[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-aws-enrich-with-aws-security-agent":3,"mdc-ov2wcr-key":54,"related-org-aws-enrich-with-aws-security-agent":446,"related-repo-aws-enrich-with-aws-security-agent":619},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":27,"repoUrl":28,"updatedAt":29,"license":30,"forks":31,"topics":32,"repo":49,"sourceUrl":52,"mdContent":53},"enrich-with-aws-security-agent","investigate security root causes in AWS","Automatically load this skill when investigating application outages, service degradation, or errors that could have security-related root causes — including unexplained downtime, authentication or authorization failures, injection attacks, data exposure, or suspicious application behavior. Query AWS Security Agent CloudWatch logs to retrieve detailed code review findings with actionable, low-level details (file, line number, vulnerability type) that customers can directly fix.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"aws","AWS (Amazon)","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Faws.png",[12,16,19,22,24],{"name":13,"slug":14,"type":15},"Security","security","tag",{"name":17,"slug":18,"type":15},"Auth","auth",{"name":20,"slug":21,"type":15},"Incident Response","incident-response",{"name":23,"slug":8,"type":15},"AWS",{"name":25,"slug":26,"type":15},"Debugging","debugging",35,"https:\u002F\u002Fgithub.com\u002Faws\u002Ftools-for-devops-agent","2026-08-20T03:53:23.097965",null,30,[33,34,35,36,37,8,38,39,40,41,42,43,21,44,45,46,47,48],"agent-skills","agentic-ai","agents","ai-agents","aiops","aws-devops-agent","cloud-operations","custom-agents","devops","devops-agent-skills","frontier-agent","operational-excellence","root-cause-analysis","skills","sre","support",{"repoUrl":28,"stars":27,"forks":31,"topics":50,"description":51},[33,34,35,36,37,8,38,39,40,41,42,43,21,44,45,46,47,48],"Open-source tools for AWS DevOps Agent - extend DevOps Agent with ready-to-use skills, custom agents, and other tools, for incident response, root cause analysis, and operational troubleshooting","https:\u002F\u002Fgithub.com\u002Faws\u002Ftools-for-devops-agent\u002Ftree\u002FHEAD\u002Fskills\u002Fenrich-with-aws-security-agent","---\nname: enrich-with-aws-security-agent\ndescription: Automatically load this skill when investigating application outages, service degradation, or errors that could have security-related root causes — including unexplained downtime, authentication or authorization failures, injection attacks, data exposure, or suspicious application behavior. Query AWS Security Agent CloudWatch logs to retrieve detailed code review findings with actionable, low-level details (file, line number, vulnerability type) that customers can directly fix.\nmetadata:\n  author: yakiratz-aws\n  version: \"1.0.0\"\n  aws-devops-agent-skills.agent-types: \"Chat tasks, Incident RCA\"\n  aws-devops-agent-skills.aws-services: \"Amazon CloudWatch, AWS Security Agent\"\n  aws-devops-agent-skills.technical-domains: \"Security\"\n---\n\n# Enriching Investigations with AWS Security Agent Findings\n\n## When to Use — AUTOMATIC ACTIVATION\n\n**Load this skill automatically when ANY of these conditions apply:**\n\n### Application-Level Symptoms (even without explicit security context)\n- Application pages or endpoints are not loading or returning errors\n- Unexplained service outages with no recent deployments\n- Application behaving unexpectedly without clear infrastructure cause\n- Services returning 4xx\u002F5xx errors without obvious resource exhaustion\n\n### Explicit Security Signals\n- Security vulnerabilities or misconfigurations mentioned\n- Suspicious code patterns or behaviors observed\n- Authentication or authorization failures\n- Injection vulnerabilities suspected (SQL, command, SSRF, etc.)\n- Sensitive data exposure concerns\n- Security-related errors in application logs\n- Findings that suggest code-level security issues\n\n### Key Insight\nMany security issues (like SSRF, injection attacks, or compromised dependencies) manifest as **application outages or errors** rather than obvious security alerts. When an app stops working and there's no clear infrastructure cause (no deployments, no resource exhaustion, no config changes), **always check for security issues**.\n\n## Overview\n\nAWS Security Agent is an AI-powered security service that performs automated code security reviews and penetration testing. Its findings are stored in CloudWatch Logs and provide detailed, actionable information about vulnerabilities including exact file locations, line numbers, and remediation guidance.