Best agent skills for DevOps and SRE Engineers, page 124

Multi-agent coordination daemon for coding agents. An agent skill from curiositech/some_claude_skills.

curiositech/some_claude_skills

Docusaurus build health validation and deployment safety for Claude Skills showcase.

curiositech/some_claude_skills

Maintainer workflow for the pre-PR secure loop: code, build/test, SAST/CodeQL, dynamic sanitizer checks, fixes, and concise handoff.

InternationalColorConsortium/iccDEV

Manage MongoDB databases via the mongosh tool. An agent skill from olasunkanmi-SE/codebuddy.

olasunkanmi-SE/codebuddy

Create Docker containers for Huawei Ascend NPU development with proper device mappings and volume mounts.

ascend-ai-coding/awesome-ascend-skills

昇腾 NPU 单算子性能基准测试 Skill；当前版本只做现有环境检查、CANN 版本识别、用户确认后执行 benchmark，不负责修复或安装环境。

ascend-ai-coding/awesome-ascend-skills

Ranked next offensive moves from engagement state. An agent skill from Encod3d-Sec/TORCH.

Encod3d-Sec/TORCH

Automate ML workflows with Airflow, Kubeflow, MLflow. An agent skill from secondsky/claude-skills.

secondsky/claude-skills

Deploy production recommendation systems with feature stores, caching, A/B testing.

secondsky/claude-skills

Health check endpoints for liveness, readiness, dependency monitoring.

secondsky/claude-skills

Structured logging with proper levels, context, PII handling, centralized aggregation.

secondsky/claude-skills

Deploy ML models with FastAPI, Docker, Kubernetes. An agent skill from secondsky/claude-skills.

secondsky/claude-skills

Nuxt 5 server-side development with Nitro v3, h3 v2, API routes, middleware, and database integration.

secondsky/claude-skills

Guides Qdrant monitoring and observability setup. An agent skill from qdrant/skills.

qdrant/skills

Navigation hub linking sub-skills for proactive Qdrant tuning: search speed, indexing performance, and memory usage optimization.

qdrant/skills

A skill your agent uses when analyzing disruption from a DisruptionRegression alert, a Grafana disruption dashboard URL, or Prow CI job runs by examining interval data, audit logs, pod logs, and CPU…

openshift-eng/ai-helpers

Start or resume an APEX workflow or named step in Agent Host after manual owner selection.

jonathan-vella/apex

Expert Australian Information Security Manual (ISM) advisor for government entities and their supply chains.

lawve-ai/awesome-legal-skills

Azure Data Factory (ADF) CI/CD, deployment, and pipeline development.

Kilo-Org/kilo-marketplace

A skill your agent uses when designing distributed storage for HDFS, S3, ADLS, GCS, MinIO, NFS, or any distributed file system for data workloads.

Kilo-Org/kilo-marketplace

Perform SCCM reconnaissance and takeover prerequisite validation, including site-role mapping, provider and AdminService checks, site database separation checks, and relay-path prechecks.

SpecterOps/skills

Perform a security-focused review of current git changes. An agent skill from SpecterOps/skills.

SpecterOps/skills

Produce a repository-grounded application security threat model with assets, boundaries, abuse paths, priorities, and mitigations.

nightly-labs/openbot

Go coding rules: style, patterns, security, testing. An agent skill from softspark/ai-toolkit.

softspark/ai-toolkit

Transform bounded HAR captures into deterministic HTTP evidence about methods, origins, paths, status classes, header presence, redirects, cookies, and body sizes without replaying traffic or…

cyberful/cyberful

Normalize and correlate bounded SARIF and Cyberful finding exports offline by rule, location, fingerprint, source, level, suppression, and evidence reference without treating scanner severity as…

cyberful/cyberful

Audit build and release pipelines for identity separation, source-to-artifact integrity, provenance, approval, promotion, signing, rollback, and production deployment controls.

cyberful/cyberful

Audit container runtime isolation across namespaces, capabilities, seccomp, mandatory access control, mounts, devices, daemon sockets, cgroups, identity, and host integration.

cyberful/cyberful

Audit secret issuance, storage, delivery, use, rotation, revocation, replication, logging, and break-glass controls across application and cloud systems.

cyberful/cyberful

Read and inspect mittwald mStudio projects, apps, runtimes, databases, domains, mail, backups, files, containers, and access users through SecretRef-backed API requests.

HybridAIOne/hybridclaw

Read Zabbix monitoring state, inspect monitored hosts, summarize current or recent problems, and prepare guarded incident-response context without exposing Zabbix credentials.

HybridAIOne/hybridclaw

Find leaked API keys, tokens, and credentials in public GitHub repositories.

uphiago/recon-skills

ArgoCD GitOps deployment management and troubleshooting When user mentions ArgoCD, GitOps, application sync, or argocd commands

shepherdjerred/monorepo

Design or change repo-owned homelab infrastructure, Kubernetes resources, Helm values, services, versions, secrets, DNS, or OpenTofu.

shepherdjerred/monorepo

Audits and hardens API credential handling (env vars, separation, rotation plan, least privilege, auditability).

sundial-org/awesome-openclaw-skills

Security incident detection, analysis, containment, eradication, recovery, and lessons learned per NIST SP 800-61r2 and ISO 27035

Hack23/cia

Never commit secrets, manage credentials securely using environment variables, vaults, and Hack23 ISMS key management policy

Hack23/cia

Conduct systematic threat modeling using STRIDE framework, attack trees, and security architecture analysis for CIA platform

Hack23/cia

Bootstrap a repository with reusable workflows from kdeldycke/repomatic.

kdeldycke/dotfiles

Manage NixOS packages declaratively. An agent skill from bolivian-peru/os-moda.

bolivian-peru/os-moda

A skill your agent uses when the user needs to write, review, or migrate SQL queries in ADVPL/TLPP using BeginSQL/EndSQL blocks and macro expressions (%table%, %xfilial%, %notDel%, %exp%, %Order%)…

thalysjuvenal/advpl-specialist

Run a blameless postmortem for an incident caused by an AI agent or LLM feature — hallucinated facts shipped to users, runaway tool use, prompt injection, cost blowouts, or wrong actions taken…

mohitagw15856/pm-claude-skills

Specify the tracing, metrics, and alerting for an AI agent or LLM feature in production.

mohitagw15856/pm-claude-skills

Set up a backup system that actually protects your photos, files, and devices — built on the 3-2-1 rule and, crucially, tested so it works when you need it.

mohitagw15856/pm-claude-skills

Run the worst-case drill before an agent goes autonomous — the 'if this agent were fully hijacked right now, what's the damage' walk-through, the containment controls (caps, kill-switch…

mohitagw15856/pm-claude-skills

Produce a capacity planning document for a service covering traffic forecasts, resource requirements, and scaling strategy.

mohitagw15856/pm-claude-skills

Write a CI/CD pipeline playbook for a service or team. An agent skill from mohitagw15856/pm-claude-skills.

mohitagw15856/pm-claude-skills

A skill your agent uses when asked 数据出境要申报吗, 数据出境安全评估还是标准合同, 个人信息出境标准合同怎么备案, 我们把数据传到海外总部合规吗, or decide how to transfer data out of mainland China lawfully.

mohitagw15856/pm-claude-skills