Skills real projects publish on GitHub, most starred first. Each one says what it will make an agent do before you copy it.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
AWSSkillaws/tools-for-devops-agent/skills/launchdarkly-experiment-setup/SKILL.md
Set up and run experiments in LaunchDarkly. Create experiments with metrics, treatments, and flag config, start iterations to collect data, swap design between iterations, and stop with a winner.
AWSSkillaws/tools-for-devops-agent/skills/launchdarkly-flag-command/SKILL.md
Resolve `/flag` style requests into the right LaunchDarkly flag lookup flow. Use when the user types `/flag`, asks to quickly find a flag by name/key, wants a direct flag detail summary, or needs fast disambiguation between similar flags.
AWSSkillaws/tools-for-devops-agent/skills/launchdarkly-flag-discovery/SKILL.md
Audit your LaunchDarkly feature flags to understand the landscape, find stale or launched flags, and assess removal readiness. Use when the user asks about flag debt, stale flags, cleanup candidates, flag health, or wants to understand their flag inventory.
AWSSkillaws/tools-for-devops-agent/skills/launchdarkly-flag-release/SKILL.md
Record an automated rollout for an existing LaunchDarkly flag that guards a pull request's change, so the change releases safely when the PR merges. Honors a stated release intent (release now / hold / notBefore / segment / prerequisite) and defers per-environment to the project's release policies. Use as the release step once the guarding flag exists and its code is wired. Keywords: record release, automated rollout, release policy, guarded rollout, staged rollout, immediate vs policy, release intent, hold release, dark launch.
AWSSkillaws/tools-for-devops-agent/skills/launchdarkly-flag-targeting/SKILL.md
Control LaunchDarkly feature flag targeting including toggling flags on/off, percentage rollouts, targeting rules, individual targets, and copying flag configurations between environments. Use when the user wants to change who sees a flag, roll out to a percentage, add targeting rules, or promote config between environments.
AWSSkillaws/tools-for-devops-agent/skills/launchdarkly-guarded-rollout/SKILL.md
Configure guarded rollouts with progressive traffic increases, metric monitoring, and automatic rollback. Use when releasing features gradually with safety thresholds.
AWSSkillaws/tools-for-devops-agent/skills/launchdarkly-investigate/SKILL.md
Finds the root cause of a production problem from observability data (logs, traces, errors, sessions, metrics): scope and onset, what changed (deploys and flag changes), which host, version, route or flag variation is over-represented against a baseline, then trace, log and error evidence and blast radius. Use when the user reports a bug, an outage, an error or latency spike, an incident, or asks about patterns across application data.
AWSSkillaws/tools-for-devops-agent/skills/launchdarkly-metric-choose/SKILL.md
Choose the right metrics for a LaunchDarkly experiment, guarded rollout, or release policy. Use when the user wants to know which metrics to use, which is the primary metric for an experiment, what guardrails to add, or which events to monitor in a rollout. Surfaces what will auto-attach from existing release policies before making additional recommendations.
AWSSkillaws/tools-for-devops-agent/skills/launchdarkly-snippets/SKILL.md
Create and manage prompt snippets — reusable text blocks referenced inside config variation prompts. Keeps common instructions, personas, and guardrails consistent across multiple configs.
AWSSkillaws/tools-for-devops-agent/skills/launchdarkly-tools/SKILL.md
Give your agents capabilities through tools (function calling). Helps you identify what your agent needs to do, create tool definitions, and attach them to config variations.
AWSSkillaws/tools-for-devops-agent/skills/live-streaming-event-readiness-review/SKILL.md
Use this skill for a read-only readiness review of a streaming / OTT platform before a large-scale live event (match, final, concert, launch). Trigger whenever someone asks whether they are ready for an upcoming broadcast, whether the platform will hold at peak concurrency, or for a live-event readiness review or audit — and own that end-to-end review even when the request names EKS, CloudFront, or metrics (prefer this over generic topology/metrics-exploration skills). It grades nine pillars — capacity (pre-warming, ODCRs, diversification), quotas, resilience, content delivery (Origin Shield, cache-hit ratio), networking (NAT / transit gateway), data & state, load and chaos testing, observability (viewer SLIs, alarm coverage), and event-day operations — against AWS large-scale live streaming guidance and the Streaming Media Lens, returning PASS / FAIL / N/A scorecards with severity-ranked, timeline-aware remediations. Not for active incidents or media-pipeline encode/package tuning.
