Skills.
Give your AI a better way to work.
A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.
Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.
Category: Cloud & infra
2,356 results · page 61 of 79
- View details
vercel-cli-with-tokensSkillCloud & infra
Lets your agent deploy and manage Vercel projects and set environment variables using access tokens.
Ready to connect★ 57
- View details
vercel-optimizeSkillCloud & infra
Lets your agent audit deployed Vercel apps for cost and performance problems and suggest fixes.
Ready to connect★ 57
- View details
docker-expertSkillCloud & infra
Advanced Docker containerization expert for multi-stage builds, image optimization, security hardening, and Compose orchestration. Use when the task involves `working with Dockerfile`, `docker-compose.yml`, `containerization`, `multi-stage builds`, or `optimizing Docker images`.
Ready to connect★ 57
- View details
kimi-peer-writerSkillCloud & infra
DP.SC.154 peer session where Kimi = writer, Claude = peer. Started with a simple phrase. Includes ORZ Opening and Closing, turn-loop, escalations, Decision Gate (commit vs implement → review → verify → deploy), deferred finalization and verification.
Ready to connect★ 54
- View details
wagmiosSkillCloud & infra
Give your OpenClaw agent a homelab. Use when managing Docker containers, installing marketplace apps, or any Docker-related tasks on behalf of the user. Scope-based API key permissions — agent can only do what the key allows. On Linux, Docker requires sudo — without root access, WAGMIOS is the only
Ready to connect★ 57
- View details
analyzing-api-gateway-access-logsSkillCloud & infra
'Parses API Gateway access logs (AWS API Gateway, Kong, Nginx) to detect
Ready to connect★ 56
- View details
analyzing-azure-activity-logs-for-threatsSkillCloud & infra
'Queries Azure Monitor activity logs and sign-in logs via azure-monitor-query
Ready to connect★ 56
- View details
analyzing-docker-container-forensicsSkillCloud & infra
Investigate compromised Docker containers by analyzing images, layers,
Ready to connect★ 56
- View details
analyzing-kubernetes-audit-logsSkillCloud & infra
'Parses Kubernetes API server audit logs (JSON lines) to detect exec-into-pod,
Ready to connect★ 56
- View details
auditing-azure-active-directory-configurationSkillCloud & infra
'Auditing Microsoft Entra ID (Azure Active Directory) configuration to
Ready to connect★ 56
- View details
auditing-gcp-iam-permissionsSkillCloud & infra
'Auditing Google Cloud Platform IAM permissions to identify overly permissive
Ready to connect★ 56
- View details
auditing-kubernetes-cluster-rbacSkillCloud & infra
'Auditing Kubernetes cluster RBAC configurations to identify overly permissive
Ready to connect★ 56
- View details
auditing-terraform-infrastructure-for-securitySkillCloud & infra
'Auditing Terraform infrastructure-as-code for security misconfigurations
Ready to connect★ 56
- View details
awsSkillCloud & infra
AWS best practices: IAM, secrets, networking, security, compute, IaC, ops. Use when building, reviewing, or modifying AWS resources.
Ready to connect★ 56
- View details
building-cloud-siem-with-sentinelSkillCloud & infra
'This skill covers deploying Microsoft Sentinel as a cloud-native SIEM
Ready to connect★ 56
- View details
building-identity-federation-with-saml-azure-adSkillCloud & infra
Establish SAML 2.0 identity federation between on-premises Active Directory
Ready to connect★ 56
- View details
building-patch-tuesday-response-processSkillCloud & infra
Establish a structured operational process to triage, test, and deploy
Ready to connect★ 56
- View details
building-red-team-c2-infrastructure-with-havocSkillCloud & infra
Deploy and configure the Havoc C2 framework with teamserver, HTTPS listeners,
Ready to connect★ 56
- View details
building-threat-intelligence-platformSkillCloud & infra
Building a Threat Intelligence Platform (TIP) involves deploying and
Ready to connect★ 56
- View details
conducting-cloud-incident-responseSkillCloud & infra
'Responds to security incidents in cloud environments (AWS, Azure, GCP) by performing identity-based containment,
Ready to connect★ 56
- View details
gcpSkillCloud & infra
GCP best practices: IAM, secrets, networking, security, compute, IaC, ops. Use when building, reviewing, or modifying GCP resources.
Ready to connect★ 56
- View details
ai-rtkSkillCloud & infra
Use when you are about to run shell commands with long output — tests, builds, git, searches, docker/kubectl logs, cloud CLIs — to route them through rtk and read 60-90% less output; also to install or configure rtk, verify what gets rewritten with `rtk rewrite`, or report savings with `rtk gain`. N
Ready to connect★ 55
- View details
source-command-ios-runSkillCloud & infra
Build, deploy and start iOS app on device. Use proactively when user asks to test, run, or deploy iOS changes.
Ready to connect★ 55
- View details
source-command-maccatalyst-runSkillCloud & infra
Build and start the Mac Catalyst app on this Mac. Use proactively when user asks to test, run, or deploy macOS (Mac Catalyst) changes.
Ready to connect★ 55
- View details
all-scenarios-stormSkillCloud & infra
Use when a user wants to enumerate plausible designs, configurations, scenarios, and paths and diagram the field before choosing. Produces an exhaustive enumerated field and a diagram before any choice. Don''t use for remote, credential, publish, deploy, or irreversible changes.
Ready to connect★ 54
- View details
append-run-logSkillCloud & infra
Use when a completed agent run must be recorded as durable, queryable evidence. Appends one entry to the JSONL run log under an ISO date guard, prunes expired entries, and updates the last-run pointer. Don''t use for remote, credential, publish, deploy, or irreversible changes.
Ready to connect★ 54
- View details
architecture-diagramSkillCloud & infra
Use when the user asks to visualize an architecture as a self-contained HTML artifact with a hash-bound receipt. Also handles delta mode: comparing two snapshots, rendering what changed when both are supplied. Not for remote, credential, publish, deploy, or irreversible changes.
Ready to connect★ 54
- View details
artifact-arenaSkillCloud & infra
Use when asked to run /artifact-arena to generate and judge competing artifact implementations. Produce one verified synthesis with provenance and rejection reasons. Don''t use for remote, credential, publish, deploy, or irreversible changes.
Ready to connect★ 54
- View details
automatic-freeform-graphs-designSkillCloud & infra
Use when a user wants a looser conceptual graph for exploratory work. Generates a freeform conceptual graph that the user can explore. Not for remote, credential, publish, deploy, or irreversible changes.
Ready to connect★ 54
- View details
autoplanSkillCloud & infra
Use when the user runs /autoplan on a plan or idea. Runs CEO, design, DX, and engineering review phases over the idea, amends the plan, derives deterministic task IDs into a task JSONL ledger, and waits at a final human approval gate. Not for remote, credential, publish, deploy, or irreversible chan
Ready to connect★ 54
What is a skill?
A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.
55,111 of the 55,543 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.
Install one and every AI you use gets it
Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.
Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.