DevOps & Infra

inlets Bundle

Installs, inspects, and operates the inlets-operator lifecycle for Kubernetes LoadBalancer Services and Tunnel CRs. Use when exposing a private cluster Service with a cloud VM/public IP, checking operator resources with kubectl, recreating a tunnel, or safely deleting operator-managed infrastructure.

kelly-griffith Bundle

Completes a contract-first Spring Boot scaffold — api/ contract interfaces, api/dto/ record DTOs, shared problem+json components, and red MockMvc contract tests, however they were produced — by implementing the web, service, and repository layers plus Flyway migrations under fixed cross-cutting decisions (hand SQL via JdbcClient vs JPA by criteria, server-assigned UUIDs, Clock-driven timestamps, database-enforced uniqueness translated through a constraint-name registry, Testcontainers on the deployed engine, migrations as a discrete deploy step) until the contract tests pass unchanged, then wires configuration and packaging. Use when a project contains that scaffold (api/ contract interfaces, api/dto/ records, red contract tests) and the user asks to implement or complete the service, make the contract tests pass or go green, add persistence, controllers, or migrations behind the contract, or take the scaffold to production.

linkupplatform Bundle

Use when someone has a business goal rather than a single query — "how can I use Linkup?", "enrich my leads", "build a competitor tracker", "research before my meeting", "vet this vendor" — and whenever designing or coding a Linkup-powered product, agent, or pipeline. Turns a goal into a multi-step Linkup workflow (which endpoint, which calls, what feeds the next step, where another tool takes over), grounded in bundled workflow patterns and 18 ready-made recipes that double as integration blueprints.

lithqube Bundle

Use this skill whenever users need to deploy, configure, or secure a NATS JetStream server or cluster — including nats-server.conf configuration, Kubernetes Helm charts, StatefulSets, Docker Compose, multi-region super-clusters with gateways, leaf nodes, TLS/mTLS setup, NKey/JWT authentication, subject-level authorization, or infrastructure sizing. Use this skill even for general "how do I run NATS in production?" questions. Do NOT use for stream/consumer design or code examples (use jetstream-architecture) or troubleshooting/monitoring (use jetstream-operations).

lithqube Bundle

Use this skill whenever users are designing, modeling, or writing code for NATS JetStream — including stream configuration, subject namespace design, consumer types (pull vs push), ack policies, retention policies, delivery guarantees, messaging patterns (fanout, work queue, request-reply), idempotent publishing, exactly-once semantics, or JetStream code examples in Go, JavaScript, or Python. Use this skill even when the user doesn't say "JetStream" explicitly — if they're asking how to build a message queue, event stream, or worker system on NATS, this skill applies. Do NOT use for deployment/clustering/Kubernetes questions (use jetstream-deployment) or troubleshooting/monitoring (use jetstream-operations).

matt1as Skill

Review existing ABAP code against the Clean ABAP rule set in ../CLAUDE.md (loaded on invocation). Use when the user asks to review, audit, or check ABAP for clean-code violations — magic numbers, naming, method shape, error handling, table reads, classes, etc. Outputs a structured report grouped by severity, ATC-checkable findings first. Targets modern ABAP only — BTP ABAP Environment or S/4HANA on-prem in the ABAP Cloud development model.

matt1as Skill

Refactor existing ABAP code to Clean ABAP style without changing behavior. Use when the user asks to refactor, clean up, modernize, or tidy ABAP code. Applies the rule set in ../CLAUDE.md in deterministic passes (naming, declaration, expression, method shape, error, class) and asks before writing back via MCP. Targets modern ABAP only — BTP ABAP Environment or S/4HANA on-prem in the ABAP Cloud development model.

matt1as Skill

Design a complete RAP business object end-to-end and create it via the official SAP ABAP MCP. Use when the user asks to design, scaffold, generate, or create a new RAP BO, OData service, Fiori UI service, or RAP managed/unmanaged behavior. Prefers the MCP x-ui-service / ui-service / webapi-service generators; falls back to hand-crafted CDS/BDEF skeletons when no generator fits. Applies the ABAP Cloud / RAP overlay rules in ../CLAUDE.md (loaded on invocation). Targets BTP ABAP Environment and S/4HANA on-prem in the ABAP Cloud development model.

matt1as Skill

Walk through ATC (ABAP Test Cockpit) violations methodically, grouped by category, with concrete fixes per finding. Use when the user asks to fix, remediate, address, or triage ATC findings on an ABAP object, package, or transport. Refuses pseudo-comment suppressions by default. Applies the rule set in ../CLAUDE.md (loaded on invocation). Targets modern ABAP — BTP ABAP Environment and S/4HANA on-prem in the ABAP Cloud development model.

matt1as Skill

Check an ABAP object or package for clean core compliance — unreleased APIs, direct SELECT on SAP-owned tables, classic constructs disallowed in ABAP Cloud, modifications to SAP standard. Use when the user asks to audit, verify, or check clean core compliance, ABAP Cloud compatibility, released API usage, or extension point usage. Produces a categorised report with hard violations and soft warnings. Read-only — never writes back. Targets BTP ABAP Environment and S/4HANA on-prem in the ABAP Cloud development model.

mikerrr Skill

Teaches and recommends data architecture decisions — choosing among the seven database types, OLTP/OLAP/hybrid designs, sharded relational platforms, data virtualization and federation approaches, Data Vault vs Anchor Model warehouse modelling, BI tool limits, and the delivery process that actually fits data pipeline work. Use when someone asks "which database should we choose?", "explain OLTP vs OLAP", "should we use Data Vault or Anchor Model?", "how do I make our data warehouse flexible?", "is Tableau enough for our corporate reporting?", "why do our data pipeline estimates always slip?", "can we run pipeline development in Scrum?", "what is data virtualization and how does it differ from ETL?", "how do we shard PostgreSQL for both fast inserts and reports?", or "teach me data engineering architecture fundamentals".

