[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-aws-support-cases":3,"mdc-twsp5f-key":54,"related-repo-aws-support-cases":890,"related-org-aws-support-cases":998},{"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},"support-cases","analyze AWS support cases for troubleshooting","ALWAYS use this skill in the beginning of any incident investigation, root cause analysis, or operational troubleshooting. This skill retrieves and analyzes AWS Support cases (open and resolved) to find historical incidents with similar symptoms, error patterns, or affected services. 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 past support cases by service, time window, severity, and error keywords to surface prior root causes, proven remediations, and recurring patterns that inform the current investigation.",{"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},"Operations","operations","tag",{"name":17,"slug":18,"type":15},"Customer Support","customer-support",{"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","2026-08-20T03:53:18.99645",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\u002Fsupport-cases","---\nname: support-cases\ndescription: ALWAYS use this skill in the beginning of any incident investigation, root cause\n  analysis, or operational troubleshooting. This skill retrieves and analyzes\n  AWS Support cases (open and resolved) to find historical incidents with\n  similar symptoms, error patterns, or affected services. Activate this skill\n  when investigating an issue and you observe service degradation, elevated\n  error rates, latency spikes, connection failures, throttling, capacity issues,\n  deployment-related failures, alarms, or any operational event or issue. This\n  skill searches past support cases by service, time window, severity, and error\n  keywords to surface prior root causes, proven remediations, and recurring\n  patterns that inform the current investigation.\nmetadata:\n  author: udid-aws\n  version: \"1.0.0\"\n  aws-devops-agent-skills.agent-types: \"Chat tasks, Incident RCA\"\n  aws-devops-agent-skills.aws-services: \"AWS Support\"\n  aws-devops-agent-skills.technical-domains: \"Operations\"\n---\n\n# Support Case Review\n\nUse this skill when investigating an incident and you need to review AWS Support\ncases — either the current case associated with the incident or historical cases\nthat may contain relevant context, similar symptoms, or proven remediation steps.\n\n## When to Use This Skill\n\n- An active incident shares symptoms with previously resolved issues.\n- You need to check if a similar support case was filed in the past 24 months.\n- You want to correlate the current incident with known AWS service events.\n- You need to retrieve communications and resolution details from a prior case.\n- You want to identify recurring patterns across multiple support cases.\n\n## Prerequisites\n\n- The AWS account must have a Business Support+, Enterprise Support, or\n  Unified Operations plan (required for the AWS Support API).\n- The agent must have permissions to call `support:DescribeCases` and\n  `support:DescribeCommunications` in the target account.\n- Support case data is available for 24 months after creation. Cases older than\n  24 months cannot be retrieved via the API.\n\n---\n\n## Step 1: Identify the Current Incident Context\n\nBefore searching support cases, gather key details from the current incident:\n\n1. **Affected AWS services** (e.g., EC2, RDS, Lambda, ELB).\n2. **Error messages or error codes** observed in logs or alarms.\n3. **Timeframe** of the incident (start time, duration).\n4. **Affected resources** (instance IDs, ARNs, endpoint names).\n5. **Symptoms** (latency spikes, 5xx errors, connection timeouts, throttling).\n\nUse these details as search criteria when filtering support cases.\n\n---\n\n## Step 2: Search for Related Support Cases\n\nUse the AWS Support API to retrieve cases that may be relevant.\n\n### Retrieve all recent cases (open and resolved)\n\n```\naws support describe-cases \\\n  --include-resolved-cases \\\n  --include-communications \\\n  --after-time \"\u003CISO-8601-start>\" \\\n  --before-time \"\u003CISO-8601-end>\" \\\n  --language \"en\"\n```\n\n### Filter by specific case IDs (if known)\n\n```\naws support describe-cases \\\n  --case-id-list \"case-123456789010-muen-2024\" \\\n  --include-communications\n```\n\n### Key filtering strategies\n\n| Strategy | How to Apply |\n|----------|-------------|\n| By time window | Use `--after-time` and `--before-time` to scope cases to the relevant period (e.g., past 30 days, or around a previous incident date), because recent cases are more likely to reflect current infrastructure state. |\n| By service | Review the `serviceCode` field in returned cases to match the affected service (e.g., `amazon-elastic-compute-cloud`, `amazon-rds`), because the same service often exhibits recurring failure patterns. |\n| By severity | Check the `severityCode` field — focus on `urgent` and `critical` cases for major incidents, because higher-severity cases tend