Claude Skills by tools-only

Used by /flow-next:prime to scan for security configuration including GitHub settings, CODEOWNERS, and dependency updates. Do not invoke directly.

Used by /flow-next:prime to scan for security configuration including GitHub settings, CODEOWNERS, and dependency updates. Do not invoke directly.

Used by /flow-next:prime to scan for linting, formatting, type checking, and pre-commit configuration. Do not invoke directly.

Used by /flow-next:prime to scan for linting, formatting, type checking, and pre-commit configuration. Do not invoke directly.

Tool for generating tested code snippets for Mintlify docs.

Tool for generating tested code snippets for Mintlify docs.

VoiceMode Connect commands for managing remote voice connections.

The [Model Context Protocol (MCP)](https://modelcontextprotocol.io) is an open protocol that standardizes how applications provide context to Large Language Models. Strands Agents integrates with MCP to extend agent capabilities through external tools and services. MCP enables communication between agents and MCP servers that provide additional tools. Strands includes built-in support for connecting to MCP servers and using their tools in both Python and TypeScript.

MCP server tools are available as **direct tool calls** — just like `Read`, `Grep`, or `Bash`. They are NOT CLI commands. Do NOT run them via `claude mcp call` or any shell command. Call them directly as tools. **CORRECT** — call the tool directly: ``` Tool: mcp__playwright__browser_snapshot Parameters: {} ``` **WRONG** — do NOT shell out: ``` Bash: claude mcp call playwright browser_snapshot ... # WRONG — not a CLI command ```

> Add visual icons to your servers, tools, resources, and prompts Icons provide visual representations for your MCP servers and components, helping client applications present better user interfaces. When displayed in MCP clients, icons help users quickly identify and navigate your server's capabilities.

Local Deep Research includes command-line tools for benchmarking and rate limit management.

<p> &nbsp;&nbsp; <a href="https://www.gnu.org/software/bash/"><b>GNU Bash</b></a> - is an sh-compatible shell that incorporates useful features from the Korn shell and C shell.<br> &nbsp;&nbsp; <a href="https://www.zsh.org/"><b>Zsh</b></a> - is a shell designed for interactive use, although it is also a powerful scripting language.<br> &nbsp;&nbsp; <a href="https://tcl-lang.org/"><b>tclsh</b></a> - is a very powerful cross-platform shell, suitable for a huge range of uses.<br> &nbsp;&nbsp; <a...

cat > filename << __EOF__ data data data __EOF__ ``` ```bash vim scp://user@host//etc/fstab ``` ```bash mkd() { mkdir -p "$@" && cd "$@"; } ``` ```bash rename 'y/A-Z/a-z/' * ``` ```bash printf "%`tput cols`s" | tr ' ' '#' ``` ```bash history | cut -c 8- fc -l -n 1 | sed 's/^\s*//' ``` ```bash cat > /etc/profile << __EOF__ _after_logout() { username=$(whoami) for _pid in $(ps afx | grep sshd | grep "$username" | awk '{print $1}') ; do kill -9 $_pid done } trap _after_logout EXIT __EOF__ ``` ``...

Provides guided code refactoring capability with deep codebase understanding, compatibility options, and comprehensive verification. Use when restructuring or improving existing code.