\n\n## Steps\n\n1. **Identify the relevant CloudWatch log group** for AWS Security Agent findings. Look for log groups with patterns like:\n   - `\u002Faws\u002Fsecurityagent\u002F*`\n   - Log groups containing \"security-agent\" or \"securityagent\" in the name\n\n2. **Query the Security Agent logs** using CloudWatch Logs Insights:\n   ```\n   fields @timestamp, @message\n   | filter @message like \u002Ffinding|vulnerability|issue|risk\u002F\n   | sort @timestamp desc\n   | limit 100\n   ```\n\n3. **Extract actionable details** from the findings:\n   - **File path**: The exact source file containing the vulnerability\n   - **Line number**: The specific line(s) of code affected\n   - **Vulnerability type**: Classification (e.g., SQL injection, XSS, SSRF, hardcoded secrets)\n   - **Severity**: Critical, High, Medium, Low\n   - **Description**: What the vulnerability is and why it's a risk\n   - **Remediation**: Suggested fix or mitigation\n\n4. **Correlate findings with the incident** by matching:\n   - Affected services or components\n   - Timeframes (when the vulnerability was introduced vs. when the incident occurred)\n   - Code paths involved in the failing functionality\n\n5. **Present findings to the customer** with:\n   - Clear identification of the vulnerable code location\n   - Explanation of how this vulnerability may relate to the incident\n   - Specific remediation steps they can take to fix the code\n\n## Example Log Query for Specific Application\n\nIf investigating a specific application (e.g., \"ssrf-demo\", \"orders\", \"account\"):\n```\nfields @timestamp, @message\n| filter @message like \u002Fssrf|orders|account|vulnerability|finding|issue\u002F\n| sort @timestamp desc\n| limit 50\n```\n\n## Important Notes\n\n- AWS Security Agent API access may require additional IAM permissions. If API calls fail, fall back to the CloudWatch logs approach.\n- Always provide the exact file and line number when available — this is the key value for customers.\n- Link the security finding to the observed incident behavior when possible.\n- **When in doubt, check security logs** — it's better to rule out security issues than to miss them.\n",{"data":55,"body":62},{"name":4,"description":6,"metadata":56},{"author":57,"version":58,"aws-devops-agent-skills":59},"yakiratz-aws","1.0.0",{"agent-types":60,"aws-services":61,"technical-domains":13},"Chat tasks, Incident RCA","Amazon CloudWatch, AWS Security Agent",{"type":63,"children":64},"root",[65,74,81,91,98,123,129,167,173,192,198,203,209,392,398,403,412,418],{"type":66,"tag":67,"props":68,"children":70},"element","h1",{"id":69},"enriching-investigations-with-aws-security-agent-findings",[71],{"type":72,"value":73},"text","Enriching Investigations with AWS Security Agent Findings",{"type":66,"tag":75,"props":76,"children":78},"h2",{"id":77},"when-to-use-automatic-activation",[79],{"type":72,"value":80},"When to Use — AUTOMATIC ACTIVATION",{"type":66,"tag":82,"props":83,"children":84},"p",{},[85],{"type":66,"tag":86,"props":87,"children":88},"strong",{},[89],{"type":72,"value":90},"Load this skill automatically when ANY of these conditions apply:",{"type":66,"tag":92,"props":93,"children":95},"h3",{"id":94},"application-level-symptoms-even-without-explicit-security-context",[96],{"type":72,"value":97},"Application-Level Symptoms (even without explicit security context)",{"type":66,"tag":99,"props":100,"children":101},"ul",{},[102,108,113,118],{"type":66,"tag":103,"props":104,"children":105},"li",{},[106],{"type":72,"value":107},"Application pages or endpoints are not loading or returning errors",{"type":66,"tag":103,"props":109,"children":110},{},[111],{"type":72,"value":112},"Unexplained service outages with no recent deployments",{"type":66,"tag":103,"props":114,"children":115},{},[116],{"type":72,"value":117},"Application behaving unexpectedly without clear infrastructure cause",{"type":66,"tag":103,"props":119,"children":120},{},[121],{"type":72,"value":122},"Services returning 4xx\u002F5xx errors without obvious resource exhaustion",{"type":66,"tag":92,"props":124,"children":126},{"id":125},"explicit-security-signals",[127],{"type":72,"value":128},"Explicit Security Signals",{"type":66,"tag":99,"props":130,"children":131},{},[132,137,142,147,152,157,162],{"type":66,"tag":103,"props":133,"children":134},{},[135],{"type":72,"value":136},"Security vulnerabilities or misconfigurations mentioned",{"type":66,"tag":103,"props":138,"children":139},{},[140],{"type":72,"value":141},"Suspicious code patterns or behaviors observed",{"type":66,"tag":103,"props":143,"children":144},{},[145],{"type":72,"value":146},"Authentication or authorization failures",{"type":66,"tag":103,"props":148,"children":149},{},[150],{"type":72,"value":151},"Injection vulnerabilities suspected (SQL, command, SSRF, etc.)",{"type":66,"tag":103,"props":153,"children":154},{},[155],{"type":72,"value":156},"Sensitive data exposure concerns",{"type":66,"tag":103,"props":158,"children":159},{},[160],{"type":72,"value":161},"Security-related