to have more detailed root cause analysis from AWS Support. |\n| By status | Use `--include-resolved-cases` to include closed cases, because resolved cases contain the root cause and remediation steps that are most valuable for correlating with the current incident. |\n| By subject keywords | Scan the `subject` field of returned cases for keywords matching the current incident symptoms, because similar symptoms often share underlying causes. |\n\n---\n\n## Step 3: Review Case Communications\n\nThe `describe-cases` response with `includeCommunications: true` returns the\nmost recent communications for each case in the `recentCommunications` field\n(up to 5 messages). Since root cause analysis and resolution steps are\ntypically in the final messages of a resolved case, this is usually sufficient.\n\nIf the `recentCommunications` field includes a `nextToken`, the case has\nadditional older messages. Only paginate using `describe-communications` if the\nrecent messages do not contain a clear root cause or resolution — for example,\nif the last messages are follow-up questions rather than a final answer.\n\n```\naws support describe-communications \\\n  --case-id \"case-123456789010-muen-2024\" \\\n  --max-results 10 \\\n  --next-token \"\u003CnextToken-from-recentCommunications>\"\n```\n\nWhen reviewing communications, look for:\n\n1. **Root cause statements** — AWS Support engineers often summarize the root\n   cause in their final response.\n2. **Remediation steps** — Specific actions taken to resolve the issue (e.g.,\n   \"increased max_connections\", \"applied security group rule\", \"scaled up\n   instance type\").\n3. **Configuration recommendations** — Best practices or tuning suggestions\n   provided by AWS.\n4. **Escalation notes** — If the case was escalated, check for deeper technical\n   analysis from specialized teams.\n\n---\n\n## Step 4: Correlate Findings with Current Incident\n\nAfter reviewing relevant cases, correlate the findings:\n\n### Pattern matching checklist\n\n- [ ] Do past cases share the same affected service and resource type?\n- [ ] Are the error messages or codes identical or similar?\n- [ ] Did past incidents occur at a similar time of day or day of week (indicating load patterns)?\n- [ ] Was the root cause a configuration issue that may still be present?\n- [ ] Was the resolution a temporary workaround that has since expired or been reverted?\n- [ ] Did AWS identify a service-side issue that may be recurring?\n\n### Relevance scoring\n\nRate each historical case on relevance to the current incident:\n\n| Score | Criteria |\n|-------|----------|\n| High | Same service, same error, same resource type, similar timeframe |\n| Medium | Same service, different error but related symptoms |\n| Low | Different service but similar architectural pattern or failure mode |\n\n---\n\n## Step 5: Summarize Findings\n\nProvide a structured summary including:\n\n1. **Number of related cases found** — How many past cases matched the search\n   criteria.\n2. **Most relevant case(s)** — Case ID, subject, status, and creation date of\n   the top matches.\n3. **Historical root causes** — What caused similar issues in the past.\n4. **Past resolutions** — What remediation steps were applied and whether they\n   were permanent fixes or temporary workarounds.\n5. **Recommendations** — Based on historical patterns, suggest investigation\n   paths or remediation steps for the current incident.\n6. **Recurring pattern alert** — If the same issue has occurred multiple times,\n   flag it as a recurring problem requiring a permanent fix or architectural\n   change.\n\n---\n\n## Decision Tree: Case Search Strategy\n\n```\nIs there a known case ID associated with the current incident?\n├── YES → Retrieve that specific case and its communications (Step 2, filter by case ID)\n└── NO → Continue below\n\nIs the affected AWS service known?\n├── YES → Search cases in the past 90 days for that service, then expand to 12 months if needed\n└── NO → Search all cases in the past 30 days and filter by error keywords\n\nWere relevant historical cases found?\n├── YES → Review communications (Step 3), correlate findings (Step 4), summarize (Step 5)\n└── NO → Broaden search criteria:\n         - Expand time window\n         - Search by related services (e.g., if ELB is affected, also check EC2 and Target Group cases)\n         - Search by error code or symptom keywords in case subjects\n```\n\n---\n\n## Tips for Effective Case Review\n\n- **Start narrow, then broaden**: Begin with specific filters (service + time\n  window) and expand only if no relevant cases are found.\n- **Check resolved cases**: The most valuable information often comes from\n  resolved cases where root cause and fix are documented.\n- **Note case severity patterns**: If past cases for the same issue were filed\n  at `critical` severity, the current incident may warrant similar urgency.\n- **Cross-reference with deployments**: If a past case was caused by a\n  deployment, check if a similar deployment occurred before the current incident.