DevOps & Infra

canepro Skill

Use when a vendor security email, CVE, GHSA, or advisory says a self-hosted or pinned dependency needs a patch and the fix should land through GitOps, Helm values, image tags, container tags, or version-pinned manifests.

canepro Bundle

Design Kubernetes platform architecture: cluster topology, tenancy, namespaces, networking, security boundaries, upgrades, and operational ownership on EKS, AKS, GKE, or on-prem. Use for platform planning, multi-cluster models, and cost or upgrade direction. Not for live incidents (k8s-sre-triage) or sync failures (gitops-reconcile).

pavel-molyanov Bundle

Provides project infrastructure conventions and review criteria for local setup, Docker, Git hooks, CI/CD, service delivery, release artifacts, monitoring, backups, and operations. Use when: "настрой инфраструктуру", "измени CI/CD", "подготовь деплой", "настрой Docker", "собери release artifact", "настрой мониторинг", "проверь инфраструктуру", "оцени деплой", "setup infrastructure", "review infrastructure" Do NOT use for: choosing or writing application tests without an infrastructure change.

pavel-molyanov Bundle

Provides project infrastructure conventions and review criteria for local setup, Docker, Git hooks, CI/CD, service delivery, release artifacts, monitoring, backups, and operations. Use when: "настрой инфраструктуру", "измени CI/CD", "подготовь деплой", "настрой Docker", "собери release artifact", "настрой мониторинг", "проверь инфраструктуру", "оцени деплой", "setup infrastructure", "review infrastructure" Do NOT use for: choosing or writing application tests without an infrastructure change.

tommywagz Bundle

This skill should be used when the user wants to "write agent code", "build an agent with ADK", "add a tool", "create a callback", "define an agent", "use state management", or needs ADK (Agent Development Kit) Python API patterns and code examples. Part of the Google ADK skills suite. It provides a quick reference for agent types, tool definitions, orchestration patterns, callbacks, state management, and reference recipes to study. Do NOT use for scaffolding (use google-agents-cli-scaffold) or deployment (use google-agents-cli-deploy).

tommywagz Bundle

Audits an unintegrated file, folder, or vendored dependency against the host repository's real quality gates, then emits an ordered remediation script and a local CI pre-flight runner. TRIGGER when the user says 'integrate repo', 'make this folder compliant', 'match the repo style', 'align external code with our conventions', 'remediate to match CONTRIBUTING.md', 'make it pass CI locally', 'why does CI fail but lint passes locally', or drops vendored/generated/AI-authored code into a repo and asks to bring it up to standard. DO NOT TRIGGER for scaffolding a brand-new repository or service (use a project-scaffolding skill), for resolving git merge conflicts, for refactoring business logic or fixing test failures unrelated to repo standards, or for authoring the CI pipeline itself rather than conforming to it.

tommywagz Bundle

Analyzes a normalized Google Cloud resource inventory (idle Compute Engine instances, unattached persistent disks/static IPs, under-utilized BigQuery flat-rate slots, unexpiring BigQuery datasets, over-provisioned Cloud Run min_instances/concurrency) and generates prescriptive recommendations plus reviewable Terraform remediation snippets to cut spend. TRIGGER when the user asks to "reduce GCP costs", "find idle Google Cloud resources", "optimize BigQuery slot utilization", "run a GCP spend/FinOps audit", or provides a GCP billing/inventory export. DO NOT TRIGGER for general Terraform authoring unrelated to cost, AWS/Azure cost optimization, or security/compliance scanning of GCP resources (use the gcp-terraform-security-policy skill for that).

tommywagz Bundle

Orchestrates a two-stage spatial research and architectural drafting pipeline using Model Context Protocol (MCP) servers: researching property floor plans across real estate listing platforms (Zillow, Apartments.com, Redfin), and programmatically authoring vector CAD layouts via Floor Builder and CAD MCP servers. TRIGGER when users ask to 'research real estate floor plans', 'extract floor plan from Zillow, Redfin, or Apartments.com', 'generate CAD floor plan from property listing', 'draw floor plan with Floor Builder MCP', 'convert listing blueprint to DXF/SVG', or route queries through real estate research and CAD drafting MCP servers. DO NOT TRIGGER for property price estimation or mortgage calculations, general 3D video game level modeling, or mechanical CAD drafting unrelated to residential architecture.

