Claude Skills by tools-only

Custom tools extend your agent's capabilities beyond built-in functions. This guide covers creating, registering, and using custom tools.

{{ community_contribution_banner }} The [AgentCore Memory Session Manager](https://github.com/aws/bedrock-agentcore-sdk-python/tree/main/src/bedrock_agentcore/memory/integrations/strands) leverages Amazon Bedrock AgentCore Memory to provide advanced memory capabilities with intelligent retrieval for Strands Agents. It supports both short-term memory (STM) for conversation persistence and long-term memory (LTM) with multiple strategies for learning user preferences, facts, and session summaries.

{{ community_contribution_banner }} The [AgentCore Memory Session Manager](https://github.com/aws/bedrock-agentcore-sdk-python/tree/main/src/bedrock_agentcore/memory/integrations/strands) leverages Amazon Bedrock AgentCore Memory to provide advanced memory capabilities with intelligent retrieval for Strands Agents. It supports both short-term memory (STM) for conversation persistence and long-term memory (LTM) with multiple strategies for learning user preferences, facts, and session summaries.

{{ experimental_feature_warning() }} Session management for `BidiAgent` provides a mechanism for persisting conversation history and agent state across bidirectional streaming sessions. This enables voice assistants and interactive applications to maintain context and continuity even when connections are restarted or the application is redeployed.

{{ ts_not_supported("Session Management is not currently supported in the TypeScript SDK, but will be coming soon!") }} Session management in Strands Agents provides a robust mechanism for persisting agent state and conversation history across multiple interactions. This enables agents to maintain context and continuity even when the application restarts or when deployed in distributed environments.

"Agents as Tools" is an architectural pattern in AI systems where specialized AI agents are wrapped as callable functions (tools) that can be used by other agents. This creates a hierarchical structure where:

"Agents as Tools" is an architectural pattern in AI systems where specialized AI agents are wrapped as callable functions (tools) that can be used by other agents. This creates a hierarchical structure where:

User simulation enables realistic multi-turn conversation evaluation by simulating end-users interacting with your agents. Using the `ActorSimulator` class configured for user simulation, you can generate dynamic, goal-oriented conversations that test your agent's ability to handle real user interactions.

Agent Files (.af) are portable snapshots of an agent's configuration, memory, and tools.

Building applications where multiple users interact with Letta agents.

**Typical limits per block:** - 2000-5000 characters depending on configuration - Total core memory should stay under 80% of context window

This reference provides detailed scenarios and techniques for Git repository recovery.

This reference provides comprehensive verification commands to ensure secrets are fully removed from a git repository's object store.

Primary tool for recovering deleted files from ext filesystems.

**Version:** v<!-- VERSION -->0.4.8<!-- /VERSION --> (Released January 2026)

**Version:** v<!-- VERSION -->0.4.9<!-- /VERSION --> (Released January 2026)

**Version:** v<!-- VERSION -->0.4.7<!-- /VERSION --> (Released January 2026)

**Version:** v<!-- VERSION -->0.4.5<!-- /VERSION --> (Released January 2026)

**Version:** v<!-- VERSION -->0.4.3<!-- /VERSION --> (Released January 2026)

How to develop and test Claude Code marketplace plugins (skills) without releasing new versions.

Create a structured discovery workspace with research questions, hypotheses, and a research plan for a given topic. ---

Domain: OUTPUT (04) STRIDE Category: T (Tampering), I (Information Disclosure)

Domain: OUTPUT (04) STRIDE Category: T (Tampering), I (Information Disclosure)

<!-- Threat Modeling Skill | Version 3.0.2 (20260204a) | https://github.com/fr33d3m0n/threat-modeling | License: BSD-3-Clause --> --- description: Data & storage security (DB isolation, TLS, least privilege, RLS/CLS, backups, auditing) languages: - c - javascript - sql - yaml alwaysApply: false --- rule_id: codeguard-0-data-storage

<!-- Threat Modeling Skill | Version 3.0.3 (20260209a) | https://github.com/fr33d3m0n/threat-modeling | License: BSD-3-Clause --> --- description: Data & storage security (DB isolation, TLS, least privilege, RLS/CLS, backups, auditing) languages: - c - javascript - sql - yaml alwaysApply: false --- rule_id: codeguard-0-data-storage

Source: Adapted from auth-implementation-patterns skill

Source: Adapted from auth-implementation-patterns skill

<!-- Threat Modeling Skill | Version 3.0.3 (20260209a) | https://github.com/fr33d3m0n/threat-modeling | License: BSD-3-Clause -->

<!-- Threat Modeling Skill | Version 3.0.2 (20260204a) | https://github.com/fr33d3m0n/threat-modeling | License: BSD-3-Clause -->

<!-- Threat Modeling Skill | Version 3.0.2 (20260204a) | https://github.com/fr33d3m0n/threat-modeling | License: BSD-3-Clause -->

<!-- Threat Modeling Skill | Version 3.0.3 (20260209a) | https://github.com/fr33d3m0n/threat-modeling | License: BSD-3-Clause -->

You are an AI agent designed to operate in an iterative loop to automate browser tasks. Your ultimate goal is accomplishing the task provided in <user_request>. <intro> You excel at following tasks: 1. Navigating complex websites and extracting precise information 2. Automating form submissions and interactive web actions 3. Gathering and saving information 4. Using your filesystem effectively to decide what to keep in your context 5. Operate effectively in an agent loop 6. Efficiently perfor...

**Date:** 2026-02-01 **Phase:** Research

Exception classes for pydantic-ai-skills error handling.

Custom exception hierarchy for TunaCode

Kraken2 is a fast taxonomic classifier that uses exact k-mer matches to assign reads to taxonomic nodes. It's highly accurate for well-represented taxa and ideal for screening large datasets.

This is the full reference documentation for the Stripe agent connector.

This reference guide contains detailed information about AWS CloudFormation resources and configurations for infrastructure security, encryption, and secrets management.

This is the full reference documentation for the Shopify agent connector.

This is the full reference documentation for the Orb agent connector.

This is the full reference documentation for the Orb agent connector.

This is the full reference documentation for the Shopify agent connector.

This is the full reference documentation for the Orb agent connector.

This is the full reference documentation for the Stripe agent connector.

Complete reference for Google Analytics 4 (GA4) metrics and dimensions.

This is the full reference documentation for the Stripe agent connector.

Tempo stores all trace data in object storage with the following structure:

Loki manages three primary data types:

Local Deep Research v1.0 introduces significant security and architectural improvements:

Local Deep Research v1.0 introduces significant security and architectural improvements: