agentleFS

Find the best CLAUDE.md, AGENTS.md and Claude skills

One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.

Worked for most · soon
AWSSkill

aws-eks-operations-review

aws/tools-for-devops-agent/skills/aws-eks-operations-review/SKILL.md

Use this skill when someone wants an Amazon EKS cluster graded against best practices. Use it when they ask to review, assess, audit, or grade a cluster; ask for an operations review, security review, operational-readiness or pre-upgrade check, inventory, or CWR; ask whether a cluster is production-ready or safe to upgrade; ask what risks, gaps, or misconfigurations it carries; or describe Kubernetes workloads on AWS without naming EKS. It grades nine pillars — Operations, Resilience, Security, Scalability, Performance, Observability, Networking, Cost, Control Plane — plus AWS API and Cluster Insights, and returns evidence-backed PASS/FAIL/N/A scorecards with prioritized remediations. Do not use it for a quick ungraded health snapshot or an active incident investigation.

1418d agoReviewMountCreate a free account to mount
AWSSkill

aws-fsxn-operations-review

aws/tools-for-devops-agent/skills/aws-fsxn-operations-review/SKILL.md

Amazon FSx for NetApp ONTAP Operational Review. Use when a user asks to review, audit, assess, or health-check FSx for NetApp ONTAP (FSxN / FSx ONTAP) — a file system, SVM, volume, or the whole footprint — for best-practices posture across Backup, Observability, Operations, Performance, and Security, in production or pre-production. Activate even on a brief request with no file-system IDs: the skill self-discovers all ONTAP file systems in the account/region and runs all pillars by default, so a bare account+region (or no scope) is enough — do not wait for named resources. Strictly read-only and fully automated via public AWS APIs (fsx, cloudwatch, backup, ec2); no manual steps, no ONTAP CLI. Triggers: "FSxN operational review", "FSx ONTAP review", "review my FSxN", "audit my FSx ONTAP", "check my FSxN posture", "FSx ONTAP best-practices audit", "FSxN health check", "assess my ONTAP file system".

1418d agoReviewMountCreate a free account to mount
AWSSkill

aws-health-events

aws/tools-for-devops-agent/skills/aws-health-events/SKILL.md

ALWAYS use this skill in the beginning of any incident investigation, root cause

1418d agoReviewMountCreate a free account to mount
AWSSkill

aws-natgw-traffic-analysis

aws/tools-for-devops-agent/skills/aws-natgw-traffic-analysis/SKILL.md

Use this skill when a user wants to understand what traffic is going through an AWS NAT Gateway, why it takes that path, or how to reduce NAT Gateway cost - for example "why is my NAT Gateway bill so high", "what is going through my NAT Gateway", traffic leaving through NAT instead of over peering or a VPC endpoint, EKS, ECS, or other private-subnet workloads sending heavy AWS API, container image, or S3 traffic through NAT, S3 traffic still hitting NAT even though a Gateway Endpoint exists, whether Gateway or Interface Endpoints are actually being used, customer-owned or BYOIP public IPs appearing as NAT destinations, estimating how much fixing NAT traffic would save, which flow logs to use for NAT analysis, or before recommending a Cross-Region S3 Interface Endpoint. Also use it when the user shares or points to NAT Gateway VPC Flow Logs, or asks which resource or service is behind a NAT Gateway destination IP. Read-only and advisory: reports traffic in GB and percent and never changes resources.

1418d agoReviewMountCreate a free account to mount
AWSSkill

aws-routing

aws/tools-for-devops-agent/skills/aws-routing/SKILL.md

Use this skill when the user wants to know which path AWS will pick for their traffic, why traffic took an unexpected route, or how to make AWS prefer a path. Covers Cloud WAN CNE route evaluation, Direct Connect Gateway local vs remote region preference, Transit Gateway route tables, ECMP and peering, VPC longest-prefix-match, BGP traffic engineering (LP communities 7224:7100/7200/7300, AS-path prepending, MED), DX + VPN redundancy and failover, and asymmetric routing. Use it even when the user only describes a symptom, such as "traffic is leaving the region", "not using my local Direct Connect", "routing to the wrong VIF/location", or "path is asymmetric". Read-only: analysis, recommendations, and describe/get/list validation commands grounded in public AWS docs.

1418d agoReviewMountCreate a free account to mount
AWSSkill

aws-vpc-dns-investigation

aws/tools-for-devops-agent/skills/aws-vpc-dns-investigation/SKILL.md

Use this skill when a name is not resolving as expected inside a VPC, or before applying a DNS control-plane change. Activate on symptoms such as NXDOMAIN or SERVFAIL from an EC2 instance, a hostname resolving to a public address when a private endpoint was expected, an AWS service endpoint that stopped resolving after a VPC endpoint or Route 53 change, an application reaching the wrong IP, resolution that works from one instance but not another, IPv6 or dualstack resolution differences, a suspected on-premises forwarding or hybrid DNS problem, or a request to check whether enabling private DNS, adding a Resolver rule, associating a private hosted zone, attaching DNS Firewall, or associating a Route 53 Profile would break anything. It drives the aws-vpc-dns-diagnostics MCP server to observe live resolution from inside the subnet and to simulate a proposed change before it is applied.

1418d agoReviewMountCreate a free account to mount
AWSSkill

bedrock-adoption-readiness

aws/tools-for-devops-agent/skills/bedrock-adoption-readiness/SKILL.md

Amazon Bedrock production readiness assessment covering IAM governance, data retention (ZDR), quota and capacity headroom, and operational observability across Standard Bedrock and Mantle surfaces. Use this skill when a user asks to review Bedrock readiness, assess Bedrock security posture, evaluate quota headroom, check ZDR configuration, validate Bedrock operational setup, or prepare for Bedrock production deployment. Triggers on "Bedrock readiness review", "am I ready for Bedrock production", "Bedrock security assessment", "check my Bedrock quotas", "Bedrock adoption audit", "Bedrock operational review", or "assess my Bedrock environment".

1418d agoReviewMountCreate a free account to mount
AWSSkill

bedrock-operation-review

aws/tools-for-devops-agent/skills/bedrock-operation-review/SKILL.md

Comprehensive Amazon Bedrock review aligned with the AWS

1418d agoReviewMountCreate a free account to mount
AWSSkill

bluebox-observability

aws/tools-for-devops-agent/skills/bluebox-observability/SKILL.md

Load when an answer depends on how services reporting to Bluebox (by Dynatrace) behave in production: active problems, errors, latency, traffic, failing endpoints, dependencies, logs, traces, deploys or past Bluebox investigations. Use it to triage or investigate incidents, test root-cause hypotheses, check health before a directed action, mitigation or release, verify recovery after a change and answer operational questions. Covers the Bluebox tools, scoping, verdicts, cost and answers as data.

1418d agoReviewMountCreate a free account to mount
AWSSkill

bronto-dataset-discovery

aws/tools-for-devops-agent/skills/bronto-dataset-discovery/SKILL.md

Load this skill when investigating an incident or answering a question that needs logs from Bronto and the dataset that holds them is not already known - for example a service, host, function or resource that is failing, slow or throwing errors. It finds which Bronto datasets hold that service's logs, which key identifies the service, and whether there is data in the incident window, before any log search runs.

1418d agoReviewMountCreate a free account to mount
AWSSkill

bronto-error-investigation

aws/tools-for-devops-agent/skills/bronto-error-investigation/SKILL.md

Load this skill when an investigation needs to explain errors in logs held in Bronto - an error surge, a failing service, a specific error event or a Bronto monitor alert. It isolates the error, finds when it started, breaks it down by version, host, customer, endpoint, client and region to find what it is concentrated on, verifies the suspect against a control query, and reports the scope, a hypothesis and next steps with links to the supporting searches.

1418d agoReviewMountCreate a free account to mount
AWSSkill

bronto-log-search

aws/tools-for-devops-agent/skills/bronto-log-search/SKILL.md

Load this skill before writing or running a Bronto log search - counting, grouping, trending or fetching log events with the Bronto MCP tools. It explains which tool answers which question, how to write a search_filter in Bronto's search syntax, and how to read the results without misreporting zero matches.

