DevOps & Infra

builderio Bundle

Use when implementing, integrating, upgrading, debugging, or answering anything involving third-party APIs, libraries, frameworks, CLIs, cloud services, model/provider SDKs, fast-moving product behavior, user requests for latest/current/official behavior, unfamiliar repo docs/specs, errors that may indicate API drift, or high-stakes auth, security, billing, data, migration, deployment, compliance, or privacy behavior. Forces Codex to web-search for current official docs and read primary docs before assuming from memory.

legendarylinux Skill

Planning and clarification workflow for requested code changes. Use when a user describes a new feature, bug fix, refactor, migration, integration, UI change, API change, test change, CI/CD change, or other code alteration and Codex should pause before implementation to clarify scope, behavior, affected files, implementation constraints, testing, CI, documentation, code style, directory placement, rollout, and acceptance criteria. Use this after the overall request is clear enough to plan; if the user's actual goal or intended outcome is still ambiguous, `ask-user-question` should trigger first.

manifold-works Skill

Runs and troubleshoots local development for dotnet-vite-webapp-template apps using Docker Compose, including logs, restarts, migrations, ports, and env fixes. Use when the user invokes /dev-webapp, asks to start/stop the dev stack, debug compose issues, or fix CORS/JWT/DB connection problems.

manifold-works Skill

Deploys a dotnet-vite-webapp-template app to production using docker-compose.prod.yml and Caddy TLS on a specific domain and SSH server, including DNS, .env.prod secrets, migration apply, and verification. Use when the user invokes /deploy-webapp, asks to deploy/go live, or configure Caddy production hosting.

costory-io Bundle

Use when a user states a FinOps *outcome* rather than a tool. Route to one recipe card, then hand off: bill jump → explain-period-change (DIGEST preview); marketplace → marketplace-spend; K8s namespace → namespace-cost; credits runway → provider-credits; GCP spend CUD leftover → gcp-spend-cud; BigQuery warehouse → bigquery; YTD credits → credits-ytd-explore; weekly env+service pulse → service-cost-weekly; tag coverage → untagged-coverage; exec env report → env-costs-cto; explore Prod vs R&D → prod-vs-rnd-explore; build Prod/R&D VDIM → prod-vs-rnd-vdim; reallocate by external metric → reallocate-by-external-metric; budget vs actual daily → budget-vs-actual-dashboard; EC2 +10% alert → ec2-cost-spike-alert; compute drill-down → compute-drilldown-dimension. Skeletons in recipes; HOW in reports/dashboards/virtual-dimensions/query/bigquery.

costory-io Skill

Use when the user asks about BigQuery costs, SKUs, on-demand Analysis vs capacity slots/editions, leftover on-demand, physical vs logical storage, time travel or fail-safe, streaming ingest, load/import jobs consuming a reservation, dbt or job labels, slot cost reallocation, dataset/table storage allocation, or unlabeled expensive queries. Call get_skill with skillId "bigquery" before investigating BigQuery spend or cloning the [BigQuery] dashboard. Not for GCP spend-based CUDs (recipes gcp-spend-cud).

qiuqiuqiu123 Bundle

将 IDD 项目部署或回滚到指定的本地、开发、staging、production 或自定义环境。使用场景（Use when）：revision 需要以 dry-run、standard、rolling、blue-green、canary 或 rollback 模式执行，并要求使用仓库定义的预检、明确的生产授权、线上 revision 验证和可审计发布报告。

shanemullens Bundle

Drive the Splunk AI Toolkit (AITK) 6.0 from Claude Code or Cursor through a Splunk MCP Server — writing and executing ML-SPL such as `ai`, `aiagent`, `fit`, `apply`, `score`, `summary`, `listmodels`, and `deletemodel` against Splunk Cloud. Use this skill whenever the user mentions the AI Toolkit, MLTK, ML-SPL, the `ai` or `aiagent` command, Agent Launchpad, LLM connections in Splunk, training or applying a Splunk ML model, scoring or validating a Splunk model, or asks to summarize/classify/enrich Splunk events with an LLM in the search pipeline — even if they don't name the toolkit explicitly. Also use it when a Splunk search containing `fit`, `apply`, or `ai` fails, times out, truncates at 100k events, or trips an SPL safeguard warning.

microsoft Bundle

Foundry IQ knowledge bases. WHEN: make local or Blob documents searchable; create/diagnose KBs; triage unsupported connectors or multi-source KB creation/reconfiguration; connect existing KB to agents (including multi-source KBs); create/reuse a Search service; retrieve from an existing knowledge base with citations; no brand words needed. Read its procedure before query/target questions. NOT: other KB providers, repository-file search, classic Azure AI Search index/query/app work, generic agent creation.

