AWS agent-toolkit documentation change
Summary
Editorial updates including rephrasing for clarity, consistency in terminology (e.g., changing 'agent' to 'your agent'), and minor grammatical improvements. Added full service names (e.g., 'Amazon S3 Tables') and simplified explanations.
Security assessment
Changes are purely editorial with no references to security vulnerabilities, incidents, or weaknesses. Existing security-related content (e.g., IAM policies) remains unchanged without new security guidance.
Diff
diff --git a/agent-toolkit/latest/userguide/skills.md b/agent-toolkit/latest/userguide/skills.md index 1506eb418..6c0a5c70b 100644 --- a//agent-toolkit/latest/userguide/skills.md +++ b//agent-toolkit/latest/userguide/skills.md @@ -11 +11 @@ What is a skill?How agents discover and use skillsTypes of skillsAvailable skill -Agent skills are curated packages of instructions, code scripts, and reference materials that help AI coding agents complete specific AWS tasks. Skills bridge the gap between what AI models know from their training data and what is needed to work effectively with AWS — especially for newer services, complex multi-service workflows, and tasks where best practices matter. +Agent skills are curated packages of instructions, code scripts, and reference materials that help AI coding agents complete specific AWS tasks. Skills bridge the gap between what AI models know from training data and what they need to work effectively with AWS. This is especially important for newer services, complex multi-service workflows, and tasks where best practices matter. @@ -32 +32 @@ Agent skills are curated packages of instructions, code scripts, and reference m -A skill is a directory containing a `SKILL.md` file and optional supporting files. The `SKILL.md` file includes a brief description and a set of instructions that tell the agent how to complete a task — which steps to follow, which AWS APIs to call, which mistakes to avoid, and how to verify the result. Skills can also include reference files with deeper guidance on specific subtasks, code scripts for deterministic operations, and slash commands that let you invoke the skill directly. +A skill is a directory containing a `SKILL.md` file and optional supporting files. The `SKILL.md` file includes a brief description and instructions that tell your agent how to complete a task. These instructions specify which steps to follow, which AWS APIs to call, which mistakes to avoid, and how to verify the result. Skills can also include reference files with deeper guidance on specific subtasks, code scripts for deterministic operations, and slash commands that let you invoke the skill directly. @@ -34 +34 @@ A skill is a directory containing a `SKILL.md` file and optional supporting file -Skills are designed to be lightweight and modular. Each skill focuses on a single task or domain, and agents load only the skills they need for the current task. A skill typically consumes a few thousand tokens when loaded — far less than the equivalent documentation — because it contains only the information the agent needs to act, not background context the agent already has. +Skills are lightweight and modular. Each skill focuses on a single task or domain, and your agent loads only the skills it needs for the current task. A skill typically consumes a few thousand tokens when loaded. This is far less than the equivalent documentation, because a skill contains only the information your agent needs to act, not background context it already has. @@ -43 +43 @@ Bundled with a plugin -Each plugin includes a curated set of skills that are available to the agent immediately after installation. The agent can use these skills without any network calls or additional setup. +Each plugin includes a curated set of skills that are available to your agent immediately after installation. Your agent can use these skills without any network calls or additional setup. @@ -53 +53 @@ Installed with the AWS CLI -You can install skills with the AWS CLI — either through the interactive setup wizard (`aws configure agent-toolkit`) or with the individual `aws agent-toolkit` commands. The CLI detects supported agents on your system and installs skills into each agent's configuration directory. For more information, see [AWS CLI](./aws-cli.html). +You can install skills with the AWS CLI through the interactive setup wizard (`aws configure agent-toolkit`) or with the individual `aws agent-toolkit` commands. The CLI detects supported agents on your system and installs skills into each agent's configuration directory. For more information, see [AWS CLI](./aws-cli.html). @@ -55 +55 @@ You can install skills with the AWS CLI — either through the interactive setup -Discovered at runtime via the AWS MCP Server +Discovered at runtime through the AWS MCP Server @@ -58 +58 @@ Discovered at runtime