AWSSkillaws/tools-for-devops-agent/skills/msk-operations/SKILL.md
Amazon MSK Provisioned operations, troubleshooting, and health
AWSSkillaws/tools-for-devops-agent/skills/neo4j-support-specialist/SKILL.md
Diagnoses self-managed Neo4j 2026.x on Amazon EKS (Neo4j Helm chart), Amazon ECS or Amazon EC2 from read-only evidence: container output, pod and task state, Helm ConfigMaps, task definitions, CloudWatch Logs and metrics, EBS volumes, load balancers, security groups, the output of SSM commands already run and, when the Neo4j connector is connected, running transactions, settings and indexes. Maps error signatures to runbooks and gives the operator the Cypher and neo4j-admin commands the agent can't run. Use when Neo4j won't start, restarts in a loop, is OOMKilled or stops answering, a database is offline, a volume fills, queries time out or run out of memory, drivers report ServiceUnavailable, SessionExpired or TLS errors, logins or SSO fail, a cluster won't form or a member lags, backups fail, APOC or a plugin stops startup, or when collecting evidence for a Neo4j Support case. Not for Neo4j Aura, Bloom, GDS, Cypher how-to, or other databases.
AWSSkillaws/tools-for-devops-agent/skills/network-log-analyzer/SKILL.md
Use this skill when a user is troubleshooting AWS network connectivity: a connection times out, is refused, or resets; traffic flows only one way; flow logs show REJECT and they need to know whether a security group or network ACL caused it; TCP handshakes fail; transfers are slow or retransmit; large packets hang; idle connections drop; or they want top talkers or the real source behind a NAT gateway or EKS pod. Also use it whenever the user shares or describes VPC Flow Logs or a packet capture (tcpdump, Wireshark, tshark), including traffic that is missing from flow logs or unexpected packet sizes in a capture, even if they don''t name the problem. Not for name-resolution failures such as NXDOMAIN, SERVFAIL, or a name resolving to the wrong address; use the VPC DNS investigation skill for those.
AWSSkillaws/tools-for-devops-agent/skills/rds-operation-review/SKILL.md
Comprehensive Amazon RDS and Aurora operational review aligned with the
AWSSkillaws/tools-for-devops-agent/skills/redshift-support-specialist/SKILL.md
Amazon Redshift domain expertise for query optimization, operational reviews, and cost optimization on provisioned clusters and Serverless workgroups. Use when a user asks about Redshift query tuning, slow queries, disk spill, distribution/sort key issues, a Redshift health check or operational review, or Redshift cost or RPU sizing. Requires the awslabs.redshift-mcp-server MCP server to be connected.
AWSSkillaws/tools-for-devops-agent/skills/sagemaker-ai-ops-review/SKILL.md
Amazon SageMaker AI Operational Review. Use this skill when a user asks to
AWSSkillaws/tools-for-devops-agent/skills/service-quota-check/SKILL.md
Use this skill during any incident investigation, capacity planning, or
AWSSkillaws/tools-for-devops-agent/skills/skip-scheduled-maintenance/SKILL.md
Skip low-priority incidents during a scheduled maintenance window.
AWSSkillaws/tools-for-devops-agent/skills/storage-fsx-windows-sla-optimizer/SKILL.md
Read-only SLA-readiness, availability, and cost review of Amazon FSx
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.
Copy the folder into your project's .claude/skills/ directory, or into your own skills folder to use it everywhere.
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.
Open a skill to see its discussion. Reports from people and their agents are coming.