\n",{"data":55,"body":62},{"name":4,"description":6,"metadata":56},{"author":57,"version":58,"aws-devops-agent-skills":59},"udid-aws","1.0.0",{"agent-types":60,"aws-services":61,"technical-domains":13},"Chat tasks, Incident RCA","AWS Support",{"type":63,"children":64},"root",[65,74,80,87,117,123,158,162,168,173,228,233,236,242,247,254,266,272,281,287,458,461,467,496,524,533,538,581,584,590,595,601,664,670,675,736,739,745,750,813,816,822,831,834,840],{"type":66,"tag":67,"props":68,"children":70},"element","h1",{"id":69},"support-case-review",[71],{"type":72,"value":73},"text","Support Case Review",{"type":66,"tag":75,"props":76,"children":77},"p",{},[78],{"type":72,"value":79},"Use this skill when investigating an incident and you need to review AWS Support\ncases — either the current case associated with the incident or historical cases\nthat may contain relevant context, similar symptoms, or proven remediation steps.",{"type":66,"tag":81,"props":82,"children":84},"h2",{"id":83},"when-to-use-this-skill",[85],{"type":72,"value":86},"When to Use This Skill",{"type":66,"tag":88,"props":89,"children":90},"ul",{},[91,97,102,107,112],{"type":66,"tag":92,"props":93,"children":94},"li",{},[95],{"type":72,"value":96},"An active incident shares symptoms with previously resolved issues.",{"type":66,"tag":92,"props":98,"children":99},{},[100],{"type":72,"value":101},"You need to check if a similar support case was filed in the past 24 months.",{"type":66,"tag":92,"props":103,"children":104},{},[105],{"type":72,"value":106},"You want to correlate the current incident with known AWS service events.",{"type":66,"tag":92,"props":108,"children":109},{},[110],{"type":72,"value":111},"You need to retrieve communications and resolution details from a prior case.",{"type":66,"tag":92,"props":113,"children":114},{},[115],{"type":72,"value":116},"You want to identify recurring patterns across multiple support cases.",{"type":66,"tag":81,"props":118,"children":120},{"id":119},"prerequisites",[121],{"type":72,"value":122},"Prerequisites",{"type":66,"tag":88,"props":124,"children":125},{},[126,131,153],{"type":66,"tag":92,"props":127,"children":128},{},[129],{"type":72,"value":130},"The AWS account must have a Business Support+, Enterprise Support, or\nUnified Operations plan (required for the AWS Support API).",{"type":66,"tag":92,"props":132,"children":133},{},[134,136,143,145,151],{"type":72,"value":135},"The agent must have permissions to call ",{"type":66,"tag":137,"props":138,"children":140},"code",{"className":139},[],[141],{"type":72,"value":142},"support:DescribeCases",{"type":72,"value":144}," and\n",{"type":66,"tag":137,"props":146,"children":148},{"className":147},[],[149],{"type":72,"value":150},"support:DescribeCommunications",{"type":72,"value":152}," in the target account.",{"type":66,"tag":92,"props":154,"children":155},{},[156],{"type":72,"value":157},"Support case data is available for 24 months after creation. Cases older than\n24 months cannot be retrieved via the API.",{"type":66,"tag":159,"props":160,"children":161},"hr",{},[],{"type":66,"tag":81,"props":163,"children":165},{"id":164},"step-1-identify-the-current-incident-context",[166],{"type":72,"value":167},"Step 1: Identify the Current Incident Context",{"type":66,"tag":75,"props":169,"children":170},{},[171],{"type":72,"value":172},"Before searching support cases, gather key details from the current incident:",{"type":66,"tag":174,"props":175,"children":176},"ol",{},[177,188,198,208,218],{"type":66,"tag":92,"props":178,"children":179},{},[180,186],{"type":66,"tag":181,"props":182,"children":183},"strong",{},[184],{"type":72,"value":185},"Affected AWS services",{"type":72,"value":187}," (e.g., EC2, RDS, Lambda, ELB).",{"type":66,"tag":92,"props":189,"children":190},{},[191,196],{"type":66,"tag":181,"props":192,"children":193},{},[194],{"type":72,"value":195},"Error messages or error codes",{"type":72,"value":197}," observed in logs or alarms.",{"type":66,"tag":92,"props":199,"children":200},{},[201,206],{"type":66,"tag":181,"props":202,"children":203},{},[204],{"type":72,"value":205},"Timeframe",{"type":72,"value":207}," of the incident (start time, duration).",{"type":66,"tag":92,"props":209,"children":210},{},[211,216],{"type":66,"tag":181,"props":212,"children":213},{},[214],{"type":72,"value":215},"Affected resources",{"type":72,"value":217}," (instance IDs, ARNs, endpoint names).",{"type":66,"tag":92,"props":219,"children":220},{},[221,226],{"type":66,"tag":181,"props":222,"children":223},{},[224],{"type":72,"value":225},"Symptoms",{"type":72,"value":227}," (latency spikes, 5xx errors, connection timeouts, throttling).",{"type":66,"tag":75,"props":229,"children":230},{},[231],{"type":72,"value":232},"Use these details as search criteria when filtering support cases.",{"type":66,"tag":159,"props":234,"children":235},{},[],{"type":66,"tag":81,"props":237,"children":239},{"id":238},"step-2-search-for-related-support-cases",[240],{"type":72,"value":241},"Step 2: Search for Related Support