errors in application logs",{"type":66,"tag":103,"props":163,"children":164},{},[165],{"type":72,"value":166},"Findings that suggest code-level security issues",{"type":66,"tag":92,"props":168,"children":170},{"id":169},"key-insight",[171],{"type":72,"value":172},"Key Insight",{"type":66,"tag":82,"props":174,"children":175},{},[176,178,183,185,190],{"type":72,"value":177},"Many security issues (like SSRF, injection attacks, or compromised dependencies) manifest as ",{"type":66,"tag":86,"props":179,"children":180},{},[181],{"type":72,"value":182},"application outages or errors",{"type":72,"value":184}," rather than obvious security alerts. When an app stops working and there's no clear infrastructure cause (no deployments, no resource exhaustion, no config changes), ",{"type":66,"tag":86,"props":186,"children":187},{},[188],{"type":72,"value":189},"always check for security issues",{"type":72,"value":191},".",{"type":66,"tag":75,"props":193,"children":195},{"id":194},"overview",[196],{"type":72,"value":197},"Overview",{"type":66,"tag":82,"props":199,"children":200},{},[201],{"type":72,"value":202},"AWS Security Agent is an AI-powered security service that performs automated code security reviews and penetration testing. Its findings are stored in CloudWatch Logs and provide detailed, actionable information about vulnerabilities including exact file locations, line numbers, and remediation guidance.",{"type":66,"tag":75,"props":204,"children":206},{"id":205},"steps",[207],{"type":72,"value":208},"Steps",{"type":66,"tag":210,"props":211,"children":212},"ol",{},[213,241,263,336,364],{"type":66,"tag":103,"props":214,"children":215},{},[216,221,223],{"type":66,"tag":86,"props":217,"children":218},{},[219],{"type":72,"value":220},"Identify the relevant CloudWatch log group",{"type":72,"value":222}," for AWS Security Agent findings. Look for log groups with patterns like:",{"type":66,"tag":99,"props":224,"children":225},{},[226,236],{"type":66,"tag":103,"props":227,"children":228},{},[229],{"type":66,"tag":230,"props":231,"children":233},"code",{"className":232},[],[234],{"type":72,"value":235},"\u002Faws\u002Fsecurityagent\u002F*",{"type":66,"tag":103,"props":237,"children":238},{},[239],{"type":72,"value":240},"Log groups containing \"security-agent\" or \"securityagent\" in the name",{"type":66,"tag":103,"props":242,"children":243},{},[244,249,251],{"type":66,"tag":86,"props":245,"children":246},{},[247],{"type":72,"value":248},"Query the Security Agent logs",{"type":72,"value":250}," using CloudWatch Logs Insights:",{"type":66,"tag":252,"props":253,"children":257},"pre",{"className":254,"code":256,"language":72},[255],"language-text","fields @timestamp, @message\n| filter @message like \u002Ffinding|vulnerability|issue|risk\u002F\n| sort @timestamp desc\n| limit 100\n",[258],{"type":66,"tag":230,"props":259,"children":261},{"__ignoreMap":260},"",[262],{"type":72,"value":256},{"type":66,"tag":103,"props":264,"children":265},{},[266,271,273],{"type":66,"tag":86,"props":267,"children":268},{},[269],{"type":72,"value":270},"Extract actionable details",{"type":72,"value":272}," from the findings:",{"type":66,"tag":99,"props":274,"children":275},{},[276,286,296,306,316,326],{"type":66,"tag":103,"props":277,"children":278},{},[279,284],{"type":66,"tag":86,"props":280,"children":281},{},[282],{"type":72,"value":283},"File path",{"type":72,"value":285},": The exact source file containing the vulnerability",{"type":66,"tag":103,"props":287,"children":288},{},[289,294],{"type":66,"tag":86,"props":290,"children":291},{},[292],{"type":72,"value":293},"Line number",{"type":72,"value":295},": The specific line(s) of code affected",{"type":66,"tag":103,"props":297,"children":298},{},[299,304],{"type":66,"tag":86,"props":300,"children":301},{},[302],{"type":72,"value":303},"Vulnerability type",{"type":72,"value":305},": Classification (e.g., SQL injection, XSS, SSRF, hardcoded secrets)",{"type":66,"tag":103,"props":307,"children":308},{},[309,314],{"type":66,"tag":86,"props":310,"children":311},{},[312],{"type":72,"value":313},"Severity",{"type":72,"value":315},": Critical, High, Medium, Low",{"type":66,"tag":103,"props":317,"children":318},{},[319,324],{"type":66,"tag":86,"props":320,"children":321},{},[322],{"type":72,"value":323},"Description",{"type":72,"value":325},": What the vulnerability is and why it's a risk",{"type":66,"tag":103,"props":327,"children":328},{},[329,334],{"type":66,"tag":86,"props":330,"children":331},{},[332],{"type":72,"value":333},"Remediation",{"type":72,"value":335},": Suggested fix or mitigation",{"type":66,"tag":103,"props":337,"children":338},{},[339,344,346],{"type":66,"tag":86,"props":340,"children":341},{},[342],{"type":72,"value":343},"Correlate findings with the