Agents
AI agents and automation
code-review
by HJewkes
Unified code review system — dispatches the right review agents for the situation. Use when reviewing code for quality, bugs, compliance, or before merging.
agent-mail
by jwcraig
Multi-agent coordination via agent-mail CLI. Use when communicating with other agents, coordinating file access, sending/receiving messages, checking inbox, or reserving files. Triggers on "send message to agent", "check inbox", "reserve files", "coordinate with other agents", multi-agent workflows, file reservations, acknowledgements, "list agents", "delete agent", "clean up agents", "purge agents".
langchain-embeddings
by christian-bromann
Guide to using embedding model integrations in LangChain including OpenAI, Azure, and local embeddings
reading-onchain-state
by SanctifiedOps
Patterns for reading Solana on-chain state efficiently: getAccountInfo, getProgramAccounts, caching, and reactivity. Use for frontends and services.
agents-py
by codeSTACKr
Build LiveKit Agent backends in Python. Use this skill when creating voice AI agents, voice assistants, or any realtime AI application using LiveKit's Python Agents SDK (livekit-agents). Covers AgentSession, Agent class, function tools, STT/LLM/TTS models, turn detection, and multi-agent workflows.
deepagents-filesystem
by christian-bromann
Using FilesystemMiddleware with virtual filesystems, backends (State, Store, Filesystem, Composite), and context management for Deep Agents.
react-hooks
by codeSTACKr
Build custom React UIs with LiveKit hooks from @livekit/components-react. Use this skill when you need low-level control over agent state, participants, tracks, chat, and data channels. For pre-built UI components, use the livekit-agents-ui skill instead.
react-component-governance
by lutzseverino
Opinionated React component architecture guidance for React projects. Use when reviewing or designing component boundaries, deciding whether UI should stay inline, become a local helper, become a component boundary, or become another boundary kind, classifying components as presentational, interactive, or container, applying compound, headless, or polymorphic patterns, setting packaging and ownership rules, or reasoning about providers, pages, forms, loading, and error shells.
code-cleanup
by krmcbride
Delegate repetitive tasks to specialized agent to preserve context. Use when user asks to fix linting errors, fix diagnostics, rename variables across files, update imports, fix formatting issues, or perform other mechanical bulk changes across multiple files.
tokenomics-design-for-memecoins
by SanctifiedOps
Craft pragmatic tokenomics for Solana memecoins: supply narrative, burns/sinks, incentives, and realism checks. Use during concepting and pre-launch docs.
agent-browser
by horuz-ai
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
deepagents-hitl
by christian-bromann
Implementing human-in-the-loop approval workflows with interrupt_on parameter for sensitive tool operations in Deep Agents.
compound
by benredmond
Capture learnings (problems, decisions, gotchas) from sessions to make future agents more effective
Verification Before Completion
by mamba-mental
Run verification commands and confirm output before claiming success
docs-seeker
by mamba-mental
"Searching internet for technical documentation using llms.txt standard, GitHub repositories via Repomix, and parallel exploration. Use when user needs: (1) Latest documentation for libraries/frameworks, (2) Documentation in llms.txt format, (3) GitHub repository analysis, (4) Documentation without direct llms.txt support, (5) Multiple documentation sources in parallel"
post-launch-content-cadence
by SanctifiedOps
Plan content cadence day 0�30 after launch: updates, proofs, community loops, and ethical hype management. Use to keep attention sustainably.
langchain-tools
by christian-bromann
Guide to using tool integrations in LangChain including pre-built toolkits, Tavily, Wikipedia, and custom tools
deepagents-skills
by christian-bromann
Creating and using custom skills with progressive disclosure, SKILL.md format, and the Agent Skills protocol in Deep Agents.
content-writer
by thoreinstein
Research-driven content writing with citations, iterative outlines, and real-time feedback. Transforms writing from solo effort to collaborative partnership.
standards-init
by weegigs
Initialize project standards baseline from a profile. Use when setting up a new project with predefined coding standards and conventions.
dispatching-parallel-agents
by HJewkes
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
deepbook-cli
by mcxross
Operate the deepbook CLI for DeepBook reads (REST/SSE), global ~/.deepbook config/account management, on-chain spot trading, top-level swap execution, balance-manager ops, and margin trading.
context-engineering
by vibery-studio
Master context engineering for AI agents - token optimization, degradation patterns, compression, memory systems, multi-agent coordination, evaluation. Use when designing agents, debugging context failures, or building LLM pipelines.
google-adk-python
by vibery-studio
Build AI agents with Google's Agent Development Kit (ADK) Python - an open-source toolkit for building, evaluating, and deploying AI agents. Features LlmAgent, workflow agents (sequential, parallel, loop), tool integration, multi-agent systems, and deployment to Vertex AI or Cloud Run.