Cases",{"type":66,"tag":75,"props":243,"children":244},{},[245],{"type":72,"value":246},"Use the AWS Support API to retrieve cases that may be relevant.",{"type":66,"tag":248,"props":249,"children":251},"h3",{"id":250},"retrieve-all-recent-cases-open-and-resolved",[252],{"type":72,"value":253},"Retrieve all recent cases (open and resolved)",{"type":66,"tag":255,"props":256,"children":260},"pre",{"className":257,"code":259,"language":72},[258],"language-text","aws support describe-cases \\\n  --include-resolved-cases \\\n  --include-communications \\\n  --after-time \"\u003CISO-8601-start>\" \\\n  --before-time \"\u003CISO-8601-end>\" \\\n  --language \"en\"\n",[261],{"type":66,"tag":137,"props":262,"children":264},{"__ignoreMap":263},"",[265],{"type":72,"value":259},{"type":66,"tag":248,"props":267,"children":269},{"id":268},"filter-by-specific-case-ids-if-known",[270],{"type":72,"value":271},"Filter by specific case IDs (if known)",{"type":66,"tag":255,"props":273,"children":276},{"className":274,"code":275,"language":72},[258],"aws support describe-cases \\\n  --case-id-list \"case-123456789010-muen-2024\" \\\n  --include-communications\n",[277],{"type":66,"tag":137,"props":278,"children":279},{"__ignoreMap":263},[280],{"type":72,"value":275},{"type":66,"tag":248,"props":282,"children":284},{"id":283},"key-filtering-strategies",[285],{"type":72,"value":286},"Key filtering strategies",{"type":66,"tag":288,"props":289,"children":290},"table",{},[291,310],{"type":66,"tag":292,"props":293,"children":294},"thead",{},[295],{"type":66,"tag":296,"props":297,"children":298},"tr",{},[299,305],{"type":66,"tag":300,"props":301,"children":302},"th",{},[303],{"type":72,"value":304},"Strategy",{"type":66,"tag":300,"props":306,"children":307},{},[308],{"type":72,"value":309},"How to Apply",{"type":66,"tag":311,"props":312,"children":313},"tbody",{},[314,344,381,417,437],{"type":66,"tag":296,"props":315,"children":316},{},[317,323],{"type":66,"tag":318,"props":319,"children":320},"td",{},[321],{"type":72,"value":322},"By time window",{"type":66,"tag":318,"props":324,"children":325},{},[326,328,334,336,342],{"type":72,"value":327},"Use ",{"type":66,"tag":137,"props":329,"children":331},{"className":330},[],[332],{"type":72,"value":333},"--after-time",{"type":72,"value":335}," and ",{"type":66,"tag":137,"props":337,"children":339},{"className":338},[],[340],{"type":72,"value":341},"--before-time",{"type":72,"value":343}," to scope cases to the relevant period (e.g., past 30 days, or around a previous incident date), because recent cases are more likely to reflect current infrastructure state.",{"type":66,"tag":296,"props":345,"children":346},{},[347,352],{"type":66,"tag":318,"props":348,"children":349},{},[350],{"type":72,"value":351},"By service",{"type":66,"tag":318,"props":353,"children":354},{},[355,357,363,365,371,373,379],{"type":72,"value":356},"Review the ",{"type":66,"tag":137,"props":358,"children":360},{"className":359},[],[361],{"type":72,"value":362},"serviceCode",{"type":72,"value":364}," field in returned cases to match the affected service (e.g., ",{"type":66,"tag":137,"props":366,"children":368},{"className":367},[],[369],{"type":72,"value":370},"amazon-elastic-compute-cloud",{"type":72,"value":372},", ",{"type":66,"tag":137,"props":374,"children":376},{"className":375},[],[377],{"type":72,"value":378},"amazon-rds",{"type":72,"value":380},"), because the same service often exhibits recurring failure patterns.",{"type":66,"tag":296,"props":382,"children":383},{},[384,389],{"type":66,"tag":318,"props":385,"children":386},{},[387],{"type":72,"value":388},"By severity",{"type":66,"tag":318,"props":390,"children":391},{},[392,394,400,402,408,409,415],{"type":72,"value":393},"Check the ",{"type":66,"tag":137,"props":395,"children":397},{"className":396},[],[398],{"type":72,"value":399},"severityCode",{"type":72,"value":401}," field — focus on ",{"type":66,"tag":137,"props":403,"children":405},{"className":404},[],[406],{"type":72,"value":407},"urgent",{"type":72,"value":335},{"type":66,"tag":137,"props":410,"children":412},{"className":411},[],[413],{"type":72,"value":414},"critical",{"type":72,"value":416}," cases for major incidents, because higher-severity cases tend to have more detailed root cause analysis from AWS Support.",{"type":66,"tag":296,"props":418,"children":419},{},[420,425],{"type":66,"tag":318,"props":421,"children":422},{},[423],{"type":72,"value":424},"By status",{"type":66,"tag":318,"props":426,"children":427},{},[428,429,435],{"type":72,"value":327},{"type":66,"tag":137,"props":430,"children":432},{"className":431},[],[433],{"type":72,"value":434},"--include-resolved-cases",{"type":72,"value":436}," to include closed cases, because resolved cases contain the root cause and remediation steps that are most valuable for correlating with the current incident.",{"type":66,"tag":296,"props":438,"children":439},{},[440,445],{"type":66,"tag":318,"props":441,"children":442},{},[443],{"type":72,"value":444},"By subject keywords",{"type":66,"tag":318,"props":446,"children":447},{},[448,450,456],{"type":72,"value":449},"Scan