microsoft Bundle

Plan, deploy, operate, and troubleshoot Azure Local (formerly Azure Stack HCI): sizing and prerequisites, Arc registration, lifecycle updates, workloads (Azure Local VMs, AKS on Azure Local, images, disks, logical networks), SDN and network security, and failure triage — starting read-only and confirming before risky changes. WHEN: Azure Local, Azure Stack HCI, Arc resource bridge, custom location, Azure Local VM, Arc VM, AKS on Azure Local, AKS hybrid, SDN, Lifecycle Manager, Azure Local update, disconnected site.

microsoft Bundle

Plan, deploy, operate, and troubleshoot multi-rack (rack scale) deployments of Azure Local — preintegrated racks scaling to hundreds of machines, built on Network Fabric Controller, Cluster Manager, SAN storage, and managed network fabric. Use for the Microsoft.NetworkCloud and Microsoft.ManagedNetworkFabric control plane. NOT for standard 1-16 node Azure Local, and NOT for rack-aware clusters (two racks as availability zones, up to 8 nodes, synchronous replication) — those are standard scale. WHEN: multi-rack, rack scale Azure Local, aggregation rack, compute rack, Network Fabric Controller, NFC, Cluster Manager, network fabric, isolation domain, az networkcloud, az networkfabric, multi-rack logical network, multi-rack Arc VM.

compozy Bundle

Comprehensive testing doctrine for software and AI systems — covers positive patterns, anti-patterns, gates for coding agents writing tests, CI discipline, and an LLM/agent evaluation primer. Use when authoring or reviewing tests, adding mocks, deciding test placement, generating tests via agents, debugging flaky CI, designing eval suites for LLM features, or rebuilding a brittle test suite. Contains 12 positive patterns (selector hierarchy, table-driven, builders, real-system gates), 25 anti-patterns across Brittleness, Flakiness, Mock-misuse, Process, and AI-specific families, 7 mandatory gates for agents writing tests, flaky-test taxonomy with quarantine workflow, contract / property / mutation testing patterns, and an oracle-ladder primer for LLM-as-judge and agent eval. Language-agnostic — pseudo-code only. Don't use for general code review, library-specific debugging unrelated to tests, non-testing CI pipeline design, or production observability.

signalpilot-labs Skill

Load when working with Xata Postgres branches: connecting to a branch, diffing two branches, or checking whether an upstream branch's schema change breaks a dbt project or pipeline before it merges. Covers branch connections, schema_diff_branches, pgroll migrations, and the pre-merge impact report.

devantler-tech Skill

Repository maintenance for devantler-tech/reusable-workflows — triage, action/workflow version hygiene, backward-compatible workflow health, and consistency across the shared CI/CD building blocks. Use when performing autonomous or on-request maintenance of this repo.

enapt Skill

Deploy parallel agents to scan the entire codebase for dead code, duplication, inconsistencies, and stale references

extrasmall0 Skill

Application tracker board. Read ~/.dear-hiring-manager/applications.md and render a status board (grouped by blocked/skipped/filled/submitted/rejected/interview/offer with counts and a response-rate summary), and update an application's status + date when the user reports progress (e.g. "mark Transcend as interview"). Use for /board or whenever the user wants to see or update their job-application pipeline.

freenet Skill

Orchestrate a new Freenet release. Determines next version, shows changelog, confirms with user, and triggers the release pipeline via GitHub Actions. Use when the user says "do a release", "new release", "release", or "/release".

freenet Skill

Run integration tests that require Linux (full loopback range 127.x.x.x) via Docker. Use when a test fails on macOS with "Can't assign requested address" or when the user says "/linux-test".

full-stack-biz Bundle

Test and benchmark Claude Code skills empirically using evaluation-driven development. Use when validating a skill's effectiveness, comparing skill vs. baseline performance, running benchmarks with timing/token metrics, and iterating on skill improvements. Two modes: Quick Workflow (with_skill only, no baseline, fast pass/fail) or Full Pipeline (7-phase with baseline comparison, timing, aggregation).

joevstaas Skill

Vannmiljo data pipeline — scrape water monitoring data from vannmiljo.miljodirektoratet.no, build GeoJSON, and ingest into ODP

leogallego Skill

Display the Zen of Ansible principles and review Ansible code against them. Use when the user wants to see the Zen of Ansible, get philosophical guidance on their automation approach, or review code for simplicity, readability, and clarity. Use when user says "zen of ansible", "simplify my playbook", "is this too complex", or "clean code review". Do NOT use for strict rule compliance (use ansible-good-practices instead). Do NOT use for Ansible module reference or documentation lookups (use ansible-docs instead).