incident",{"type":72,"value":345}," by matching:",{"type":66,"tag":99,"props":347,"children":348},{},[349,354,359],{"type":66,"tag":103,"props":350,"children":351},{},[352],{"type":72,"value":353},"Affected services or components",{"type":66,"tag":103,"props":355,"children":356},{},[357],{"type":72,"value":358},"Timeframes (when the vulnerability was introduced vs. when the incident occurred)",{"type":66,"tag":103,"props":360,"children":361},{},[362],{"type":72,"value":363},"Code paths involved in the failing functionality",{"type":66,"tag":103,"props":365,"children":366},{},[367,372,374],{"type":66,"tag":86,"props":368,"children":369},{},[370],{"type":72,"value":371},"Present findings to the customer",{"type":72,"value":373}," with:",{"type":66,"tag":99,"props":375,"children":376},{},[377,382,387],{"type":66,"tag":103,"props":378,"children":379},{},[380],{"type":72,"value":381},"Clear identification of the vulnerable code location",{"type":66,"tag":103,"props":383,"children":384},{},[385],{"type":72,"value":386},"Explanation of how this vulnerability may relate to the incident",{"type":66,"tag":103,"props":388,"children":389},{},[390],{"type":72,"value":391},"Specific remediation steps they can take to fix the code",{"type":66,"tag":75,"props":393,"children":395},{"id":394},"example-log-query-for-specific-application",[396],{"type":72,"value":397},"Example Log Query for Specific Application",{"type":66,"tag":82,"props":399,"children":400},{},[401],{"type":72,"value":402},"If investigating a specific application (e.g., \"ssrf-demo\", \"orders\", \"account\"):",{"type":66,"tag":252,"props":404,"children":407},{"className":405,"code":406,"language":72},[255],"fields @timestamp, @message\n| filter @message like \u002Fssrf|orders|account|vulnerability|finding|issue\u002F\n| sort @timestamp desc\n| limit 50\n",[408],{"type":66,"tag":230,"props":409,"children":410},{"__ignoreMap":260},[411],{"type":72,"value":406},{"type":66,"tag":75,"props":413,"children":415},{"id":414},"important-notes",[416],{"type":72,"value":417},"Important Notes",{"type":66,"tag":99,"props":419,"children":420},{},[421,426,431,436],{"type":66,"tag":103,"props":422,"children":423},{},[424],{"type":72,"value":425},"AWS Security Agent API access may require additional IAM permissions. If API calls fail, fall back to the CloudWatch logs approach.",{"type":66,"tag":103,"props":427,"children":428},{},[429],{"type":72,"value":430},"Always provide the exact file and line number when available — this is the key value for customers.",{"type":66,"tag":103,"props":432,"children":433},{},[434],{"type":72,"value":435},"Link the security finding to the observed incident behavior when possible.",{"type":66,"tag":103,"props":437,"children":438},{},[439,444],{"type":66,"tag":86,"props":440,"children":441},{},[442],{"type":72,"value":443},"When in doubt, check security logs",{"type":72,"value":445}," — it's better to rule out security issues than to miss them.",{"items":447,"total":618},[448,466,481,494,509,519,532,548,562,579,592,604],{"slug":449,"name":449,"fn":450,"description":451,"org":452,"tags":453,"stars":463,"repoUrl":464,"updatedAt":465},"agents-build","add capabilities to existing agent projects","Use to extend an existing agent project with memory, app integration, VPC, multi-agent, migration, model, browser, code interpreter, payments, or resource removal. Triggers: \"add memory\", \"remember across sessions\", \"call agent from app\", \"invoke agent from code\", \"agent auth\", \"streaming\", \"VPC\", \"VPC connectivity\", \"can't reach from VPC\", \"multi-agent\", \"A2A\", \"A2A auth\", \"orchestrator not delegating\", \"specialist not called\", \"migrate Bedrock Agent\", \"migration issue\", \"change model\", \"browser tool\", \"code interpreter\", \"delete agent\", \"tear down\", \"agentcore remove\", \"cross-account memory\", \"add payments capability to my agent\", \"wire payments plugin\", \"integrate x402 payments with the agent I'm building\", \"add MPP payments\", \"Machine Payments Protocol\". External APIs via Gateway: use agents-connect. New project: use agents-get-started. CLI\u002Fdev-server errors: use agents-debug. Runtime x402\u002FMPP payments: use agents-pay. Migration-specific Strands vs LangGraph routes here.