the ",{"type":66,"tag":137,"props":451,"children":453},{"className":452},[],[454],{"type":72,"value":455},"subject",{"type":72,"value":457}," field of returned cases for keywords matching the current incident symptoms, because similar symptoms often share underlying causes.",{"type":66,"tag":159,"props":459,"children":460},{},[],{"type":66,"tag":81,"props":462,"children":464},{"id":463},"step-3-review-case-communications",[465],{"type":72,"value":466},"Step 3: Review Case Communications",{"type":66,"tag":75,"props":468,"children":469},{},[470,472,478,480,486,488,494],{"type":72,"value":471},"The ",{"type":66,"tag":137,"props":473,"children":475},{"className":474},[],[476],{"type":72,"value":477},"describe-cases",{"type":72,"value":479}," response with ",{"type":66,"tag":137,"props":481,"children":483},{"className":482},[],[484],{"type":72,"value":485},"includeCommunications: true",{"type":72,"value":487}," returns the\nmost recent communications for each case in the ",{"type":66,"tag":137,"props":489,"children":491},{"className":490},[],[492],{"type":72,"value":493},"recentCommunications",{"type":72,"value":495}," field\n(up to 5 messages). Since root cause analysis and resolution steps are\ntypically in the final messages of a resolved case, this is usually sufficient.",{"type":66,"tag":75,"props":497,"children":498},{},[499,501,506,508,514,516,522],{"type":72,"value":500},"If the ",{"type":66,"tag":137,"props":502,"children":504},{"className":503},[],[505],{"type":72,"value":493},{"type":72,"value":507}," field includes a ",{"type":66,"tag":137,"props":509,"children":511},{"className":510},[],[512],{"type":72,"value":513},"nextToken",{"type":72,"value":515},", the case has\nadditional older messages. Only paginate using ",{"type":66,"tag":137,"props":517,"children":519},{"className":518},[],[520],{"type":72,"value":521},"describe-communications",{"type":72,"value":523}," if the\nrecent messages do not contain a clear root cause or resolution — for example,\nif the last messages are follow-up questions rather than a final answer.",{"type":66,"tag":255,"props":525,"children":528},{"className":526,"code":527,"language":72},[258],"aws support describe-communications \\\n  --case-id \"case-123456789010-muen-2024\" \\\n  --max-results 10 \\\n  --next-token \"\u003CnextToken-from-recentCommunications>\"\n",[529],{"type":66,"tag":137,"props":530,"children":531},{"__ignoreMap":263},[532],{"type":72,"value":527},{"type":66,"tag":75,"props":534,"children":535},{},[536],{"type":72,"value":537},"When reviewing communications, look for:",{"type":66,"tag":174,"props":539,"children":540},{},[541,551,561,571],{"type":66,"tag":92,"props":542,"children":543},{},[544,549],{"type":66,"tag":181,"props":545,"children":546},{},[547],{"type":72,"value":548},"Root cause statements",{"type":72,"value":550}," — AWS Support engineers often summarize the root\ncause in their final response.",{"type":66,"tag":92,"props":552,"children":553},{},[554,559],{"type":66,"tag":181,"props":555,"children":556},{},[557],{"type":72,"value":558},"Remediation steps",{"type":72,"value":560}," — Specific actions taken to resolve the issue (e.g.,\n\"increased max_connections\", \"applied security group rule\", \"scaled up\ninstance type\").",{"type":66,"tag":92,"props":562,"children":563},{},[564,569],{"type":66,"tag":181,"props":565,"children":566},{},[567],{"type":72,"value":568},"Configuration recommendations",{"type":72,"value":570}," — Best practices or tuning suggestions\nprovided by AWS.",{"type":66,"tag":92,"props":572,"children":573},{},[574,579],{"type":66,"tag":181,"props":575,"children":576},{},[577],{"type":72,"value":578},"Escalation notes",{"type":72,"value":580}," — If the case was escalated, check for deeper technical\nanalysis from specialized teams.",{"type":66,"tag":159,"props":582,"children":583},{},[],{"type":66,"tag":81,"props":585,"children":587},{"id":586},"step-4-correlate-findings-with-current-incident",[588],{"type":72,"value":589},"Step 4: Correlate Findings with Current Incident",{"type":66,"tag":75,"props":591,"children":592},{},[593],{"type":72,"value":594},"After reviewing relevant cases, correlate the findings:",{"type":66,"tag":248,"props":596,"children":598},{"id":597},"pattern-matching-checklist",[599],{"type":72,"value":600},"Pattern matching checklist",{"type":66,"tag":88,"props":602,"children":605},{"className":603},[604],"contains-task-list",[606,619,628,637,646,655],{"type":66,"tag":92,"props":607,"children":610},{"className":608},[609],"task-list-item",[611,617],{"type":66,"tag":612,"props":613,"children":616},"input",{"disabled":614,"type":615},true,"checkbox",[],{"type":72,"value":618}," Do past cases share the same affected service and resource type?",{"type":66,"tag":92,"props":620,"children":622},{"className":621},[609],[623,626],{"type":66,"tag":612,"props":624,"children":625},{"disabled":614,"type":615},[],{"type":72,"value":627}," Are the error messages or codes identical or