Guided code refactoring with deep codebase understanding, compatibility options, and comprehensive verification

```bash nx g @nx/js:lib utils --buildable

Track Claude Code usage, estimate costs, and identify patterns across development sessions

Reference documentation for implementing global Claude Code hooks that inject context and enforce behavior.

TunaCode employs a multi-layered state management strategy that combines a central global session store with localized component states and explicit state machines for agent behavior. This architecture provides both centralized truth and localized control where appropriate, while supporting session persistence.

{{ community_contribution_banner }} As an agent builder, you want users to interact with your agents through a rich and responsive interface. Building UIs from scratch requires a lot of effort, especially to support streaming events and client state. That's exactly what [AG-UI](https://docs.ag-ui.com/) was designed for - rich user experiences directly connected to an agent. [AG-UI](https://github.com/ag-ui-protocol/ag-ui) provides a consistent interface to empower rich clients across technolo...

{{ community_contribution_banner }} !!! info "Language Support" This provider is only supported in Python. [strands-sglang](https://github.com/horizon-rl/strands-sglang) is an [SGLang](https://docs.sglang.io/) model provider for Strands Agents SDK with Token-In/Token-Out (TITO) support for agentic RL training. It provides direct integration with SGLang servers using the native `/generate` endpoint, optimized for reinforcement learning workflows. **Features:** - **SGLang Native API**: Uses SGL...

!!! info "Community Contribution" This is a community-maintained package that is not owned or supported by the Strands team. Validate and review the package before using it in your project. Have your own integration? [We'd love to add it here too!](https://github.com/strands-agents/docs/issues/new?assignees=&labels=enhancement&projects=&template=content_addition.yml&title=%5BContent+Addition%5D%3A+) !!! note "Language Support" This provider is only supported in Python. [xAI](https://x.ai/) is...

The `ExperimentGenerator` automatically creates comprehensive evaluation experiments with test cases and rubrics tailored to your agent's specific tasks and domains. It uses LLMs to generate diverse, realistic test scenarios and evaluation criteria, significantly reducing the manual effort required to build evaluation suites.

Strands Agents SDK provides an extensible interface for implementing custom model providers, allowing organizations to integrate their own LLM services while keeping implementation details private to their codebase.

This document provides a comprehensive overview of the `Promptheus` project, its architecture, and development conventions to be used as instructional context.

!!! info "Language Support" This provider is only supported in Python. [Google Gemini](https://ai.google.dev/api) is Google's family of multimodal large language models designed for advanced reasoning, code generation, and creative tasks. The Strands Agents SDK implements a Gemini provider, allowing you to run agents against the Gemini models available through Google's AI API.

Send work to Gemini CLI in headless mode. Use when the user wants to run prompts, pipe content, or parse output through `gemini -p`.

[Google Gemini](https://ai.google.dev/api) is Google's family of multimodal large language models designed for advanced reasoning, code generation, and creative tasks. The Strands Agents SDK implements a Gemini provider, allowing you to run agents against the Gemini models available through Google's AI API.

!!! info "Language Support" This provider is only supported in Python. [LiteLLM](https://docs.litellm.ai/docs/) is a unified interface for various LLM providers that allows you to interact with models from Amazon, Anthropic, OpenAI, and many others through a single API. The Strands Agents SDK implements a LiteLLM provider, allowing you to run agents against any model LiteLLM supports.

!!! info "Language Support" This provider is only supported in Python. [llama.cpp](https://github.com/ggml-org/llama.cpp) is a high-performance C++ inference engine for running large language models locally. The Strands Agents SDK implements a llama.cpp provider, allowing you to run agents against any llama.cpp server with quantized models.

The `TrajectoryEvaluator` is an LLM-based evaluator that assesses the sequence of actions or tool calls made by an agent during task execution. It evaluates whether the agent followed an appropriate path to reach its goal, making it ideal for evaluating multi-step reasoning and tool usage patterns. A complete example can be found [here](https://github.com/strands-agents/docs/blob/main/docs/examples/evals-sdk/trajectory_evaluator.py).

{{ experimental_feature_warning() }} [Amazon Nova Sonic](https://docs.aws.amazon.com/nova/latest/userguide/speech.html) provides real-time, conversational interactions through bidirectional audio streaming. Amazon Nova Sonic processes and responds to real-time speech as it occurs, enabling natural, human-like conversational experiences. Key capabilities and features include: - Adaptive speech response that dynamically adjusts delivery based on the prosody of the input speech. - Graceful handl...

{{ experimental_feature_warning() }} The [OpenAI Realtime API](https://platform.openai.com/docs/guides/realtime) is a speech-to-speech interface that enables low-latency, natural voice conversations with AI. Key features include: - **Bidirectional Interaction**: The user and the model can provide input and output at the same time. - **Interruptibility**: Allows users to interrupt the AI mid-response, like in human conversations. - **Multimodal Streaming**: The API supports streaming of text a...

The MCPClient enables developers to use MCP tools in Strands agents without dealing with async complexity. Since MCP requires async operations but Strands aims for simple synchronous usage (`agent = Agent(); agent("Do something")`), the client uses a background thread with its own event loop to handle MCP communication. This creates challenges around thread synchronization, hanging prevention, and connection stability that this architecture addresses.

--- When creating a Message, you can set `"stream": true` to incrementally stream the response using [server-sent events](https://developer.mozilla.org/en-US/Web/API/Server-sent%5Fevents/Using%5Fserver-sent%5Fevents) (SSE).

Complete plugin development toolkit for creating, refactoring, and validating Claude Code plugins, agents, skills, and commands. ---

This repo is a Claude Code plugin marketplace. It ships two plugins: **flow** and **flow-next**.

This guide covers the finance skill and its Python automation tools.

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

**Complex problems require simple and clear solutions.** MIRA is a FastAPI application with event-driven architecture coordinating three core systems: CNS (conversation management via immutable Continuum aggregate), Working Memory (trinket-based system prompt composition), and LT_Memory (batch memory extraction/linking/refinement). PostgreSQL RLS with contextvars provides automatic user isolation - all user-scoped queries, tool access, and repository operations enforce `user_id` filtering at ...

**VERSION:** See SKILL.md frontmatter ---

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

These rules enforce delegation discipline for the orchestrator role. The orchestrator's context window is a shared, finite resource across the entire session. Agents get fresh context per task — the orchestrator does not. ---

This guide covers the 12 production-ready RA/QM compliance skills for HealthTech/MedTech companies.

Unified interface library for working with multiple AI models (LLM, embedding, reranking, speech-to-text, text-to-speech) from different providers.

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

**Official Anthropic documentation (always check these first):**

Stateless service layer. Services never touch the database directly — they go through repositories in `cns/infrastructure/` or receive data from the orchestrator.

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.