tommywagz Bundle

Audits Google Cloud IAM bindings and service-account key exposure, interprets IAM Recommender evidence, and proposes reviewable least-privilege predefined/custom roles or Workload Identity Federation migration without changing access. TRIGGER when users ask to 'audit GCP IAM permissions', 'harden service account keys', 'implement least-privilege roles', 'configure Workload Identity', 'rightsize project-level editor bindings', or review IAM Recommender output. DO NOT TRIGGER for granting new broad production access, rotating secrets without an IAM audit objective, or AWS/Azure IAM reviews.

tommywagz Bundle

Designs and operates headless, long-running ADK agents triggered by Pub/Sub events or Cloud Scheduler cron jobs, with idempotent event handling, structured logs, retries/dead-lettering, and session-context compaction. TRIGGER when users ask to 'build an event-driven ADK agent', 'run ADK on a cron schedule', 'configure Pub/Sub triggers', 'manage long-running background tasks', or use `EventsCompactionConfig`/`LlmEventSummarizer` to summarize session history. DO NOT TRIGGER for interactive single-request ADK agents, generic FastAPI endpoints without an autonomous worker, or one-time local scripts.

tommywagz Bundle

Designs user-authenticated OAuth 2.0/OIDC consent flows for ADK agents accessing Google Workspace APIs, using least-privilege scopes, authorization-code + PKCE redirects, and ADK credential-request callbacks without exposing user tokens to the model. TRIGGER when users ask to 'configure OAuth for ADK agent', 'request user consent in ADK', 'connect my agent to Google Drive/Workspace', 'handle user OAuth tokens', or use `OAuth2Auth`, `OidcAuth`, or `tool_context.request_credential`. DO NOT TRIGGER for service-account-only server-to-server access, creating Google Cloud API keys, or general Google Workspace administration.

tommywagz Bundle

Configures and deploys a runner-wide ADK BasePlugin that wraps every coordinator and sub-agent with GCP Model Armor safety guardrails, blocking harmful inputs, session-state poisoning, and sensitive-data (PII) exfiltration at model boundaries and configured outbound tools. TRIGGER when the user asks to "add safety guardrails in ADK", "configure Model Armor in agents-cli", "block harmful content or prompts", "implement exfiltration detection", "write a runner-wide safety plugin", or mentions `BasePlugin`, `before_model_callback`, `sanitizeUserPrompt`/`sanitizeModelResponse`. DO NOT TRIGGER for agent-specific (non-global) callback logic unrelated to safety, generic content moderation outside an ADK Runner, or GCP IAM/Terraform security auditing (use gcp-terraform-security-policy for that).

tommywagz Bundle

Audits Google Cloud Terraform configuration (raw .tf files or a `terraform show -json` plan) against CIS Google Cloud Platform Foundation Benchmark controls, private-by-default storage/network defaults, and least-privilege IAM, then proposes remediation HCL before `terraform apply`. TRIGGER when the user asks to "audit Terraform for GCP security", "scan for public GCS buckets/IAM/firewall rules", "check CIS GCP benchmark compliance", "review least-privilege IAM in Terraform", or provides a `terraform plan`/`terraform show -json` output for GCP. DO NOT TRIGGER for general Terraform authoring/module design unrelated to security, AWS/Azure/other-cloud IaC scanning, or actually running `terraform apply` (this skill only audits and proposes; it never applies infrastructure changes).

tommywagz Bundle

Diagnoses failing GKE/Kubernetes workloads from read-only pod status, events, logs, container exit codes, resource settings, and Artifact Registry image-pull signals; produces reviewable remediation patch manifests without applying them. TRIGGER when users mention `CrashLoopBackOff`, `OOMKilled`, `ImagePullBackOff`, `ErrImagePull`, `CreateContainerConfigError`, a pod stuck `Pending`, or ask why a Kubernetes/GKE deployment is crashing or restarting. DO NOT TRIGGER for deploying a new Kubernetes app, modifying a healthy workload, cluster-node/network outages, or running destructive `kubectl` recovery commands.

