support-cases
ALWAYS use this skill in the beginning of any incident investigation, root cause
Install
npx skills add https://github.com/aws/tools-for-devops-agent/tree/main/skills/support-cases
claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install aws-tools-for-devops-agent@llmmart
git clone https://github.com/aws/tools-for-devops-agent.git
The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole aws/tools-for-devops-agent collection as a plugin from our marketplace. Git is the plain clone.
README
Support Cases Skill
This skill enables the AWS DevOps Agent to retrieve and analyze AWS Support cases during incident investigation, root cause analysis, and operational troubleshooting.
Purpose
When an operational incident occurs, historical support cases often contain valuable context — prior root causes, proven remediations, and recurring patterns. This skill searches past AWS Support cases by service, time window, severity, and error keywords to surface relevant history that informs the current investigation.
Key Capabilities
- Retrieve open and resolved AWS Support cases via the Support API
- Search and filter cases by service, severity, time range, and keywords
- Review case communications for root cause statements and remediation steps
- Correlate historical findings with current incident symptoms
- Identify recurring patterns that may require permanent fixes
Prerequisites
- AWS account with Business Support+, Enterprise Support, or Unified Operations plan
- Agent permissions for
support:DescribeCasesandsupport:DescribeCommunications
Limitations
- Support case data is only available for up to 24 months after creation
Agent Types
This skill is used by the following agent types:
- Chat tasks — conversational support case lookup and analysis
- Incident RCA — root cause analysis during active incidents
Uploading to AWS DevOps Agent
To deploy this skill to your Agent Space, you can use any of three ways:
Option A: Import from GitHub (recommended)
If you have a GitHub connection configured in your Agent Space, you can import this skill directly from the repository. In the DevOps Agent web app, go to Settings → Add Skill → Import from repository, then point to the skills/support-cases directory. See Importing a skill from a repository for full instructions.
Note: You cannot connect the
awsGitHub organization directly because the GitHub connection setup requires admin rights on the organization. Instead, connect your personal GitHub account and select any repository from it during the connection setup. Once a GitHub connection is established, you can import skills from any public repository — including this one — even if it wasn't selected during the connection setup.
Option B: Upload as a zip file
Zip the
support-cases/directory (only including allowed extensions):cd skills zip -r support-cases.zip support-cases/ -i '*.md' '*.txt' '*.json' '*.yaml' '*.yml' '*.xml' '*.csv' '*.tsv' '*.html' '*.htm' '*.png' '*.jpg' '*.jpeg' '*.gif' '*.svg' '*.webp' '*.pdf' -x '*/.claude/*' '*/scripts/*' '*/README.md' '*/.skilleval.yaml' '*/.skilleval.yml' '*/CHANGELOG.md' '*/evals/*'In the AWS DevOps Agent web app, navigate to the Skills page.
Click Add skill → Upload skill.
Drag and drop the
support-cases.zipfile (max 6 MB).Select the agent types: Chat tasks and Incident RCA.
Click Upload.
Option C: Upload via the Asset API
Use the AWS DevOps Agent Asset API to programmatically manage skills — useful for CI/CD pipelines or automation workflows. Assign the skill to the CHAT and INCIDENT_RCA agent types. See Managing a skill end-to-end for the full API workflow.
For more details, see Uploading a skill in the AWS DevOps Agent User Guide.
How to Use This Skill
This skill is most suitable for chat and investigation. Below are sample prompts for each use-case
Chat
- "Create a support cases report for all support cases in the last 12 months, including breakdowns by service and severity"
- "Show me all support cases opened in the last 30 days for RDS."
- "What was the resolution for case-123456789010-muen-2024?"
- "Are there any open critical-severity cases in this account?"
- "Summarize the communications on our most recent EC2 support case."
- "Have we filed any support cases related to Lambda throttling this quarter?"
Investigation
- "Investigate the Lambda-Errors alarm"
- "We're seeing 5xx errors on our ALB — can you investigate?"
- "RDS connections are maxing out and queries are timing out. What's going on?"
- "There's a latency spike on our ECS service starting around 3am UTC."
- "Our last deployment triggered elevated error rates across multiple endpoints."