similar?",{"type":66,"tag":92,"props":629,"children":631},{"className":630},[609],[632,635],{"type":66,"tag":612,"props":633,"children":634},{"disabled":614,"type":615},[],{"type":72,"value":636}," Did past incidents occur at a similar time of day or day of week (indicating load patterns)?",{"type":66,"tag":92,"props":638,"children":640},{"className":639},[609],[641,644],{"type":66,"tag":612,"props":642,"children":643},{"disabled":614,"type":615},[],{"type":72,"value":645}," Was the root cause a configuration issue that may still be present?",{"type":66,"tag":92,"props":647,"children":649},{"className":648},[609],[650,653],{"type":66,"tag":612,"props":651,"children":652},{"disabled":614,"type":615},[],{"type":72,"value":654}," Was the resolution a temporary workaround that has since expired or been reverted?",{"type":66,"tag":92,"props":656,"children":658},{"className":657},[609],[659,662],{"type":66,"tag":612,"props":660,"children":661},{"disabled":614,"type":615},[],{"type":72,"value":663}," Did AWS identify a service-side issue that may be recurring?",{"type":66,"tag":248,"props":665,"children":667},{"id":666},"relevance-scoring",[668],{"type":72,"value":669},"Relevance scoring",{"type":66,"tag":75,"props":671,"children":672},{},[673],{"type":72,"value":674},"Rate each historical case on relevance to the current incident:",{"type":66,"tag":288,"props":676,"children":677},{},[678,694],{"type":66,"tag":292,"props":679,"children":680},{},[681],{"type":66,"tag":296,"props":682,"children":683},{},[684,689],{"type":66,"tag":300,"props":685,"children":686},{},[687],{"type":72,"value":688},"Score",{"type":66,"tag":300,"props":690,"children":691},{},[692],{"type":72,"value":693},"Criteria",{"type":66,"tag":311,"props":695,"children":696},{},[697,710,723],{"type":66,"tag":296,"props":698,"children":699},{},[700,705],{"type":66,"tag":318,"props":701,"children":702},{},[703],{"type":72,"value":704},"High",{"type":66,"tag":318,"props":706,"children":707},{},[708],{"type":72,"value":709},"Same service, same error, same resource type, similar timeframe",{"type":66,"tag":296,"props":711,"children":712},{},[713,718],{"type":66,"tag":318,"props":714,"children":715},{},[716],{"type":72,"value":717},"Medium",{"type":66,"tag":318,"props":719,"children":720},{},[721],{"type":72,"value":722},"Same service, different error but related symptoms",{"type":66,"tag":296,"props":724,"children":725},{},[726,731],{"type":66,"tag":318,"props":727,"children":728},{},[729],{"type":72,"value":730},"Low",{"type":66,"tag":318,"props":732,"children":733},{},[734],{"type":72,"value":735},"Different service but similar architectural pattern or failure mode",{"type":66,"tag":159,"props":737,"children":738},{},[],{"type":66,"tag":81,"props":740,"children":742},{"id":741},"step-5-summarize-findings",[743],{"type":72,"value":744},"Step 5: Summarize Findings",{"type":66,"tag":75,"props":746,"children":747},{},[748],{"type":72,"value":749},"Provide a structured summary including:",{"type":66,"tag":174,"props":751,"children":752},{},[753,763,773,783,793,803],{"type":66,"tag":92,"props":754,"children":755},{},[756,761],{"type":66,"tag":181,"props":757,"children":758},{},[759],{"type":72,"value":760},"Number of related cases found",{"type":72,"value":762}," — How many past cases matched the search\ncriteria.",{"type":66,"tag":92,"props":764,"children":765},{},[766,771],{"type":66,"tag":181,"props":767,"children":768},{},[769],{"type":72,"value":770},"Most relevant case(s)",{"type":72,"value":772}," — Case ID, subject, status, and creation date of\nthe top matches.",{"type":66,"tag":92,"props":774,"children":775},{},[776,781],{"type":66,"tag":181,"props":777,"children":778},{},[779],{"type":72,"value":780},"Historical root causes",{"type":72,"value":782}," — What caused similar issues in the past.",{"type":66,"tag":92,"props":784,"children":785},{},[786,791],{"type":66,"tag":181,"props":787,"children":788},{},[789],{"type":72,"value":790},"Past resolutions",{"type":72,"value":792}," — What remediation steps were applied and whether they\nwere permanent fixes or temporary workarounds.",{"type":66,"tag":92,"props":794,"children":795},{},[796,801],{"type":66,"tag":181,"props":797,"children":798},{},[799],{"type":72,"value":800},"Recommendations",{"type":72,"value":802}," — Based on historical patterns, suggest investigation\npaths or remediation steps for the current incident.",{"type":66,"tag":92,"props":804,"children":805},{},[806,811],{"type":66,"tag":181,"props":807,"children":808},{},[809],{"type":72,"value":810},"Recurring pattern alert",{"type":72,"value":812}," — If the same issue has occurred multiple times,\nflag it as a recurring problem requiring a permanent fix or architectural\nchange.",{"type":66,"tag":159,"props":814,"children":815},{},[],{"type":66,"tag":81,"props":817,"children":819},{"id":818},"decision-tree-case-search-strategy",[820],{"type":72,"value":821},"Decision Tree: Case Search Strategy",{"type":66,"tag":255,"props":823,"children":826},{"className":824,"code":825,"language":72},[258],"Is there a known case ID associated with the current incident?