AWS Cloudwatch Investigation
Use when investigating AWS incidents with CloudWatch Logs, Metrics, Alarms, CloudTrail, and Health evidence, correlating deployments, narrowing blast radius, reconstructing timelines, or testing metric anomalies.
Install
npx skills add sandbaseai/workbuddy-skill --skill aws-cloudwatch-investigationgit clone --depth 1 https://github.com/sandbaseai/workbuddy-skill.git /tmp/workbuddy-skill
mkdir -p ~/.claude/skills
cp -r /tmp/workbuddy-skill/skills/aws-cloudwatch-investigation ~/.claude/skills/aws-cloudwatch-investigationPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# AWS CloudWatch Investigation Investigate AWS incidents from bounded, auditable evidence. This skill helps turn a symptom into a time-bounded evidence set across CloudWatch Logs, Metrics, Alarms, CloudTrail, and AWS Health, then records what is known, uncertain, and safe to check next. ## Purpose and boundary - Confirm account, region, environment, service, and time zone before querying. - Use read-only access only: query logs and metrics, inspect alarms and history, read CloudTrail and Health events, and inspect deployment metadata. - Never change dashboards, alarms, log retention, metric filters, resources, deployments, or incident state through this skill. - Treat temporal correlation as a lead, not proof of causality; seek independent evidence and counterevidence. ## Investigation contract Before running a query, record: 1. The reported symptom, impact hypothesis, and first-known-good/first-known-bad times. 2. Account ID, region, environment, service/resource identifiers, and the source of each identifier. 3. Query purpose, time range, log groups or namespaces, filters, limit, and expected result shape. 4. Redaction requirements and evidence retention destination. If scope or timestamps are missing, ask for them or state the narrow assumption. Do not silently query every account or region. ## First signal and alarm correlation
Details
- Skill name
aws-cloudwatch-investigation- Repository
- sandbaseai/workbuddy-skill
- Path
skills/aws-cloudwatch-investigation/SKILL.md- License
- MIT
- Repo updated
- 8 September 2026
FAQ
What does the AWS Cloudwatch Investigation skill do?
Use when investigating AWS incidents with CloudWatch Logs, Metrics, Alarms, CloudTrail, and Health evidence, correlating deployments, narrowing blast radius, reconstructing timelines, or testing metric anomalies.
How do I install the AWS Cloudwatch Investigation skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add sandbaseai/workbuddy-skill --skill aws-cloudwatch-investigation. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is AWS Cloudwatch Investigation popular?
It lives in sandbaseai/workbuddy-skill, which has 9 GitHub stars and 3 forks.
Related skills
Access Control Security Best Practices
9sandbaseai/workbuddy-skill
Design, review, implement, and verify least-privilege access controls across users, services, tenants, resources, and administrative workflows.
Accessibility Review
9sandbaseai/workbuddy-skill
Use when reviewing a web interface or interaction for semantic, keyboard, focus, screen-reader, ARIA, and contrast accessibility risks.
Acquire Codebase Knowledge
9sandbaseai/workbuddy-skill
Use when the user asks to map, document, or onboard into an existing codebase and needs evidence-backed architecture, structure, conventions, integrations, testing, and concerns documentation.
AWS Cost Optimize
9sandbaseai/workbuddy-skill
Use when analyzing an authorized AWS workload's IaC, usage metrics, and costs to produce evidence-backed optimization recommendations.
Spec to Symphony
5adelrioj/claude-skills
Use when a groomed Linear ticket already carries its design spec and the build must be handed to a Symphony autonomous pipeline — puts the spec on the remote under the filename that deployment actually reads, then arms the existing ticket so the poller dispatches it. The ticket must already exist; this skill never creates one. Triggers on: hand off to symphony, hand the build to symphony, arm the pipeline, arm the ticket, spec to symphony, spec-to-symphony.
AWS Resilience Assessment
9sandbaseai/workbuddy-skill
Use when assessing an AWS workload's failure modes, dependencies, availability, recoverability, RTO/RPO, disaster recovery, observability, or resilience improvement roadmap from architecture evidence, IaC, or authorized read-only inventory.
Browse the most popular Claude skills, all devops & cloud skills, or write your own with the skills generator.