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[454,456,459,460],{"name":455,"slug":35,"type":15},"Agents",{"name":457,"slug":458,"type":15},"Automation","automation",{"name":23,"slug":8,"type":15},{"name":461,"slug":462,"type":15},"Engineering","engineering",1822,"https:\u002F\u002Fgithub.com\u002Faws\u002Fagent-toolkit-for-aws","2026-08-20T03:27:06.137661",{"slug":467,"name":467,"fn":468,"description":469,"org":470,"tags":471,"stars":463,"repoUrl":464,"updatedAt":480},"agents-connect","connect agents to external services","Use when connecting your agent to external APIs, tools, or services via Gateway, or restricting tool access with Cedar policies. Handles gateway setup, target types, outbound auth (OAuth, API key, IAM), credentials, and Cedar policy authoring. Triggers on: \"connect to API\", \"add gateway\", \"connect to MCP server\", \"Lambda tools\", \"OpenAPI\", \"gateway target\", \"Cedar policy\", \"restrict tools\", \"policy engine\", \"gateway auth error\", \"store API key\", \"outbound credential\", \"env var API key\", \"API key None after deploy\", \"credential not available after deploy\", \"should this be a gateway target\", \"give my agent tools\", \"add tools to agent\". Not for inbound auth (who can call your agent) — use agents-harden. Not for debugging agent behavior — use agents-debug. Not for VPC networking errors (agent can't reach APIs due to VPC) — use agents-build. Not for creating or hosting a new MCP server project — use agents-get-started.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[472,473,476,479],{"name":455,"slug":35,"type":15},{"name":474,"slug":475,"type":15},"API Development","api-development",{"name":477,"slug":478,"type":15},"Authentication","authentication",{"name":23,"slug":8,"type":15},"2026-07-16T06:00:38.866147",{"slug":482,"name":482,"fn":483,"description":484,"org":485,"tags":486,"stars":463,"repoUrl":464,"updatedAt":493},"agents-debug","debug agent and environment issues","Use when your agent or environment is broken — wrong answers, errors, timeouts, tool failures, or CLI issues. Reads traces and logs to diagnose root causes. Also checks prerequisites when the CLI itself isn't working. Triggers on: \"agent not working\", \"wrong answer\", \"agent error\", \"tool call failing\", \"debug agent\", \"check logs\", \"read traces\", \"broken\", \"500 error\", \"424 error\", \"model access denied\", \"command not found\", \"stuck in DELETING\", \"maxVms exceeded\", \"cold start diagnosis\", \"cold start slow\", \"agentcore create error\", \"create failed\", \"exit code 7\", \"connection refused local dev\". Not for deploy failures — use agents-deploy. Not for performance tuning without errors — use agents-optimize. Not for VPC configuration — use agents-build. Not for observability setup or missing logs — use agents-optimize.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[487,488,489,490],{"name":455,"slug":35,"type":15},{"name":23,"slug":8,"type":15},{"name":25,"slug":26,"type":15},{"name":491,"slug":492,"type":15},"Observability","observability","2026-07-16T06:00:44.679093",{"slug":495,"name":495,"fn":496,"description":497,"org":498,"tags":499,"stars":463,"repoUrl":464,"updatedAt":508},"agents-deploy","deploy AI agents to AWS","Use when deploying your agent to AWS, or when a deploy has failed. Handles pre-flight validation, CDK\u002FIAM\u002Fquota error diagnosis, version management, rollback, and canary deployments. Triggers on: \"deploy my agent\", \"agentcore deploy\", \"deploy failed\", \"CDK error\", \"rollback\", \"canary deploy\", \"pin version\", \"redeploy\", \"deploy stuck\". Not for production hardening — use agents-harden. Not for adding capabilities before deploy — use agents-build or agents-connect. Not for VPC configuration errors — use agents-build.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[500,501,502,505],{"name":455,"slug":35,"type":15},{"name":23,"slug":8,"type":15},{"name":503,"slug":504,"type":15},"CI\u002FCD","ci-cd",{"name":506,"slug":507,"type":15},"Deployment","deployment","2026-07-12T08:42:55.059577",{"slug":510,"name":510,"fn":511,"description":512,"org":513,"tags":514,"stars":463,"repoUrl":464,"updatedAt":518},"agents-get-started","scaffold and deploy new agent projects","Use when a developer wants to create a new agent project or get started with AgentCore. Handles framework selection, project scaffolding, first deploy, and first invocation. Triggers on: \"build an agent\", \"create an agent\", \"get started\", \"new project\", \"agentcore create\", \"which framework\", \"Strands vs LangGraph\", \"hello world agent\", \"first agent\", \"create MCP server\", \"host MCP server\", \"agentcore dev\", \"dev server\", \"what port\", \"local development\". Not for adding capabilities to existing projects — use agents-build or agents-connect. Strands vs LangGraph in a migration context routes to agents-build, not here. Connecting to an existing MCP server routes to agents-connect, not here.