\n├── YES → Retrieve that specific case and its communications (Step 2, filter by case ID)\n└── NO → Continue below\n\nIs the affected AWS service known?\n├── YES → Search cases in the past 90 days for that service, then expand to 12 months if needed\n└── NO → Search all cases in the past 30 days and filter by error keywords\n\nWere relevant historical cases found?\n├── YES → Review communications (Step 3), correlate findings (Step 4), summarize (Step 5)\n└── NO → Broaden search criteria:\n         - Expand time window\n         - Search by related services (e.g., if ELB is affected, also check EC2 and Target Group cases)\n         - Search by error code or symptom keywords in case subjects\n",[827],{"type":66,"tag":137,"props":828,"children":829},{"__ignoreMap":263},[830],{"type":72,"value":825},{"type":66,"tag":159,"props":832,"children":833},{},[],{"type":66,"tag":81,"props":835,"children":837},{"id":836},"tips-for-effective-case-review",[838],{"type":72,"value":839},"Tips for Effective Case Review",{"type":66,"tag":88,"props":841,"children":842},{},[843,853,863,880],{"type":66,"tag":92,"props":844,"children":845},{},[846,851],{"type":66,"tag":181,"props":847,"children":848},{},[849],{"type":72,"value":850},"Start narrow, then broaden",{"type":72,"value":852},": Begin with specific filters (service + time\nwindow) and expand only if no relevant cases are found.",{"type":66,"tag":92,"props":854,"children":855},{},[856,861],{"type":66,"tag":181,"props":857,"children":858},{},[859],{"type":72,"value":860},"Check resolved cases",{"type":72,"value":862},": The most valuable information often comes from\nresolved cases where root cause and fix are documented.",{"type":66,"tag":92,"props":864,"children":865},{},[866,871,873,878],{"type":66,"tag":181,"props":867,"children":868},{},[869],{"type":72,"value":870},"Note case severity patterns",{"type":72,"value":872},": If past cases for the same issue were filed\nat ",{"type":66,"tag":137,"props":874,"children":876},{"className":875},[],[877],{"type":72,"value":414},{"type":72,"value":879}," severity, the current incident may warrant similar urgency.",{"type":66,"tag":92,"props":881,"children":882},{},[883,888],{"type":66,"tag":181,"props":884,"children":885},{},[886],{"type":72,"value":887},"Cross-reference with deployments",{"type":72,"value":889},": If a past case was caused by a\ndeployment, check if a similar deployment occurred before the current incident.",{"items":891,"total":997},[892,905,920,934,950,966,981],{"slug":893,"name":893,"fn":894,"description":895,"org":896,"tags":897,"stars":27,"repoUrl":28,"updatedAt":904},"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},[898,899,900,901],{"name":23,"slug":8,"type":15},{"name":25,"slug":26,"type":15},{"name":20,"slug":21,"type":15},{"name":902,"slug":903,"type":15},"Monitoring","monitoring","2026-08-20T03:53:41.178955",{"slug":906,"name":906,"fn":907,"description":908,"org":909,"tags":910,"stars":27,"repoUrl":28,"updatedAt":919},"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},[911,912,913,916],{"name":23,"slug":8,"type":15},{"name":25,"slug":26,"type":15},{"name":914,"slug":915,"type":15},"DNS","dns",{"name":917,"slug":918,"type":15},"Networking","networking","2026-08-20T03:53:46.027593",{"slug":921,"name":921,"fn":922,"description":923,"org":924,"tags":925,"stars":27,"repoUrl":28,"updatedAt":933},"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},[926,927,930,931,932],{"name":23,"slug":8,"type":15},{"name":928,"slug":929,"type":15},"CRM","crm",{"name":25,"slug":26,"type":15},{"name":20,"slug":21,"type":15},{"name":13,"slug":14,"type":15},"2026-08-20T03:53:23.532781",{"slug":935,"name":935,"fn":936,"description":937,"org":938,"tags":939,"stars":27,"repoUrl":28,"updatedAt":949},"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},[940,941,944,945,948],{"name":23,"slug":8,"type":15},{"name":942,"slug":943,"type":15},"Database","database",{"name":25,"slug":26,"type":15},{"name":946,"slug":947,"type":15},"Migration","migration",{"name":13,"slug":14,"type":15},"2026-08-20T03:53:23.927999",{"slug":951,"name":951,"fn":952,"description":953,"org":954,"tags":955,"stars":27,"repoUrl":28,"updatedAt":965},"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},[956,957,958,959,962],{"name":23,"slug":8,"type":15},{"name":942,"slug":943,"type":15},{"name":25,"slug":26,"type":15},{"name":960,"slug":961,"type":15},"MySQL","mysql",{"name":963,"slug":964,"type":15},"PostgreSQL","postgresql","2026-08-20T03:53:41.560344",{"slug":967,"name":967,"fn":968,"description":969,"org":970,"tags":971,"stars":27,"repoUrl":28,"updatedAt":980},"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},[972,975,976,979],{"name":973,"slug":974,"type":15},"Audit","audit",{"name":23,"slug":8,"type":15},{"name":977,"slug":978,"type":15},"Kubernetes","kubernetes",{"name":13,"slug":14,"type":15},"2026-08-20T03:53:20.524374",{"slug":982,"name":982,"fn":983,"description":984,"org":985,"tags":986,"stars":27,"repoUrl":28,"updatedAt":996},"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},[987,990,991,992,993],{"name":988,"slug":989,"type":15},"Auth","auth",{"name":23