via the AWS MCP Server -Agents can search for and retrieve skills on demand through the AWS MCP Server, without any local installation. The agent uses the `search_documentation` tool to find relevant skills and the `retrieve_skill` tool to load them into context. +Agents can search for and retrieve skills on demand through the AWS MCP Server, without any local installation. Your agent uses the `search_documentation` tool to find relevant skills and the `retrieve_skill` tool to load them into context. @@ -60 +60 @@ Agents can search for and retrieve skills on demand through the AWS MCP Server, -When an agent uses a skill — regardless of how it was installed — the process is the same: +Regardless of how a skill was installed, your agent uses it the same way: @@ -62 +62 @@ When an agent uses a skill — regardless of how it was installed — the proces - 1. The agent reads the skill's description to determine if it is relevant to the current task. + 1. Your agent reads the skill's description to determine if it is relevant to the current task. @@ -64 +64 @@ When an agent uses a skill — regardless of how it was installed — the proces - 2. If relevant, the agent loads the full instructions from `SKILL.md`. + 2. If relevant, your agent loads the full instructions from `SKILL.md`. @@ -66 +66 @@ When an agent uses a skill — regardless of how it was installed — the proces - 3. The agent follows the skill's procedures, loading reference files only as needed. + 3. Your agent follows the skill's procedures, loading reference files only as needed. @@ -68 +68 @@ When an agent uses a skill — regardless of how it was installed — the proces - 4. After the task is complete, the agent releases the skill content from context. + 4. After the task is complete, your agent releases the skill content from context. @@ -73 +73 @@ When an agent uses a skill — regardless of how it was installed — the proces -This progressive disclosure approach means that having many skills available does not slow your agent down or consume unnecessary context. Only the skills relevant to the current task are loaded. +This progressive disclosure means that many available skills do not slow your agent down or consume unnecessary context. Your agent loads only the skills relevant to the current task. @@ -82 +82 @@ Service decision guides -These skills help agents choose the right AWS service for a use case. For example, a database decision guide helps agents recommend DynamoDB, Aurora, or DSQL based on the workload requirements. +These skills help your agent choose the right AWS service for a use case. For example, a database decision guide helps your agent recommend Amazon DynamoDB, Amazon Aurora, or Amazon DSQL based on the workload requirements. @@ -87 +87 @@ Step-by-step procedures -These skills provide tested workflows for common tasks like creating S3 Tables, setting up AWS Glue ETL pipelines, configuring IAM policies, and deploying serverless applications. +These skills provide tested workflows for common tasks like creating Amazon S3 Tables, setting up AWS Glue ETL pipelines, configuring IAM policies, and deploying serverless applications. @@ -97 +97 @@ SDK usage guides -These skills provide language-specific best practices for the AWS SDKs, covering common mistakes that models consistently get wrong (like DynamoDB marshalling in JavaScript or pagination patterns in Python). +These skills provide language-specific best practices for the AWS SDKs. They cover common mistakes that models consistently get wrong, like Amazon DynamoDB marshalling in JavaScript or pagination patterns in Python. @@ -101 +101 @@ These skills provide language-specific best practices for the AWS SDKs, covering -Each plugin includes a curated set of skills covering the most common workflows for that domain. The full set of skills — including domain-specific skills for individual AWS services — is available on [GitHub](https://github.com/aws/agent-toolkit-for-aws) and discoverable at runtime through the AWS MCP Server. +Each plugin includes a curated set of skills covering the most common workflows for that domain. The full set of skills, including domain-specific skills for individual AWS services, is available on [GitHub](https://github.com/aws/agent-toolkit-for-aws) and discoverable at runtime through the AWS MCP Server. @@ -114 +114 @@ Skills work best with the AWS MCP Server, which provides authenticated API acces -Skills also work without the AWS MCP Server. When agents do not have access to the MCP Server, they can run the same AWS operations using the AWS CLI directly. Each skill includes instructions that work with both approaches. +Skills also work without the AWS MCP Server. When your agent does not have access to the AWS MCP Server, it can run the same AWS operations using the AWS CLI directly. Each skill includes instructions that work with both approaches.