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[515,516,517],{"name":455,"slug":35,"type":15},{"name":23,"slug":8,"type":15},{"name":506,"slug":507,"type":15},"2026-07-12T08:42:51.963247",{"slug":520,"name":520,"fn":521,"description":522,"org":523,"tags":524,"stars":463,"repoUrl":464,"updatedAt":531},"agents-harden","harden agents for production","Use when preparing your agent for production — IAM scoping, inbound auth (JWT, SigV4), secrets management, cold start optimization, session lifecycle, rate limiting, input validation, and quota guidance. Triggers on: \"production checklist\", \"harden agent\", \"production ready\", \"secure agent\", \"inbound auth\", \"going live\", \"cold start optimization\", \"session lifecycle\", \"StopRuntimeSession\", \"quota\", \"throttling\", \"maxVms\", \"rate limit\", \"security audit of outbound API calls\", \"gateway target audit for production\", \"restrict who can call\", \"lock down endpoint\", \"only our app can call\". Not for Cedar tool-restriction policies — use agents-connect. Not for quality measurement — use agents-optimize. Not for outbound credential storage or API key wiring — use agents-connect. Not for A2A agent-to-agent auth — use agents-build. Cold start observation and diagnosis (not optimization) routes to agents-debug.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[525,526,527,530],{"name":455,"slug":35,"type":15},{"name":23,"slug":8,"type":15},{"name":528,"slug":529,"type":15},"Best Practices","best-practices",{"name":13,"slug":14,"type":15},"2026-07-16T06:00:42.174705",{"slug":533,"name":533,"fn":534,"description":535,"org":536,"tags":537,"stars":463,"repoUrl":464,"updatedAt":547},"agents-optimize","optimize agent quality and performance","Use when measuring or improving agent quality and performance — set up evaluators, online monitoring, CI\u002FCD quality gates, observability, or cost optimization. Triggers on: \"evaluate my agent\", \"add evaluator\", \"measure quality\", \"quality gate\", \"run evals\", \"agent too slow\", \"why is it slow\", \"reduce latency\", \"set up observability\", \"CloudWatch dashboard\", \"how much does my agent cost\", \"cost optimization\", \"logs not showing up\", \"logs missing\", \"spans not found\", \"eval failing\", \"eval error\", \"dev traces\", \"local traces\", \"agentcore dev traces\", \"traces to CloudWatch\". Not for debugging errors or crashes — use agents-debug. Slow but correct routes here; broken routes to debug.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[538,539,540,543,544],{"name":455,"slug":35,"type":15},{"name":23,"slug":8,"type":15},{"name":541,"slug":542,"type":15},"Evals","evals",{"name":491,"slug":492,"type":15},{"name":545,"slug":546,"type":15},"Performance","performance","2026-07-12T08:42:56.488105",{"slug":549,"name":549,"fn":550,"description":551,"org":552,"tags":553,"stars":463,"repoUrl":464,"updatedAt":561},"agents-pay","handle x402 payments for agent tasks","Use when THIS agent needs to pay for x402-protected content at runtime: hitting a paywall mid-task, settling it via AgentCore Payments, and applying operator-defined spend limits. Covers payment setup, policy, session budgets, and troubleshooting. Triggers on: \"my agent hit a 402 while calling an API\", \"a tool call returned 402 Payment Required\", \"my agent needs to pay for x402-protected content\", \"let the agent pay for content, capped at $5 per session\", \"set a spend limit for the agent\", \"ProcessPayment failed\", or \"why did my agent refuse to pay\". Not for BUILDING payment capability for end users, including wallets and framework middleware; use agents-build and references\u002Fpayments.md. For non-paid APIs via Gateway use agents-connect. For inbound auth use agents-harden. For project scaffolding use agents-get-started.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[554,555,556,559],{"name":455,"slug":35,"type":15},{"name":457,"slug":458,"type":15},{"name":557,"slug":558,"type":15},"Payments","payments",{"name":560,"slug":560,"type":15},"x402","2026-08-10T04:16:31.844309",{"slug":563,"name":563,"fn":564,"description":565,"org":566,"tags":567,"stars":463,"repoUrl":464,"updatedAt":578},"amazon-aurora-mysql","manage Amazon Aurora MySQL clusters","Amazon Aurora MySQL — creates, modifies, and advises on Aurora MySQL clusters specifically (MySQL-compatible engine, Aurora serverless, parallel query). Trigger for Aurora MySQL cluster operations, ACU sizing, I\u002FO-Optimized storage, commitment pricing, or MySQL upgrade planning. Aurora MySQL uses full (VPC-based) configuration — express configuration is PostgreSQL-only. For Aurora PostgreSQL, use amazon-aurora-postgresql instead. Contains safety guardrails and response templates that override defaults.