- "The same DynamoDB throttling alarm fired again. Help me figure out why this keeps happening."
Skill manifest
Support Case Review
Use this skill when investigating an incident and you need to review AWS Support cases — either the current case associated with the incident or historical cases that may contain relevant context, similar symptoms, or proven remediation steps.
When to Use This Skill
- An active incident shares symptoms with previously resolved issues.
- You need to check if a similar support case was filed in the past 24 months.
- You want to correlate the current incident with known AWS service events.
- You need to retrieve communications and resolution details from a prior case.
- You want to identify recurring patterns across multiple support cases.
Prerequisites
- The AWS account must have a Business Support+, Enterprise Support, or Unified Operations plan (required for the AWS Support API).
- The agent must have permissions to call
support:DescribeCasesandsupport:DescribeCommunicationsin the target account. - Support case data is available for 24 months after creation. Cases older than 24 months cannot be retrieved via the API.
Step 1: Identify the Current Incident Context
Before searching support cases, gather key details from the current incident:
- Affected AWS services (e.g., EC2, RDS, Lambda, ELB).
- Error messages or error codes observed in logs or alarms.
- Timeframe of the incident (start time, duration).
- Affected resources (instance IDs, ARNs, endpoint names).
- Symptoms (latency spikes, 5xx errors, connection timeouts, throttling).
Use these details as search criteria when filtering support cases.
Step 2: Search for Related Support Cases
Use the AWS Support API to retrieve cases that may be relevant.
Retrieve all recent cases (open and resolved)
aws support describe-cases \
--include-resolved-cases \
--include-communications \
--after-time "<ISO-8601-start>" \
--before-time "<ISO-8601-end>" \
--language "en"
Filter by specific case IDs (if known)
aws support describe-cases \
--case-id-list "case-123456789010-muen-2024" \
--include-communications
Key filtering strategies
| Strategy | How to Apply |
|---|---|
| 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. |
| 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. |
| 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. |
| 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. |
| By subject keywords | Scan the subject field of returned cases for keywords matching the current incident symptoms, because similar symptoms often share underlying causes. |
Step 3: Review Case Communications
The describe-cases response with includeCommunications: true returns the
most recent communications for each case in the recentCommunications field
(up to 5 messages). Since root cause analysis and resolution steps are
typically in the final messages of a resolved case, this is usually sufficient.
If the recentCommunications field includes a nextToken, the case has
additional older messages. Only paginate using describe-communications if the
recent messages do not contain a clear root cause or resolution — for example,
if the last messages are follow-up questions rather than a final answer.
aws support describe-communications \
--case-id "case-123456789010-muen-2024" \
--max-results 10 \
--next-token "<nextToken-from-recentCommunications>"
When reviewing communications, look for:
- Root cause statements — AWS Support engineers often summarize the root cause in their final response.
- Remediation steps — Specific actions taken to resolve the issue (e.g., "increased max_connections", "applied security group rule", "scaled up instance type").
- Configuration recommendations — Best practices or tuning suggestions provided by AWS.
- Escalation notes — If the case was escalated, check for deeper technical analysis from specialized teams.
Step 4: Correlate Findings with Current Incident
After reviewing relevant cases, correlate the findings:
Pattern matching checklist
- Do past cases share the same affected service and resource type?
- Are the error messages or codes identical or similar?
- Did past incidents occur at a similar time of day or day of week (indicating load patterns)?
- Was the root cause a configuration issue that may still be present?
- Was the resolution a temporary workaround that has since expired or been reverted?
- Did AWS identify a service-side issue that may be recurring?
Relevance scoring
Rate each historical case on relevance to the current incident:
| Score | Criteria |
|---|---|
| High | Same service, same error, same resource type, similar timeframe |
| Medium | Same service, different error but related symptoms |
| Low | Different service but similar architectural pattern or failure mode |
Step 5: Summarize Findings
Provide a structured summary including:
- Number of related cases found — How many past cases matched the search criteria.
- Most relevant case(s) — Case ID, subject, status, and creation date of the top matches.
- Historical root causes — What caused similar issues in the past.
- Past resolutions — What remediation steps were applied and whether they were permanent fixes or temporary workarounds.