1418d agoReviewMountCreate a free account to mount
AWSSkill

clickstack-investigation

aws/tools-for-devops-agent/skills/clickstack-investigation/SKILL.md

Investigate incidents with the customer's logs, traces and metrics in ClickHouse Observability, the managed ClickStack service in ClickHouse Cloud, through the ClickStack MCP server. Covers finding data sources, checking service health, explaining error spikes, latency regressions and post-deploy changes, drilling into traces, querying OpenTelemetry metrics, and confirming every write with the operator. Use when an investigation or a chat question needs telemetry stored in ClickHouse Observability, ClickStack or ClickHouse, when the customer asks to search their ClickHouse Observability logs or traces, or when checking its alerts and dashboards.

1418d agoReviewMountCreate a free account to mount
AWSSkill

cloudtrail-cost-optimization

aws/tools-for-devops-agent/skills/cloudtrail-cost-optimization/SKILL.md

Identify and quantify AWS CloudTrail cost optimization opportunities.

1418d agoReviewMountCreate a free account to mount
AWSSkill

config-cost-optimization

aws/tools-for-devops-agent/skills/config-cost-optimization/SKILL.md

Identify and quantify AWS Config cost optimization opportunities.

1418d agoReviewMountCreate a free account to mount
AWSSkill

coralogix-ai-center

aws/tools-for-devops-agent/skills/coralogix-ai-center/SKILL.md

Coralogix AI Center — observe, evaluate, and guard GenAI/LLM applications and agents. Use for questions or actions about the user's AI/GenAI applications or agents — their behavior, prompts/responses, chats, quality, hallucinations, guardrails, cost/tokens, evaluations/policies, model pricing or comparing or tracking agents over time. Combines GenAI span queries (via `query_dataprime`) with the `ai_center_*` / `manage_ai_*` configuration tools. Only load this skill when you have an indication that GenAI is related.

1418d agoReviewMountCreate a free account to mount
AWSSkill

coralogix-alerts

aws/tools-for-devops-agent/skills/coralogix-alerts/SKILL.md

Alert and case terminology, alert definitions, alert events, cases, IDs, alert types, and skill routing. Load whenever working with alerts or cases to understand shared terminology.

1418d agoReviewMountCreate a free account to mount
AWSSkill

coralogix-case-analytics

aws/tools-for-devops-agent/skills/coralogix-case-analytics/SKILL.md

Fleet/aggregate analytics across many cases via the `system/labs.cases.state_updates` DataPrime dataset. Load when the user asks counts, trends, distributions or rates across cases — e.g. "MTTR last week", "how many P1 cases today", "active case count per team", "list active cases", "how long until activation on average". Do NOT load for one specific case ID — use alert tools for single-case investigation. Load the `coralogix-dataprime` skill alongside this skill.

1418d agoReviewMountCreate a free account to mount
AWSSkill

coralogix-case-management

aws/tools-for-devops-agent/skills/coralogix-case-management/SKILL.md

Create and change Coralogix Cases — open a case, comment, re-prioritise, assign, acknowledge, retitle, resolve, close, mute, link and unlink. Load when the user asks to "open a case", "create a case for this", "raise a case for X", "comment on CASE-123", "make CASE-123 a P1", "change the priority", "assign this case to …", "acknowledge CASE-123", "resolve CASE-123", "close this case", "mute this case", "stop this case notifying", "link CASE-390 under CASE-383", "make this a child of", or to find a case they described in words rather than by ID. The `coralogix-alerts` skill must be loaded alongside this skill for terminology. This skill performs mutations; for read-only investigation of one case use `coralogix-single-case`, and for counts, trends and fleet questions use `coralogix-case-analytics`.

1418d agoReviewMountCreate a free account to mount
AWSSkill

coralogix-cases

aws/tools-for-devops-agent/skills/coralogix-cases/SKILL.md

Triage and manage Coralogix Cases. Load when a user wants to inspect a case, update it, add a comment, assign or acknowledge it, resolve or close it, change its priority, inspect its events, or inspect notification deliveries.

1418d agoReviewMountCreate a free account to mount
CLAUDE.md vs AGENTS.md

Agent instruction files

What are agent instruction files?

Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.

CLAUDE.md or AGENTS.md?

CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.

What is a skill?

A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.

Can I search my own team's files too?

Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.