leogallego Skill

Answer Ansible questions and review Ansible code using official documentation from the Ansible ecosystem. Covers ansible-core, ansible-lint, ansible-navigator, ansible-builder, ansible-creator, and molecule. Use when the user asks about Ansible concepts, syntax, best practices, deprecations, or wants Ansible code reviewed against official docs. Use when user says "check my playbook against docs", "what does Ansible say about X", "how do I use module Y", or "review my role". Do NOT use for CoP good practices review (use ansible-good-practices instead). Do NOT use for general Python or YAML questions unrelated to Ansible.

leogallego Skill

Create a new Ansible execution environment project following good practices. Optionally uses ansible-know MCP tools to validate collection dependencies on Galaxy and pin latest versions. Use when the user wants to create, generate, or bootstrap a new EE. Use when user says "create an EE", "new execution environment", "scaffold EE", or "build EE project". Leverages ansible-creator when available. Do NOT use for building existing EEs or managing containers. Do NOT use for reviewing existing EEs (use ansible-good-practices instead).

leogallego Skill

Create a new Ansible role following all Red Hat CoP good practices. Use when the user wants to create, generate, or bootstrap a new Ansible role. Use when user says "create a role", "new role", "scaffold role", or "generate role skeleton". Optionally uses ansible-know MCP tools for module-aware task generation with verified parameters. Falls back to template-based generation when MCP is unavailable. Leverages ansible-creator when available. Do NOT use for reviewing existing roles (use ansible-good-practices instead). Do NOT use for creating collections (use ansible-new-collection) or adding molecule tests to existing roles (use ansible-new-molecule).

leogallego Skill

Scaffold molecule testing for an Ansible role or collection following the current molecule testing philosophy (Ansible-native everything). Use when the user wants to add molecule tests, create test scenarios, or set up molecule for an existing role or collection. Use when user says "add molecule", "create molecule tests", "scaffold testing", "add test scenarios", or "set up molecule". Generates modern ansible-native molecule.yml (no driver/provisioner/verifier/platforms blocks), working create.yml/destroy.yml playbooks, smart verify.yml from role introspection, and optional GitHub Actions CI. Optionally uses ansible-know MCP server for module return value lookup. Do NOT use for migrating existing molecule setups (migration skill planned for a future release).

leogallego Skill

Review Ansible code against Red Hat CoP automation good practices. Use when the user wants to audit, lint, review, check, or validate Ansible roles, playbooks, collections, or inventory for compliance with CoP rules. Optionally validates module parameters via ansible-know MCP. Use when user says "lint my role", "check my playbook", "review best practices", or "audit my Ansible code". Do NOT use for general Python or YAML linting unrelated to Ansible. Do NOT use for answering Ansible module usage questions or checking syntax against official Ansible documentation (use ansible-docs instead).

leogallego Skill

Create a new Ansible content collection following all Red Hat CoP good practices. Optionally uses ansible-know MCP tools to discover existing collections on Galaxy and inspect reference collections before scaffolding. Use when the user wants to create, generate, or bootstrap a new Ansible collection. Use when user says "create a collection", "new collection", "scaffold collection", or "init collection". Leverages ansible-creator when available. Do NOT use for reviewing existing collections (use ansible-good-practices instead).

smith6jt-cop Skill

Crypto Training Pipeline Review (v5.4.1)

vidanov Bundle

Generate AWS architecture diagrams in draw.io format. Activates when the user asks to create, generate, or build an architecture diagram, system diagram, or draw.io diagram for AWS services.

different-ai Skill

AI Email Pipeline

poteto Skill

Deploys the project to the target environment.

adminturneddevops Skill

Kubernetes Expert Skill

googlecloudplatform-vertex-ai-samples Skill

<!--

scientiacapital Bundle

Analyze pipeline health, identify stalled deals, predict close probability, and suggest actions to move deals forward. Improves forecast accuracy and prevents revenue leakage. Use when deals get stuck or forecast accuracy is poor.

louisblythe Skill

When the user wants help with outbound sales prospecting, lead sourcing, or pipeline building. Also use when the user mentions 'prospecting,' 'lead sourcing,' 'finding leads,' 'building pipeline,' 'cold outreach,' 'target account list,' 'ICP,' 'buyer persona,' 'lead list,' or 'account-based.' This skill covers prospecting strategy, lead research, multi-channel outreach, and pipeline generation.

aliyun Bundle

Alibaba Cloud RDS PostgreSQL Instance Inspection Skill