DevOps & Infra

tomevault-io Bundle

Primary entrypoint for coding agents using CAIRA as reference material to design and build generative AI solutions with Azure AI Foundry, Azure OpenAI-compatible endpoints, agent frameworks, APIs, and frontends tailored to a user's scenario. Use when this capability is needed.

tomevault-io Bundle

Create agent skills for Microsoft technologies using official documentation. Use whenever the user wants to build, generate, or scaffold a skill for any Microsoft technology (Azure, .NET, M365, VS Code, Bicep, etc.)—even phrased casually like "make a skill for Cosmos DB." Investigates the topic via official docs, then generates a hybrid skill with essential knowledge stored locally and dynamic lookups for depth. Use when this capability is needed.

tomevault-io Bundle

Run Semgrep static analysis for fast security scanning and pattern matching. Use when asked to scan code with Semgrep, write custom YAML rules, find vulnerabilities quickly, use taint mode, or set up Semgrep in CI/CD pipelines. Use when this capability is needed.

tomevault-io Bundle

provides expert guidance on lord, a minimalist paas cli tool for deploying docker containers via ssh. use when user mentions lord deployment, docker container deployment, traefik configuration, remote hosting, or paas management and has a lord.yml file in their repo directory.

tomevault-io Bundle

Launch and manage Codex Cloud tasks from the CLI, including detached background watchers that track completion. Use when users ask to run coding work in cloud/background agents, queue multiple cloud tasks, poll task status, fetch cloud diffs, apply cloud outputs locally, or pair cloud kickoff with `$cas` orchestration. Use when this capability is needed.

tomevault-io Bundle

Build and run LLM-powered data processing pipelines with DocETL. Use when users say "docetl", want to analyze unstructured data, process documents, extract information, or run ETL tasks on text. Helps with data collection, pipeline creation, execution, and optimization. Use when this capability is needed.

tomevault-io Bundle

Privacy-first, self-hosted chat memory for OpenClaw — save and recall conversation history across sessions without any cloud dependency. Use when this capability is needed.

tomevault-io Bundle

Guides JoSk integration for horizontally scaled Node.js and Bun apps — cluster-wide scheduling via Redis, MongoDB, or PostgreSQL so each tick runs on one instance. Use when writing or reviewing recurring jobs, cron-style tasks, `setInterval`/`setTimeout`/`setImmediate` work, periodic background jobs (queues, sync, polling, cleanup), multi-instance / Kubernetes / PM2 / Meteor deployments, the `josk` npm package, or `ostrio:cron-jobs`. Also when the user names JoSk, `RedisAdapter`, `MongoAdapter`, `PostgresAdapter`, Redis Cluster / KeyDB Cluster hash-tag routing via `useHashTags`, at-least-once / at-most-once semantics, zombie recovery, leases, `zombieTime`, `execute`, `concurrency`, `pause()`/`resume()` instance backpressure, or comparisons to Agenda, Bree, node-cron, Bull, or BullMQ. Use when this capability is needed.

tomevault-io Bundle

Create and start an aide agent instance from an image. Use when the user wants to spin up, deploy, or create a new agent. Use when this capability is needed.

lobehub Bundle

Command-line tool for managing LobeHub services. Use this skill when you need to manage AI agents, knowledge bases, conversations, files, models, providers, bot integrations, or any LobeHub Cloud resources. Covers authentication, agent execution, content generation, memory management, and device connectivity.

materializeinc Bundle

Bump the mz-deploy Homebrew formula (Formula/mz-deploy.rb) to a new release version — updates the version field and recomputes every platform's sha256 checksum from the published tarballs. Use this whenever the user wants to release, bump, update, or upgrade mz-deploy to a new version in this tap, or mentions a new mz-deploy version number (e.g. "release mz-deploy 0.2.0", "bump mz-deploy", "new mz-deploy version is out"). Edits files only and stops for review — it does not commit or open a PR.