leadgenjay Bundle

One front door for making creative output and the skills that produce it better. Reads the session and picks a pathway: polish (critique one finished creative and regenerate it, skill untouched), heal (trace blatant defects in an output back to the producing skill, mutate it, regenerate until clean), learn (eval-driven loop that mutates a skill until its assertion pass rate stops rising), or create and improve a skill (skill-creator writes it, then learn and heal run on it). Asks once only when two pathways are equally supported. Triggers: 'ultraskill', 'autoskill', 'polish this', 'critique and redo', 'make this creative better', 'heal this', 'heal the skill', 'fix and prevent', 'output is broken', 'improve skill', 'skill eval', 'benchmark skill', 'optimize skill', 'skill loop', 'self-improve', 'create and improve a skill', 'skill pipeline', 'perfect skill'.

netdata Bundle

Query or explain direct Netdata Agent APIs and Functions; review direct-query recipes or helpers; troubleshoot bearer authentication. Use query-netdata-cloud for Cloud-proxied calls.

dkpapadopoulos Skill

Use when preparing to ship or release — before pushing to production, promoting a build, or finalizing a branch — to confirm CI is green, no WIP commits remain, and version and design artifacts are in order

dkpapadopoulos Bundle

Use when facing flapping alerts, alert fatigue, recurring noisy incidents, threshold audits, or SLO-alert redesign questions for a GCP monitoring project.

dkpapadopoulos Bundle

Use when investigating production symptoms — connection failures, pod crashes/restarts, SIGTERM/OOM errors, latency spikes, Cloud SQL/proxy issues, deployment-correlated errors, ImagePullBackOff, CreateContainerConfigError, or node NotReady events

0gfoundation Skill

Deploy Contract to 0G Chain

0gfoundation Skill

Deploy an AgenticID Agent

axross Bundle

Every task that touches a project — implementing, refactoring, running a project command, or writing a pull request body — even when the request never mentions formatting, linting, comments, dependencies, docs, or descriptions. Also when you need to know how to run one of the project's operations (tests, dev server, build, lint, deploy) and must find it documented or ask. Not for a session that touches nothing, where the conduct baseline applies instead. The baseline discipline — the format/lint loop, scoped change management, risk-surface mapping, and contributor docs.

rkortthinkwise Skill

Reference guide for starting, monitoring, and controlling a Thinkwise Software Factory definition-generation job — generating the application definition alone, or the full generate/validate/build/deploy pipeline ("complete creation") — via the sf/software_development domain. Use whenever an MCP connector with Software Factory access starts, checks, cancels, or resolves a paused step of a generation/validation/deployment job, or before calling get_task_definition/stage_task/execute_odata_query against add_job_to_generate_definition, definition_generation_overview, definition_generation_step, or definition_validation_overview.

paulieb89 Skill

Search BAILII for UK case law and retrieve full judgment text. Use when someone asks to find a case, search for case law on a topic, read a judgment, or check how courts have ruled on an issue. Covers UKSC, EWCA, EWHC, Upper Tribunal, EAT, and more. Requires the BAILII MCP server running locally (BAILII blocks cloud IPs).

neronain Skill

Train SONA neural patterns from successful task completions, view learned patterns, and optimize the intelligence pipeline

neronain Bundle

Deploy, size, move and repair LLMs on NVIDIA DGX Spark (GB10) fleets with LMDS — fit, push/clone, stacked pairs, start failures, fleet updates.

compozy Bundle

Explains Compozy capabilities, CLI commands, core workflow skills, optional extension skills, configuration, artifact structure, reusable agents, and extensions. Use when the user asks how to use Compozy, what commands are available, how the workflow pipeline works, or how to configure a workspace. Do not use for executing workflow steps — use the specific cy- skills instead.

tobihagemann Skill

Project-wide health audit pipeline that fans out to all analysis skills in parallel, evaluates findings, and produces a unified report at .turbo/audit.md. Use when the user asks to "audit the project", "run a full audit", "project health check", "audit my code", "codebase audit", or "comprehensive review".

ww-w-ai Bundle

Enterprise-grade system development with microservices, Kubernetes, Terraform. Includes AI Native methodology and Monorepo patterns. Project initialization with "init enterprise". Actions: init->system setup, strategy->architecture decisions, infra->infrastructure design, review->architecture review. Triggers: microservices, kubernetes, terraform, k8s, AWS, monorepo, 마이크로서비스, 쿠버네티스, マイクロサービス, 微服务, microservicios, microservices, Microservices, microservizi Do NOT use for: simple websites (use $starter), BaaS apps (use $dynamic).