- Recommendations — Based on historical patterns, suggest investigation paths or remediation steps for the current incident.
- Recurring pattern alert — If the same issue has occurred multiple times, flag it as a recurring problem requiring a permanent fix or architectural change.
Decision Tree: Case Search Strategy
Is there a known case ID associated with the current incident?
├── YES → Retrieve that specific case and its communications (Step 2, filter by case ID)
└── NO → Continue below
Is the affected AWS service known?
├── YES → Search cases in the past 90 days for that service, then expand to 12 months if needed
└── NO → Search all cases in the past 30 days and filter by error keywords
Were relevant historical cases found?
├── YES → Review communications (Step 3), correlate findings (Step 4), summarize (Step 5)
└── NO → Broaden search criteria:
- Expand time window
- Search by related services (e.g., if ELB is affected, also check EC2 and Target Group cases)
- Search by error code or symptom keywords in case subjects
Tips for Effective Case Review
- Start narrow, then broaden: Begin with specific filters (service + time window) and expand only if no relevant cases are found.
- Check resolved cases: The most valuable information often comes from resolved cases where root cause and fix are documented.
- Note case severity patterns: If past cases for the same issue were filed
at
criticalseverity, the current incident may warrant similar urgency. - Cross-reference with deployments: If a past case was caused by a deployment, check if a similar deployment occurred before the current incident.
Files (tools-for-devops-agent)
-
evals
-
benchmark.json 39.5 KB
Loading… -
evals.json 3.7 KB
Loading… -
eval_queries.json 603 B
Loading… -
report.json 1.6 KB
Loading… -
trigger_report.json 2.3 KB
Loading…
-
-
references
-
case-review-patterns.md 4.5 KB
Loading… -
support-api-reference.md 4 KB
Loading…
-
-
.skilleval.yaml 76 B
Loading… -
CHANGELOG.md 232 B
Loading… -
README.md 4.8 KB
# Support Cases Skill This skill enables the AWS DevOps Agent to retrieve and analyze AWS Support cases during incident investigation, root cause analysis, and operational troubleshooting. ## Purpose When an operational incident occurs, historical support cases often contain valuable context — prior root causes, proven remediations, and recurring patterns. This skill searches past AWS Support cases by service, time window, severity, and error keywords to surface relevant history that informs the current investigation. ## Key Capabilities - Retrieve open and resolved AWS Support cases via the Support API - Search and filter cases by service, severity, time range, and keywords - Review case communications for root cause statements and remediation steps - Correlate historical findings with current incident symptoms - Identify recurring patterns that may require permanent fixes ## Prerequisites - AWS account with Business Support+, Enterprise Support, or Unified Operations plan - Agent permissions for `support:DescribeCases` and `support:DescribeCommunications` ## Limitations - Support case data is only available for up to 24 months after creation ## Agent Types This skill is used by the following agent types: - **Chat tasks** — conversational support case lookup and analysis - **Incident RCA** — root cause analysis during active incidents ## Uploading to AWS DevOps Agent To deploy this skill to your Agent Space, you can use any of three ways: **Option A: Import from GitHub (recommended)** If you have a [GitHub connection configured](https://docs.aws.amazon.com/devopsagent/latest/userguide/connecting-to-cicd-pipelines-connecting-github.html) in your Agent Space, you can import this skill directly from the repository. In the DevOps Agent web app, go to Settings → Add Skill → Import from repository, then point to the `skills/support-cases` directory. See [Importing a skill from a repository](https://docs.aws.amazon.com/devopsagent/latest/userguide/about-aws-devops-agent-devops-agent-skills.html#creating-skills) for full instructions. > **Note:** You cannot connect the `aws` GitHub organization directly because the GitHub connection setup requires admin rights on the organization. Instead, connect your personal GitHub account and select any repository from it during the connection setup. Once a GitHub connection is established, you can import skills from any public repository — including this one — even if it wasn't selected during the connection setup. **Option B: Upload as a zip file** 1. Zip the `support-cases/` directory (only including allowed extensions): ```bash cd skills zip -r support-cases.zip support-cases/ -i '*.md' '*.txt' '*.json' '*.yaml' '*.yml' '*.xml' '*.csv' '*.tsv' '*.html' '*.htm' '*.png' '*.jpg' '*.jpeg' '*.gif' '*.svg' '*.webp' '*.pdf' -x '*/.claude/*' '*/scripts/*' '*/README.md' '*/.skilleval.yaml' '*/.skilleval.yml' '*/CHANGELOG.md' '*/evals/*' ``` 2. In the AWS DevOps Agent web app, navigate to the **Skills** page. 3. Click **Add skill** → **Upload skill**. 