,"slug":8,"type":15},{"name":25,"slug":26,"type":15},{"name":20,"slug":21,"type":15},{"name":994,"slug":995,"type":15},"Security","security","2026-08-20T03:53:23.097965",15,{"items":999,"total":1164},[1000,1018,1033,1046,1061,1071,1084,1100,1114,1127,1138,1150],{"slug":1001,"name":1001,"fn":1002,"description":1003,"org":1004,"tags":1005,"stars":1015,"repoUrl":1016,"updatedAt":1017},"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},[1006,1008,1011,1012],{"name":1007,"slug":35,"type":15},"Agents",{"name":1009,"slug":1010,"type":15},"Automation","automation",{"name":23,"slug":8,"type":15},{"name":1013,"slug":1014,"type":15},"Engineering","engineering",1822,"https:\u002F\u002Fgithub.com\u002Faws\u002Fagent-toolkit-for-aws","2026-08-20T03:27:06.137661",{"slug":1019,"name":1019,"fn":1020,"description":1021,"org":1022,"tags":1023,"stars":1015,"repoUrl":1016,"updatedAt":1032},"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},[1024,1025,1028,1031],{"name":1007,"slug":35,"type":15},{"name":1026,"slug":1027,"type":15},"API Development","api-development",{"name":1029,"slug":1030,"type":15},"Authentication","authentication",{"name":23,"slug":8,"type":15},"2026-07-16T06:00:38.866147",{"slug":1034,"name":1034,"fn":1035,"description":1036,"org":1037,"tags":1038,"stars":1015,"repoUrl":1016,"updatedAt":1045},"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},[1039,1040,1041,1042],{"name":1007,"slug":35,"type":15},{"name":23,"slug":8,"type":15},{"name":25,"slug":26,"type":15},{"name":1043,"slug":1044,"type":15},"Observability","observability","2026-07-16T06:00:44.679093",{"slug":1047,"name":1047,"fn":1048,"description":1049,"org":1050,"tags":1051,"stars":1015,"repoUrl":1016,"updatedAt":1060},"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},[1052,1053,1054,1057],{"name":1007,"slug":35,"type":15},{"name":23,"slug":8,"type":15},{"name":1055,"slug":1056,"type":15},"CI\u002FCD","ci-cd",{"name":1058,"slug":1059,"type":15},"Deployment","deployment","2026-07-12T08:42:55.059577",{"slug":1062,"name":1062,"fn":1063,"description":1064,"org":1065,"tags":1066,"stars":1015,"repoUrl":1016,"updatedAt":1070},"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},[1067,1068,1069],{"name":1007,"slug":35,"type":15},{"name":23,"slug":8,"type":15},{"name":1058,"slug":1059,"type":15},"2026-07-12T08:42:51.963247",{"slug":1072,"name":1072,"fn":1073,"description":1074,"org":1075,"tags":1076,"stars":1015,"repoUrl":1016,"updatedAt":1083},"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},[1077,1078,1079,1082],{"name":1007,"slug":35,"type":15},{"name":23,"slug":8,"type":15},{"name":1080,"slug":1081,"type":15},"Best Practices","best-practices",{"name":994,"slug":995,"type":15},"2026-07-16T06:00:42.174705",{"slug":1085,"name":1085,"fn":1086,"description":1087,"org":1088,"tags":1089,"stars":1015,"repoUrl":1016,"updatedAt":1099},"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},[1090,1091,1092,1095,1096],{"name":1007,"slug":35,"type":15},{"name":23,"slug":8,"type":15},{"name":1093,"slug":1094,"type":15},"Evals","evals",{"name":1043,"slug":1044,"type":15},{"name":1097,"slug":1098,"type":15},"Performance","performance","2026-07-12T08:42:56.488105",{"slug":1101,"name":1101,"fn":1102,"description":1103,"org":1104,"tags":1105,"stars":1015,"repoUrl":1016,"updatedAt":1113},"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},[1106,1107,1108,1111],{"name":1007,"slug":35,"type":15},{"name":1009,"slug":1010,"type":15},{"name":1109,"slug":1110,"type":15},"Payments","payments",{"name":1112,"slug":1112,"type":15},"x402","2026-08-10T04:16:31.844309",{"slug":1115,"name":1115,"fn":1116,"description":1117,"org":1118,"tags":1119,"stars":1015,"repoUrl":1016,"updatedAt":1126},"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},[1120,1121,1122,1123],{"name":23,"slug":8,"type":15},{"name":942,"slug":943,"type":15},{"name":960,"slug":961,"type":15},{"name":1124,"slug":1125,"type":15},"Serverless","serverless","2026-07-12T08:43:13.27939",{"slug":1128,"name":1128,"fn":1129,"description":1130,"org":1131,"tags":1132,"stars":1015,"repoUrl":1016,"updatedAt":1137},"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},[1133,1134,1135,1136],{"name":23,"slug":8,"type":15},{"name":942,"slug":943,"type":15},{"name":963,"slug":964,"type":15},{"name":1124,"slug":1125,"type":15},"2026-07-16T06:00:34.789624",{"slug":1139,"name":1139,"fn":1140,"description":1141,"org":1142,"tags":1143,"stars":1015,"repoUrl":1016,"updatedAt":1149},"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},[1144,1145,1146],{"name":1007,"slug":35,"type":15},{"name":23,"slug":8,"type":15},{"name":1147,"slug":1148,"type":15},"LLM","llm","2026-08-07T04:38:13.03499",{"slug":1151,"name":1151,"fn":1152,"description":1153,"org":1154,"tags":1155,"stars":1015,"repoUrl":1016,"updatedAt":1163},"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},[1156,1157,1160],{"name":23,"slug":8,"type":15},{"name":1158,"slug":1159,"type":15},"Quantum Computing","quantum-computing",{"name":1161,"slug":1162,"type":15},"Simulation","simulation","2026-08-20T03:53:19.377174",139]