materializeinc Skill

Contributing to the Materialize Terraform provider codebase. Covers the project layout (pkg/materialize, pkg/resources, pkg/datasources, pkg/provider), the builder pattern for SQL generation, adding new resources and data sources end to end, the acceptance test framework, unit testing with sqlmock, CI pipelines, release flow via goreleaser, and codebase conventions. Use this skill whenever the user wants to add a new Terraform resource or data source, modify an existing resource, write or run provider tests, understand the provider architecture, debug test failures, cut a release, or contribute a fix to the terraform-provider-materialize codebase. Also trigger when the user mentions pkg/materialize, pkg/resources, acceptance tests, mock scans, the builder pattern in this provider, or GNUmakefile targets.

mebusw Bundle

Extract structured data from Canadian receipt and invoice images with vision LLM cross-validation, then map each expense to a CRA GIFI code for T2 filing. Use whenever the user mentions processing receipts, extracting invoice data, OCR on receipts, expense extraction, GIFI coding, T2 Schedule 125, Schedule 1 adjustments, or converting receipt images into a structured expense spreadsheet. Triggers on "process these receipts", "extract data from invoices", "OCR these photos", "categorize expenses by GIFI", "build an expense workpaper". Useful for Canadian small-business tax preparation, CPA workpapers, and batch processing of receipt photos or PDFs. ALWAYS use this skill when the user provides receipt images and wants structured data out — the cross-validation pipeline and CRA-verified GIFI mapping produce far better results than handling it inline.

mebusw Bundle

Publish a completed SKILL.md folder to one or more public marketplaces (ClawHub, Tencent SkillHub, skills.sh, SkillsMP, LobeHub, Agensi, Coze, ClawMart) — validates frontmatter, optionally drafts a bilingual README, strips credential / build / dot-files, tags git, and ships serially. Use when the user names BOTH the action and the destination — e.g. "publish to ClawHub and skills.sh", "把这个 skill 推到腾讯 SkillHub", "ship a new version of my-skill to all 8 marketplaces". Do NOT trigger on bare "发布 skill" or "ship to marketplace" — those alone are too ambiguous for a destructive pipeline. Side effects (see Security & Privacy): local file read/overwrite, optional deletion of credential files (dry-run by default), git tag push, network calls to marketplace APIs, token auth via env vars. Not for: local-only management, drafting an unfinished skill, or single-marketplace docs.

mebusw Bundle

Manage Zoom meetings, cloud recordings, and account users via a Server-to-Server OAuth REST script. Use this skill when the user wants to list, view, create, or delete a scheduled Zoom meeting; query cloud recordings for a user; or look up account users. The script exposes a fixed CLI action whitelist (list/get/create/delete meeting, get/list user, list recordings); agents must only invoke these documented actions and must not modify the script, import internal functions, or construct arbitrary Zoom API requests. create_meeting requires the agent to obtain explicit user confirmation of topic, start_time, and duration before invoking. delete_meeting is gated by a required --yes flag and the agent must display the meeting info and obtain explicit user confirmation before invoking. Requires a Zoom Server-to-Server OAuth app and a local .env with ACCOUNT_ID, CLIENT_ID, CLIENT_SECRET, USER_ID.

metabase Skill

Set up and run a local Metabase instance. Downloads the JAR (if Java 21+ is available) or runs via Docker. Also handles stopping running instances.

microsoft-foundry Bundle

Use when the user wants to fine-tune a model on Azure AI Foundry — including dataset preparation, training, evaluation, and deployment.

microsoft Bundle

Sets up, migrates, or enhances Azure Monitor Application Insights in .NET applications. Detects application type and existing instrumentation automatically. Use when adding Application Insights, Azure Monitor, observability, or telemetry to ASP.NET Core, Worker Service, ASP.NET Classic, or Console apps, upgrading from Application Insights 2.x to 3.x, migrating from TelemetryClient to OpenTelemetry, or adding Entity Framework, Redis, SQL, or OTLP telemetry to apps already using Application Insights.