ww-w-ai Bundle

Zero Script QA methodology: log-based testing without writing test scripts. Uses Docker logs, curl commands, and runtime verification for quality assurance. Triggers: zero script qa, log-based testing, docker logs, QA, test without scripts, 제로 스크립트 QA, 로그 기반 테스트, ゼロスクリプトQA, ログベーステスト, 零脚本QA, 日志测试, QA sin scripts, QA sans script, skriptloses QA Do NOT use for: unit testing frameworks (use standard test tools), deployment (use $phase-9-deployment).

ww-w-ai Bundle

Phase 9: Deployment & CI/CD. Set up production deployment, CI/CD pipelines, monitoring, and operational readiness. Triggers: deployment, CI/CD, production, release, monitoring, hosting, 배포, CI/CD, デプロイ, 部署, despliegue, déploiement, Bereitstellung, distribuzione Do NOT use for: API implementation (use $phase-4-api), code review (use $phase-8-review).

ww-w-ai Bundle

9-phase Development Pipeline overview. Use when starting a new project or unsure about development order. Triggers: development pipeline, phase, development order, where to start, 개발 파이프라인, 뭐부터, 어디서부터, 開発パイプライン, 何から, 开发流程, 从哪里开始, pipeline de desarrollo, pipeline de développement Do NOT use for: specific phase details (use $phase-N-xxx).

kevin-burns Bundle

Orchestration playbook for driving the development agent fleet (code-builder, fact-verifier, coherence-checker, code-reviewer) through a build → verify → cohere → review → commit pipeline with explicit, deterministic hand-offs. Use when implementing a non-trivial change where correctness and fact-accuracy matter and you want the steps to actually run in order rather than hoping the orchestrator delegates. Also use when deciding which fleet agent to dispatch for a task, or when wiring a new agent into the pipeline. Covers how to pass context between agents, the fact-gate and coherence-gate before commit, the loop-back semantics on each gate, and handing off to commit-pr.

kevin-burns Bundle

Deterministic, offline-first lookups over Azure Policy, Policy Initiative, and RBAC Role metadata sourced from AzAdvertizer's CSV exports — including the cross-references that exist nowhere else in one place (which roles a policy uses, which initiatives include a policy, which policies a role is used by). Use whenever you need accurate current facts about an Azure built-in policy, initiative/policy-set, or RBAC role — definitions, effects, allowed effect values, categories, role actions/dataActions, or the policy↔role and policy↔initiative relationships — for writing or reviewing Azure IaC, governance, or landing-zone work. Fetches each CSV once into a provenance-stamped cache and answers queries offline; stdlib only, JSON envelope output. Pairs with terragrunt-skill, azure-architect, and fact-verifier (snapshots become tier-1 sources).

kevin-burns Bundle

Comprehensive Terragrunt 1.x skill for generating, validating, reviewing, and debugging Terragrunt configurations (root.hcl, terragrunt.hcl, terragrunt.stack.hcl, units, stacks, catalogs) across AWS, Azure, and GCP. Use this skill whenever the user mentions Terragrunt, terragrunt.hcl, root.hcl, stack files, units, HCL orchestration of OpenTofu/Terraform, remote state DRY configuration, run --all, dependency blocks between modules, or asks to scaffold/lint/diagnose multi-environment IaC layouts — even if they don't say "Terragrunt" explicitly but show Terragrunt HCL.

kevin-burns Bundle

Provider-agnostic CLI for targeted search and inspection of the Terraform Registry via its JSON API — any provider (AWS, GCP/google, Azure/azurerm, GitLab, OpenStack, Kubernetes, ...). Use to find modules by keyword, inspect a module's inputs/outputs/versions, or look up a resource type's attributes, WITHOUT web-scraping or dumping pages into context — it fetches the JSON payload, strips it locally, and returns only what you asked for. Caches every payload as a provenance-stamped snapshot so repeat calls are offline and token-free. Use whenever you need accurate, current Terraform module/provider facts for writing or reviewing IaC.