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[568,569,572,575],{"name":23,"slug":8,"type":15},{"name":570,"slug":571,"type":15},"Database","database",{"name":573,"slug":574,"type":15},"MySQL","mysql",{"name":576,"slug":577,"type":15},"Serverless","serverless","2026-07-12T08:43:13.27939",{"slug":580,"name":580,"fn":581,"description":582,"org":583,"tags":584,"stars":463,"repoUrl":464,"updatedAt":591},"amazon-aurora-postgresql","configure Amazon Aurora PostgreSQL clusters","Amazon Aurora PostgreSQL — creates, modifies, and advises on Aurora PostgreSQL clusters specifically (PostgreSQL-compatible engine, Aurora serverless, express configuration, pgvector, Babelfish). Trigger for Aurora PostgreSQL cluster operations, express-configuration quick-start, ACU sizing, I\u002FO-Optimized storage, commitment pricing, or PostgreSQL upgrade planning. For Aurora MySQL, use amazon-aurora-mysql instead. Contains safety guardrails, express-first routing, and response templates that override defaults.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[585,586,587,590],{"name":23,"slug":8,"type":15},{"name":570,"slug":571,"type":15},{"name":588,"slug":589,"type":15},"PostgreSQL","postgresql",{"name":576,"slug":577,"type":15},"2026-07-16T06:00:34.789624",{"slug":593,"name":593,"fn":594,"description":595,"org":596,"tags":597,"stars":463,"repoUrl":464,"updatedAt":603},"amazon-bedrock","build generative AI apps with Amazon Bedrock","Builds generative AI applications on Amazon Bedrock. Covers model invocation (Converse API, InvokeModel), RAG with Knowledge Bases, Bedrock Agents, Guardrails, and AgentCore (including the Harness managed agent loop). Use when invoking models, setting up Knowledge Bases, creating agents, applying guardrails, deploying to AgentCore, migrating\u002Fporting\u002Fconverting a Bedrock Agent (including inline agents) to an AgentCore Harness, troubleshooting Bedrock errors (ThrottlingException, AccessDeniedException), or choosing models (Claude, Llama, Nova, Titan). ALSO USE for prompt caching, quota health checks and throttling diagnosis, cost attribution, migrating between Claude model generations, chunking strategies, API selection (Converse vs InvokeModel), and model selection. Also covers AgentCore Payments setup (x402, microtransactions, Payment Manager, Coinbase CDP, Stripe Privy, 402 Payment Required, paid endpoint). NOT for custom model training, Rekognition, or Comprehend.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[598,599,600],{"name":455,"slug":35,"type":15},{"name":23,"slug":8,"type":15},{"name":601,"slug":602,"type":15},"LLM","llm","2026-08-07T04:38:13.03499",{"slug":605,"name":605,"fn":606,"description":607,"org":608,"tags":609,"stars":463,"repoUrl":464,"updatedAt":617},"amazon-braket","run quantum computing workflows on AWS","Runs quantum computing workflows on AWS through Amazon Braket — discovering devices (QPUs and simulators) and their availability, building gate-model circuits and analog Hamiltonian programs, submitting quantum tasks, program sets and hybrid jobs, looking up prices, and capping spend with spending limits. Applies to any request about quantum computing, quantum hardware, quantum simulation, AHS, OpenQASM, or running a quantum algorithm on AWS.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[610,611,614],{"name":23,"slug":8,"type":15},{"name":612,"slug":613,"type":15},"Quantum Computing","quantum-computing",{"name":615,"slug":616,"type":15},"Simulation","simulation","2026-08-20T03:53:19.377174",139,{"items":620,"total":714},[621,634,649,665,679,691,706],{"slug":622,"name":622,"fn":623,"description":624,"org":625,"tags":626,"stars":27,"repoUrl":28,"updatedAt":633},"aws-health-events","analyze AWS Health events for incidents","ALWAYS use this skill in the beginning of any incident investigation, root cause analysis, or operational troubleshooting. This skill retrieves and analyzes AWS Health events (service issues, scheduled changes, and account notifications) to identify AWS-side events that may explain or correlate with observed operational issues. Activate this skill when investigating an issue and you observe service degradation, elevated error rates, latency spikes, connection failures, throttling, capacity issues, deployment-related failures, alarms, or any operational event or issue. This skill searches AWS Health events by service, time window, region, and status to surface active or recent service disruptions, scheduled maintenance, and account-specific notifications that inform the current investigation. Also activate when a user requests a health event summary or report for their account over a specified time period.