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.
1418d agoReviewMountCreate a free account to mount
Comprehensive Amazon Data Firehose (formerly Kinesis Data Firehose) review aligned with the AWS Well-Architected Framework and Firehose best practices. Use this skill when a user asks to review, audit, or assess Amazon Data Firehose delivery streams for best-practices compliance, security posture, reliability, delivery health, performance, cost optimization, service quotas, operational excellence, or sustainability. Triggers on requests like "Firehose review", "Kinesis Firehose best practices audit", "review my delivery streams", "Firehose health check", "why is my Firehose lagging", "Firehose delivery failures", "Firehose cost optimization review", or "ORR for Firehose".
1418d agoReviewMountCreate a free account to mount
Use the Grafana Cloud connector to investigate incidents with the customer's Grafana Cloud telemetry. Covers choosing tools, when to use Grafana Assistant, the Read, Query and Write access levels, confirming every write with the operator, keeping results small, and querying Prometheus, Loki and Tempo data. Use when an investigation needs metrics, logs, traces or profiles from Grafana Cloud, when checking Grafana dashboards, alert rules, incidents or on-call schedules, or when the customer asks a question about their Grafana Cloud stack.
1418d agoReviewMountCreate a free account to mount
Load when the operator asks for a Honeycomb board or dashboard: a board for a service, a feature, or an incident, a golden signals dashboard, or a board to visualize service health. Designs the board from SLOs and queries, shows the full plan to the operator, and calls create_board only after the operator approves it.
1418d agoReviewMountCreate a free account to mount
Load before querying a Honeycomb OpenTelemetry metrics dataset (dataset_type=metrics): gauges, counters, histograms and sums, including infrastructure metrics such as CPU, memory, disk I/O and network. Metrics follow different rules from trace datasets: bare COUNT, RATE_SUM, RATE_AVG, RATE_MAX and CONCURRENCY are rejected, temporal aggregation is automatic, and each metric has its own attributes. Not for event datasets that only have metrics in their name.
1418d agoReviewMountCreate a free account to mount
Load when the operator asks a conceptual question about observability or Honeycomb: what observability is, why wide events, what high cardinality or dimensionality means, events vs metrics vs logs, observability vs monitoring, or the core analysis loop. Grounds recommendations in first principles. Not for running queries or investigating a live issue.
1418d agoReviewMountCreate a free account to mount
Load when an investigation needs Honeycomb telemetry to find a root cause: a latency spike, an error surge, a deployment regression, a failing dependency or an SLO burning budget. Gives the order of Honeycomb MCP tool calls (orient, broad query, BubbleUp, trace drill-down, verification) and how to carry each result into the next step.
1418d agoReviewMountCreate a free account to mount
Load before building or reading a Honeycomb run_query on a trace, log or event dataset. Covers which operation to pick (percentiles and HEATMAP over AVG), relational fields (root., parent., any., none.), calculated fields, query math, and how to read results such as P99/P50 ratios, heatmap bands and TOTAL/OTHER rows. For datasets with dataset_type=metrics, use honeycomb-metrics-queries instead.
1418d agoReviewMountCreate a free account to mount
Load before calling Honeycomb get_slos or get_triggers, or when an investigation must judge SLO compliance, error budget burn or trigger status. Explains what the numbers mean, how to spot a misconfigured SLI, when a burn rate justifies paging or freezing deploys, and how to design burn alert thresholds.
1418d agoReviewMountCreate a free account to mount
Load when the operator asks to verify a recent test or deployment in Honeycomb, find the most recent trace, or show the trace a test produced. Finds the traces created since the test started and summarizes the most recent one.
1418d agoReviewMountCreate a free account to mount
Cost guardrail for AWS DevOps Agent that covers ALL AWS services and native agent tools. Before the agent makes any paid API call, this skill estimates cost, enforces budgets per investigation, detects expensive operations across all services (Athena queries, S3 scans, DynamoDB scans, SageMaker inference, PromQL, etc.), enforces time window requirements, monitors cumulative call volume, and cancels if thresholds are exceeded. This skill applies to ALL investigations regardless of which services are involved.
1418d agoReviewMountCreate a free account to mount
Create and manage agent graphs — directed graphs of configs connected by edges with handoff logic. Use when building multi-agent workflows where configs route to each other.
1418d agoReviewMountCreate a free account to mount
Investigates a firing or recently fired observability alert: finds the firing and replays the value it evaluated, decides whether the alert is chronic noise or a new problem, reuses any automatic investigation, then finds the cause (what changed, which host, version or route is over-represented) and returns a structured diagnosis with cause, scope and next steps.
1418d agoReviewMountCreate a free account to mount
Configure AgentControl config targeting to control which variation each context receives. Set the default rule or a percentage split, add attribute and segment rules, target individual contexts, and roll a config back to an earlier variation.
1418d agoReviewMountCreate a free account to mount
Update, retire, and delete LaunchDarkly configs and their variations. Use when you need to modify config properties, change model parameters, update instructions or messages, take unused configs out of service, or permanently remove them.
1418d agoReviewMountCreate a free account to mount
Experiment with configs by creating and managing variations. Helps you test different models, prompts, and parameters to find what works best through systematic experimentation.
1418d agoReviewMountCreate a free account to mount
Creates observability dashboards and graphs from logs, traces, errors, sessions, metrics, and events data by previewing charts inline and saving them to a dashboard.
1418d agoReviewMountCreate a free account to mount
Create, track, retrieve, update, and delete custom business metrics for configs. Covers full lifecycle: define metrics with the LaunchDarkly MCP server, emit events via SDK, and query results.
1418d agoReviewMountCreate a free account to mount
A folder with a SKILL.md file: a name, a description of when to use it, and instructions. Claude loads a skill only when the task matches its description.
How do I use one I find here?
Copy the folder into your project's .claude/skills/ directory, or into your own skills folder to use it everywhere.
What do the warnings mean?
We read each file for commands that read secrets, delete things or pipe downloads into a shell, and say so before you copy it. No warning is not a promise that a file is safe.
Which skills worked for people?
Open a skill to see its discussion. Reports from people and their agents are coming.
AWSSkill