microsoft Bundle

Use when the user wants to create, manage, or operate Azure Container Apps sandboxes — hardware-isolated microVMs driven by the `aca` CLI. USE FOR: create sandbox group, create sandbox, aca doctor, aca auth login, install aca, exec in sandbox, sandbox shell, fs read/write, expose port, mount volume, snapshot/suspend/resume sandbox, commit to disk, egress rules, secrets, identity, list disk images, Python SDK install, Azure portal sandbox surface, compare to Dynamic Sessions or Container Apps, scenarios like coding agents, code interpreter, agent swarms, computer-use, web apps, MCP hosting. DO NOT USE FOR: regular Azure Container Apps (`Microsoft.App/containerApps`), AKS, or VM workloads.

microsoft Skill

Primary entrypoint for coding agents using CAIRA as reference material to design and build generative AI solutions with Azure AI Foundry, Azure OpenAI-compatible endpoints, agent frameworks, APIs, and frontends tailored to a user's scenario.

microsoft Bundle

Development workflow for building, syncing, packaging, and shipping Copilot Studio agents. Use this skill when working with Copilot Studio YAML files (agent.mcs.yml, topics, actions, variables), when pulling or pushing agent changes, when packaging solutions for distribution, or when troubleshooting common Copilot Studio platform issues. Triggers on: Copilot Studio, MCS, agent.mcs.yml, .mcs.yml files, pac CLI, Power Platform solution, pull from cloud, push to cloud, publish agent, solution packaging, heartbeat flow, Power Automate flows.

microsoft Bundle

Scaffold a complete, production-ready Azure project from scratch for ANY use case: RAG chatbots, multi-agent systems, API backends, data pipelines, Azure Functions, full-stack web apps, ML training/inference, or event-driven microservices. USE FOR: gathering requirements through adaptive questioning, generating complete project folder structures with all source files, Azure Bicep infrastructure, azure.yaml for azd-up deployment, Docker configuration, CI/CD workflows, README with architecture diagrams, and Responsible AI documentation. Produces fully deployable Azure projects targeting Azure Container Apps, Azure AI Foundry, Azure Functions, or Azure ML. DO NOT USE FOR: modifying existing projects, deploying to Azure (use azure-deploy skill), managing Azure resources (use azure-prepare skill).

microsoft Skill

Deploy, operate, and troubleshoot the openclaw-dev template: a secure, hosted OpenClaw AI assistant on Azure (Azure Container Apps + Azure OpenAI in Foundry Models, passwordless via Managed Identity, Entra ID Easy Auth, ephemeral sandbox execution, optional Microsoft Teams channel) using the repo's `devclaw` wrapper around the Azure Developer CLI (azd). USE FOR: deploy openclaw-dev / OpenClaw to Azure in one prompt, "devclaw up" / "azd up" failing, set the model or region, switch tool execution to ephemeral sandboxes (EXECUTION_MODE=sandbox / devclaw exec-mode), clone another sandbox, connect OpenClaw to Microsoft Teams / use it from a phone, stop to save cost, start/restart, stream logs, verify the deployment, configure Entra ID sign-in, restrict access to specific users, tear everything down (nuke & pave). DO NOT USE FOR: editing OpenClaw's own source on npm, general Azure resource creation unrelated to this template, non-Azure hosting.

mikekelly Skill

Drive the claude-design CLI for deterministic, inference-free Claude Design sync (pull/push/list/create). Use when you need to mirror a Claude Design project to/from a local directory, resolve a project UUID, or script repeatable sync in CI — without putting model inference in the loop. Crucially, it lets synced design content (and its `.etags` baseline) live in git for versioning, audit, and one-command revert — the change-tracking the cloud service lacks, so agents can't overwrite reference designs without a tracked, revertible checkpoint. Prefer this over routing sync through the DesignSync MCP tool or claude -p whenever the work is scriptable, repeatable, CI-driven, or when design changes must be tracked and revertible.

mikeyobrien Bundle

Get an email address for your AI agent. Register, receive, read, reply, and manage a sender allowlist at name@rhobot.dev.

