Agents
AI agents and automation
standards
by weegigs
Manage project standards. Auto-detects state and offers appropriate actions.
langchain-rag
by christian-bromann
Build Retrieval Augmented Generation (RAG) systems with LangChain - includes embeddings, vector stores, retrievers, document loaders, and text splitting
langchain-chat-models
by christian-bromann
Guide to using chat model integrations in LangChain including OpenAI, Anthropic, Google, Azure, and Bedrock
publish-skill
by johnlindquist
Publish a skill to GitHub for discovery via npx skills. Use when asked to "publish skill", "share skill", "make skill discoverable", or "upload skill to GitHub".
codex-spec-review
by weegigs
Spec review via Codex CLI for independent validation. Use when seeking external validation of specifications before implementation.
token-distribution-planning
by SanctifiedOps
Plan wallet splits, allocations, vesting, and transparency for SPL token launches. Use when designing distribution charts or multisig treasuries.
langchain-models
by christian-bromann
Initialize and use LangChain chat models - includes provider selection (OpenAI, Anthropic, Google), model configuration, and invocation patterns
smart-writing-workflow
by bahayonghang
This skill should be used when the user wants to start a complete article writing project and needs guidance through the full iterative workflow. Triggers: "开始写作流程", "开始创作", "help me write article", "guide writing process"
git-workflow
by HJewkes
Use when committing, branching, splitting changes, managing stacks, creating worktrees, or cleaning up branches — detects Graphite or Git and guides the agent through best-practice workflows via CLI.
n8n-mcp-tools-expert
by RedcoatAsher
Expert guide for using n8n-mcp MCP tools effectively. Use when searching for nodes, validating configurations, accessing templates, managing workflows, or using any n8n-mcp tool. Provides tool selection guidance, parameter formats, and common patterns.
Autonomous Development
by liauw-media
/mentor - Architecture review gate
skill-share
by Ing-la
"Generate daily Xiaohongshu content about Agent Skills. Selects a skill from skills.sh, generates initial copywriting, and optionally installs for deep technical analysis."
sequential-thinking
by mamba-mental
Use when complex problems require systematic step-by-step reasoning with ability to revise thoughts, branch into alternative approaches, or dynamically adjust scope. Ideal for multi-stage analysis, design planning, problem decomposition, or tasks with initially unclear scope.
youskill-finder
by youware-labs
Find AI skills and solutions for open-ended tasks. Use when user asks "how to...", "help me build...", "automate...", or any scenario-based question about what tools/skills could help.
workflow-composer
by vibery-studio
Chain Vibery commands, skills, and agents into repeatable automated workflows. Outputs: Executable workflow files, hook configurations, CI/CD integration. Use when user has repetitive multi-step processes to automate. Triggers: create workflow, automate this process, chain these commands, /workflow
langchain-text-splitters
by christian-bromann
Guide to using text splitter integrations in LangChain including recursive, character, and semantic splitters
Google ADK Python Skill
by mamba-mental
Remember: ADK treats agent development like traditional software engineering - use version control, write tests, and follow engineering best practices.
deepagents-memory
by christian-bromann
Implementing long-term memory in Deep Agents with cross-session storage using StoreBackend, CompositeBackend, and InMemoryStore for persistent data.
feature-agents
by HJewkes
Specialized feature development agents. Use for deep codebase exploration and architecture design during feature development.
deepagents-subagents
by christian-bromann
Using SubAgentMiddleware to spawn subagents for task delegation, context isolation, and specialized work in Deep Agents.
agent-browser
by HJewkes
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
code-simplify
by HJewkes
Simplify and refine code for clarity, consistency, and maintainability. Use after writing or modifying code to clean it up while preserving all functionality.
data-cache
by dgriffin831
Cache and restore agent data efficiently
deepagents-todolist
by christian-bromann
Using TodoListMiddleware for task planning and tracking progress with the write_todos tool in Deep Agents for complex multi-step workflows.