4. Drag and drop the `support-cases.zip` file (max 6 MB). 5. Select the agent types: **Chat tasks** and **Incident RCA**. 6. Click **Upload**. **Option C: Upload via the Asset API** Use the AWS DevOps Agent Asset API to programmatically manage skills — useful for CI/CD pipelines or automation workflows. Assign the skill to the `CHAT` and `INCIDENT_RCA` agent types. See [Managing a skill end-to-end](https://docs.aws.amazon.com/devopsagent/latest/userguide/about-aws-devops-agent-managing-assets.html#managing-a-skill-end-to-end) for the full API workflow. For more details, see [Uploading a skill](https://docs.aws.amazon.com/devopsagent/latest/userguide/about-aws-devops-agent-devops-agent-skills.html#creating-skills) in the AWS DevOps Agent User Guide. ## How to Use This Skill This skill is most suitable for chat and investigation. Below are sample prompts for each use-case ### Chat - "Create a support cases report for all support cases in the last 12 months, including breakdowns by service and severity" - "Show me all support cases opened in the last 30 days for RDS." - "What was the resolution for case-123456789010-muen-2024?" - "Are there any open critical-severity cases in this account?" - "Summarize the communications on our most recent EC2 support case." - "Have we filed any support cases related to Lambda throttling this quarter?" ### Investigation - "Investigate the Lambda-Errors alarm" - "We're seeing 5xx errors on our ALB — can you investigate?" - "RDS connections are maxing out and queries are timing out. What's going on?" - "There's a latency spike on our ECS service starting around 3am UTC." - "Our last deployment triggered elevated error rates across multiple endpoints." - "The same DynamoDB throttling alarm fired again. Help me figure out why this keeps happening." -
SKILL.md 8.6 KB
--- name: support-cases description: 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. metadata: author: udid-aws version: "1.0.1" aws-devops-agent-skills.agent-types: "CHAT, INCIDENT_RCA" aws-devops-agent-skills.aws-services: "AWS Support" aws-devops-agent-skills.technical-domains: "Operations" --- # Support Case Review Use this skill when investigating an incident and you need to review AWS Support cases — either the current case associated with the incident or historical cases that may contain relevant context, similar symptoms, or proven remediation steps. ## When to Use This Skill - An active incident shares symptoms with previously resolved issues. - You need to check if a similar support case was filed in the past 24 months. - You want to correlate the current incident with known AWS service events. - You need to retrieve communications and resolution details from a prior case. - You want to identify recurring patterns across multiple support cases. ## Prerequisites - The AWS account must have a Business Support+, Enterprise Support, or Unified Operations plan (required for the AWS Support API). - The agent must have permissions to call `support:DescribeCases` and `support:DescribeCommunications` in the target account. - Support case data is available for 24 months after creation. Cases older than 24 months cannot be retrieved via the API. --- ## Step 1: Identify the Current Incident Context Before searching support cases, gather key details from the current incident: 1. **Affected AWS services** (e.g., EC2, RDS, Lambda, ELB). 2. **Error messages or error codes** observed in logs or alarms. 3. **Timeframe** of the incident (start time, duration). 4. **Affected resources** (instance IDs, ARNs, endpoint names). 5. **Symptoms** (latency spikes, 5xx errors, connection timeouts, throttling). Use these details as search criteria when filtering support cases. --- ## Step 2: Search for Related Support Cases Use the AWS Support API to retrieve cases that may be relevant. ### Retrieve all recent cases (open and resolved) ``` aws support describe-cases \ --include-resolved-cases \ --include-communications \ --after-time "<ISO-8601-start>" \ --before-time "<ISO-8601-end>" \ --language "en" ``` ### Filter by specific case IDs (if known) ``` aws support describe-cases \ --case-id-list "case-123456789010-muen-2024" \ --include-communications ``` ### Key filtering strategies | Strategy | How to Apply | |----------|-------------| | 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. | | 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. | | 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. | | 