mikkelkrogsholm Bundle

Set up, manage, and run ralph-it autonomous agent loops on projects. Use when: (1) Setting up ralph-it on a new or existing project, (2) Creating GitHub issues for autonomous processing, (3) Writing or editing RALPH.md prompt templates, (4) Running, monitoring, or debugging ralph-it loops, (5) Configuring agents (Claude, Codex, Gemini, Aider), (6) Working with ralph-it labels, logs, or lock files. Covers: installation, issue format standards, RALPH.md syntax, multi-LLM configuration, label system, logging, and GitHub Actions CI/CD.

miyaosk Bundle

加密货币量化交易 AI Skill。用自然语言描述交易规则 → 生成策略脚本 → 服务器回测 → 参数优化 → 实时监控。 支持 Binance/Hyperliquid 全币种，6 种优化算法（genetic/bayesian/grid/random/annealing/pso），异步进度推送。 Use when user asks to: 推荐策略, 有什么策略, 推荐, 有现成的吗, 不会写, recommend, suggestions, 创建策略, 创建一个策略, 创建, 建策略, 新策略, 写策略, 做策略, 生成策略, 设计策略, 帮我写, create strategy, new strategy, 弄个策略, 回测, 测一下, 测试, 跑一下, 试试, 看看效果, backtest, test, 历史验证, 优化, 调参, 优化参数, 优化策略, 优化下, optimize, tune, 监控, 部署, 上线, 跑起来, 定时执行, 定时跑, 跑策略, 执行策略, 自动执行, 自动跑, 挂着跑, 定时任务, cron, run, deploy, monitor, 盯盘. This skill MUST be used for ANY request involving trading strategies, backtesting, parameter optimization, or strategy monitoring/execution. Also triggered when user replies with a number (1-6) following a skill prompt with numbered options. Do NOT use coding-agent for these tasks. ========== CRITICAL RULE ========== 当用户要求创建/写/建/做策略时，你必须生成 PYTHON 脚本（使用 data_client + indicators 框架）。 ⛔ 绝对禁止生成 TradingView Pine Script（//@version=5, strategy(), ta.ema(), ta.crossover()）。 ⛔ 绝对禁止生成 MQL4/MQL5 或任何非 Python 的代码。 策略脚本必须包含: from d

tomevault-io Bundle

Azure Backup MCP — Weekly Telemetry & Customer Report Generator

tomevault-io Bundle

Retrieve Terraform documentation from the public registry using the tfdc CLI. Supports provider doc search/get/export, module search/get, policy search/get, and Terraform style/module-dev guides. Use when you need to find, read, or export Terraform provider docs, module docs, policy docs, or development guides. Use when this capability is needed.

tomevault-io Bundle

Deploy Slawk to GCP. Use when the user says "deploy", "/deploy", or asks to deploy the application. Use when this capability is needed.

tomevault-io Bundle

Use when reviewing PRs that add or modify a payment Provider in yansongda/pay - covers plugin pipeline, multi-tenant safety, signature verification, docs, and naming conventions.

tomevault-io Bundle

Use when helping someone use okdev to initialize, start, inspect, connect to, sync with, troubleshoot, or tear down Kubernetes dev sessions, including manifest-backed and PyTorchJob workloads.

tomevault-io Bundle

Run Doris docker-based regression tests from a clean package Use when this capability is needed.

tomevault-io Bundle

Use when setting up or modifying CI/CD pipelines with GitHub Actions. Covers workflow syntax, triggers, caching, matrix builds, secrets, deployment jobs, and status checks.

tomevault-io Bundle

Guidelines for writing BDD-style test code using Ginkgo/Gomega framework in Go. Use when writing tests for Kubernetes operators, controllers, or Go services. Focuses on behavior-driven development with Given-When-Then patterns and table-driven tests. Use when this capability is needed.

tomevault-io Bundle

Docker development environment CLI. Use for managing containers (start/stop/restart), executing commands in services, viewing logs, and running project scripts from kool.yml. Use when this capability is needed.