语义化洞察
☆ 0View skill
GitHub
create-subagent
Create custom subagents for specialized AI tasks. Use when the user wants to create a subagent, set up task-specific agents, configure code reviewers, debuggers, or domain-specific assistants with custom prompt...
☆ 0View skill
GitHub
linebot-notebook-design
LINE Bot Flex Message 筆記樣式設計指南。包含 Flex Message 限制、卡片結構設計、圖片生成規範（matplotlib）、常見錯誤排解。適用於教育類、知識卡片類的 LINE Bot 開發。
☆ 0View skill
GitHub
recover-quota
LLMのクオータ（利用制限）を管理・節約し、効率的に回復・継続するための戦略を実行する
☆ 0View skill
GitHub
worktree-swarm
Set up and orchestrate parallel Claude Code agents using git worktrees. Use this skill when the user wants to parallelize a feature across multiple agents, spawn worktrees, or merge agent work back together.
☆ 0View skill
GitHub
agnostic-prompt-standard
The reference framework to generate, compile, and lint greenfield prompts that conform to the Agnostic Prompt Standard (APS) v1.0.
☆ 0View skill
GitHub
chinese-responder
确保 Agent 在本项目中的所有回复都使用中文。当用户与 Agent 进行任何对话、代码解释、错误提示、文档说明时，Agent 应始终使用中文进行回复，除非用户明确要求使用其他语言。
☆ 0View skill
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.