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. | | By subject keywords | Scan the `subject` field of returned cases for keywords matching the current incident symptoms, because similar symptoms often share underlying causes. | --- ## Step 3: Review Case Communications The `describe-cases` response with `includeCommunications: true` returns the most recent communications for each case in the `recentCommunications` field (up to 5 messages). Since root cause analysis and resolution steps are typically in the final messages of a resolved case, this is usually sufficient. If the `recentCommunications` field includes a `nextToken`, the case has additional older messages. Only paginate using `describe-communications` if the recent messages do not contain a clear root cause or resolution — for example, if the last messages are follow-up questions rather than a final answer. ``` aws support describe-communications \ --case-id "case-123456789010-muen-2024" \ --max-results 10 \ --next-token "<nextToken-from-recentCommunications>" ``` When reviewing communications, look for: 1. **Root cause statements** — AWS Support engineers often summarize the root cause in their final response. 2. **Remediation steps** — Specific actions taken to resolve the issue (e.g., "increased max_connections", "applied security group rule", "scaled up instance type"). 3. **Configuration recommendations** — Best practices or tuning suggestions provided by AWS. 4. **Escalation notes** — If the case was escalated, check for deeper technical analysis from specialized teams. --- ## Step 4: Correlate Findings with Current Incident After reviewing relevant cases, correlate the findings: ### Pattern matching checklist - [ ] Do past cases share the same affected service and resource type? - [ ] Are the error messages or codes identical or similar? - [ ] Did past incidents occur at a similar time of day or day of week (indicating load patterns)? - [ ] Was the root cause a configuration issue that may still be present? - [ ] Was the resolution a temporary workaround that has since expired or been reverted? - [ ] Did AWS identify a service-side issue that may be recurring? ### Relevance scoring Rate each historical case on relevance to the current incident: | Score | Criteria | |-------|----------| | High | Same service, same error, same resource type, similar timeframe | | Medium | Same service, different error but related symptoms | | Low | Different service but similar architectural pattern or failure mode | --- ## Step 5: Summarize Findings Provide a structured summary including: 1. **Number of related cases found** — How many past cases matched the search criteria. 2. **Most relevant case(s)** — Case ID, subject, status, and creation date of the top matches. 3. **Historical root causes** — What caused similar issues in the past. 4. **Past resolutions** — What remediation steps were applied and whether they were permanent fixes or temporary workarounds. 5. **Recommendations** — Based on historical patterns, suggest investigation paths or remediation steps for the current incident. 6. **Recurring pattern alert** — If the same issue has occurred multiple times, flag it as a recurring problem requiring a permanent fix or architectural change. --- ## Decision Tree: Case Search Strategy ``` Is there a known case ID associated with the current incident? ├── YES → Retrieve that specific case and its communications (Step 2, filter by case ID) └── NO → Continue below Is the affected AWS service known? ├── YES → Search cases in the past 90 days for that service, then expand to 12 months if needed └── NO → Search all cases in the past 30 days and filter by error keywords Were relevant historical cases found? ├── YES → Review communications (Step 3), correlate findings (Step 4), summarize (Step 5) └── NO → Broaden search criteria: - Expand time window - Search by related services (e.g., if ELB is affected, also check EC2 and Target Group cases) - Search by error code or symptom keywords in case subjects ``` --- ## Tips for Effective Case Review - **Start narrow, then broaden**: Begin with specific filters (service + time window) and expand only if no relevant cases are found. - **Check resolved cases**: The most valuable information often comes from resolved cases where root cause and fix are documented. - **Note case severity patterns**: If past cases for the same issue were filed at `critical` severity, the current incident may warrant similar urgency. - **Cross-reference with deployments**: If a past case was caused by a deployment, check if a similar deployment occurred before the current incident.
Comments (0)
Sign in to join the conversation.
Reviews (0)
No reviews yet.
No comments yet.