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[627,628,629,630],{"name":23,"slug":8,"type":15},{"name":25,"slug":26,"type":15},{"name":20,"slug":21,"type":15},{"name":631,"slug":632,"type":15},"Monitoring","monitoring","2026-08-20T03:53:41.178955",{"slug":635,"name":635,"fn":636,"description":637,"org":638,"tags":639,"stars":27,"repoUrl":28,"updatedAt":648},"aws-vpc-dns-investigation","investigate VPC DNS resolution issues","Use this skill when a name is not resolving as expected inside a VPC, or before applying a DNS control-plane change. Activate on symptoms such as NXDOMAIN or SERVFAIL from an EC2 instance, a hostname resolving to a public address when a private endpoint was expected, an AWS service endpoint that stopped resolving after a VPC endpoint or Route 53 change, an application reaching the wrong IP, resolution that works from one instance but not another, IPv6 or dualstack resolution differences, a suspected on-premises forwarding or hybrid DNS problem, or a request to check whether enabling private DNS, adding a Resolver rule, associating a private hosted zone, attaching DNS Firewall, or associating a Route 53 Profile would break anything. It drives the aws-vpc-dns-diagnostics MCP server to observe live resolution from inside the subnet and to simulate a proposed change before it is applied.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[640,641,642,645],{"name":23,"slug":8,"type":15},{"name":25,"slug":26,"type":15},{"name":643,"slug":644,"type":15},"DNS","dns",{"name":646,"slug":647,"type":15},"Networking","networking","2026-08-20T03:53:46.027593",{"slug":650,"name":650,"fn":651,"description":652,"org":653,"tags":654,"stars":27,"repoUrl":28,"updatedAt":664},"crm-production-investigation-guidelines","investigate CRM production incidents","Guidelines for investigating production incidents in the CRM application. Use when triaging any alert or incident involving the CRM REST API, SQS queues, Lambda functions, or Aurora DSQL database in this AWS account. Ensures thorough root cause analysis using AWS-native observability tools.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[655,656,659,660,661],{"name":23,"slug":8,"type":15},{"name":657,"slug":658,"type":15},"CRM","crm",{"name":25,"slug":26,"type":15},{"name":20,"slug":21,"type":15},{"name":662,"slug":663,"type":15},"Operations","operations","2026-08-20T03:53:23.532781",{"slug":666,"name":666,"fn":667,"description":668,"org":669,"tags":670,"stars":27,"repoUrl":28,"updatedAt":678},"database-migration-service-expertise","troubleshoot AWS Database Migration Service","AWS Database Migration Service (DMS) operational review and troubleshooting skill. Conducts best practices validation, health assessments, performance diagnostics, cost optimization reviews, and migration cutover guidance. Triggers on requests like \"DMS review\", \"DMS health check\", \"DMS troubleshooting\", \"migration assessment\", \"DMS best practices audit\", \"DMS cost optimization\", \"replication instance review\", \"CDC latency issue\", or \"DMS task failure\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[671,672,673,674,677],{"name":23,"slug":8,"type":15},{"name":570,"slug":571,"type":15},{"name":25,"slug":26,"type":15},{"name":675,"slug":676,"type":15},"Migration","migration",{"name":662,"slug":663,"type":15},"2026-08-20T03:53:23.927999",{"slug":680,"name":680,"fn":681,"description":682,"org":683,"tags":684,"stars":27,"repoUrl":28,"updatedAt":690},"database-rds-devops","diagnose Aurora MySQL and PostgreSQL databases","Database-level data-plane diagnostics for Aurora MySQL and Aurora PostgreSQL. Executes predefined read-only health check queries via RDS Data API to analyze buffer pool, connections, locks, replication, storage, performance, and index efficiency. Requires the rds-aidba MCP server for database-internal access beyond what CloudWatch and RDS APIs provide.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[685,686,687,688,689],{"name":23,"slug":8,"type":15},{"name":570,"slug":571,"type":15},{"name":25,"slug":26,"type":15},{"name":573,"slug":574,"type":15},{"name":588,"slug":589,"type":15},"2026-08-20T03:53:41.560344",{"slug":692,"name":692,"fn":693,"description":694,"org":695,"tags":696,"stars":27,"repoUrl":28,"updatedAt":705},"eks-operation-review","audit Amazon EKS cluster operations","Comprehensive Amazon EKS operational review aligned with the AWS EKS Best Practices Guide. Use this skill when a user asks to review, audit, or assess EKS clusters for best practices compliance, operational readiness, security posture, cost optimization, reliability, networking, scalability, or upgrade readiness. Triggers on requests like \"EKS review\", \"EKS best practices audit\", \"EKS operational assessment\", \"review my EKS cluster\", or \"EKS health check\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[697,700,701,704],{"name":698,"slug":699,"type":15},"Audit","audit",{"name":23,"slug":8,"type":15},{"name":702,"slug":703,"type":15},"Kubernetes","kubernetes",{"name":662,"slug":663,"type":15},"2026-08-20T03:53:20.524374",{"slug":4,"name":4,"fn":5,"description":6,"org":707,"tags":708,"stars":27,"repoUrl":28,"updatedAt":29},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[709,710,711,712,713],{"name":17,"slug":18,"type":15},{"name":23,"slug":8,"type":15},{"name":25,"slug":26,"type":15},{"name":20,"slug":21,"type":15},{"name":13,"slug":14,"type":15},15]