Menu
SkillsMP has collected 10 skills from aws-samples/sample-aws-ops-skills-for-agents. Open a skill to review its source and details.
Showing 10 of 10 collected skills.
Iterative fact-checking loop for any document (PPT, Word, PDF, Markdown, etc.) against its original source. Spawns independent subagents in fresh contexts to eliminate confirmation bias. Each round checks all claims, the main agent fixes issues found, then a…
Use at the start of a non-trivial agentic coding task, or when a long-horizon task keeps coming back wrong. Surfaces the gaps between what you told the agent (the "map") and where the work actually happens (the "territory") — your unknowns — before, during,…
Draw an animated, light-theme, LEFT-TO-RIGHT AWS architecture diagram as one self-contained SVG — official AWS service icons, marching-ants connectors, and traveling request dots that show data moving through the system. Use this whenever the user asks for an…
Use when performing routine environment checks, validating service health before or after deployments, checking SLO compliance, or generating a health status report. Also use when the user asks "环境健康么", "服务状态怎样", "部署前检查", or "SLO 达标了么". Queries CloudWatch…
Source text: Chinese
Use when searching CloudWatch logs for errors, investigating application issues, correlating events across services, or when a user reports a problem and you need to find relevant log entries. Also use when the user asks "what errors happened recently",…
Source text: Chinese
Reference example agent-friendly CLI for managing todos. Demonstrates all 10 agent-friendly principles end-to-end. Use this as a structural template for your own CLI. Common workflows: list pending todos, create new todos, mark complete and archive (single…
Use when the user has a set of internal APIs / REST endpoints / SDK and wants to expose them as an agent-friendly CLI. Also use when retrofitting an existing CLI for AI agent use, or when auditing how agent-ready an existing CLI is. Prevents the common 1:1…
Source text: Mixed languages
Universal AWS troubleshooting framework. Activate when: any AWS resource is unhealthy, unreachable, or degraded; status checks fail; deployments fail; connectivity issues; performance degradation; unexpected errors or state transitions; the user says…
Use when investigating what AWS services are running, checking fleet health by service tag, responding to "what's in my account" questions, onboarding to a new AWS account, or preparing an environment overview. Uses tag-based Fleet Intelligence: discovers tag…
Source text: Chinese
Use when an alarm fires, a user reports an outage or degradation, or when you need to quickly assess severity, identify affected services, and determine immediate next steps. Also use when the user says "有告警", "服务挂了", "出问题了", "incident", or "on-call". Focuses…
Source text: Chinese