minpeter Bundle

Consult the local `hermes` agent as the long-term-memory oracle for minpeter's machines, from inside another coding agent (pi, codex, senpi, Kiro, Claude Code). Use it whenever a task needs context the repo does not contain — infrastructure layout, hostnames/ports/routing, why a past decision was made, prior incidents, cross-repo conventions, deploy/ops procedure — and the instinct is to ask the user: run `hermes -z "<query>"` FIRST, then ask the user only what hermes could not answer. Also use it after an infra change or a long-lived decision, to write that fact back into hermes memory (`-t memory`), and for a second-opinion review of a diff or plan from an agent that has the operational history. Covers query construction, why a failed run can still look like an answer (`--usage-file`), auto-approved tools, and what must never be sent to a hosted model. Query templates: references/queries.md. CLI flags, memory layout, troubleshooting: references/cli.md.

codeboy-bot Bundle

为 Python FastAPI 算法接口工程设计、审查、生成和修复可复现的 Docker/Compose 打包链路。用于创建或更新 Dockerfile、docker-compose.dev.yaml、docker-compose.yaml、.dockerignore、.gitattributes、.env.production、uv/requirements 依赖、原生库或源码补丁、健康检查、start-dev/package-image 脚本、镜像导出归档和跨平台部署；尤其适用于需要以 `.\scripts\start-dev.ps1 .\.env.production` 作为最终构建、启动和健康验收入口的项目。

codeboy-bot Bundle

分析项目实际使用的 Python 第三方包，并在 .docker-deps 中生成仅含依赖的基础镜像 Dockerfile、锁定清单、审计报告及可选的应用运行 Compose 模板。用于准备依赖镜像构建上下文和以只读源码挂载运行项目的静态编排文件；本 skill 不调用 Docker、不启动本机程序、不实际构建或运行镜像。若任务要求把业务源码封装进镜像并完成运行验收，应改用 python-api-docker-packager。

dahls Bundle

Drive a consuming project through the nFTT fine-tuning loop — init, declare config and data, run the data pipeline, train, export, eval, and read results. Use when the user wants to fine-tune, evaluate, export, or inspect a model project driven by nftt, or asks about nftt config or data conventions. Do NOT use when changing nftt itself (developing the tool — that work goes through the tool's own development process, not project patches).

frankjie09 Skill

Runs all builds, tests, and runtime for the anyverse repo inside container agent_dev_nvidia via docker exec, not on the host. Use for colcon, ROS 2, repo scripts, launches, verification; triggers Docker、docker exec、agent_dev_nvidia、容器编译、容器运行、本仓库.

practical-ai-leadership Bundle

This skill should be used when the user asks to "edit my video", "edit my recording in Descript", "run the video edit pipeline", "descript edit my video", "remove retakes from my video", or wants to turn a raw Descript talking-head recording into the finished long-form YouTube edit. Drives the Descript MCP Underlord agent through the validated pipeline - duplicate-first safety, script-diffed retake removal with human cut approval, scoped filler cleanup, Studio Sound and Eye Contact, brand stat cards and lower-third from the brand package, 1.28x zoom punch-ins with Smart Transition glides, verification after every destructive pass. Not for audio podcasts - use podcast-edit for that. Not for generating vertical shorts - use personal-brand-youtube-shorts-generation for that. Not for writing the teleprompter script - use personal-brand-youtube-script-generation for that.

temmax Skill

Use when the user wants the complete delivery pipeline from planning through a reviewed pull request. Do not use for a single planning, implementation, or review stage, and never merge.

aerospike Skill

Work with the Aerospike core database end to end — run a local instance with Docker and verify a first write and read, build or review client code with the official SDKs (Python, Node.js, Go, Java, C#), and design or review a data model, whether from requirements or against a schema that already exists. Covers namespaces, sets, bins, primary key design, TTL and NSUP, collection data types, expressions, secondary indexes, batch and scan workflows, client policies, connection pooling, record sizing, and schema deliverables. Use when the user sets up Aerospike, writes or debugs Aerospike client code, chooses keys or models data for it, reviews an Aerospike schema before building, or evaluates it as a persistent replacement for Redis or Memcached in real-time, low-latency, feature-store, or user-profile workloads. Core database only — not Aerospike Graph, and not cluster operations, sizing, XDR, or backup and restore, which belong to Aerospike Operations documentation.

aerospike Bundle

Getting started with Aerospike Database locally and in application code: run Docker, install official client SDKs (Python, Node.js, Go, Java, C#), verify put/get, and learn defaults. Covers namespaces, ports, TTL/NSUP, and Community vs Enterprise images. Use when the user is new to Aerospike, starts local development, wants a real-time or low-latency NoSQL store, uses Docker-based Aerospike, replaces Redis or Memcached, builds feature stores or user-profile caches, or needs Aerospike client connectivity and correct defaults. Core database only (not Aerospike Graph).

astronomer Skill

Use for Helm chart work - creating charts, modifying existing charts, values design, testing. For the Astronomer airflow-chart repository, this is the umbrella chart whose single dependency is the upstream Apache Airflow chart.

astronomer Skill

Use when writing, editing, reviewing, or running Helm chart tests for the Astronomer airflow-chart repository. Covers pytest patterns, render_chart() usage, sub-chart value nesting under `airflow`, parametrized tests, uv run commands, schema validation, and test organization.

eranw2000 Skill

Cold-start orientation for a project. Gathers git state, open PRs against main, Render deploy health, local Docker container status, OpenSpec change progress, unresolved spec-review Blockers, and pending items from project memory — then synthesizes a "what's the state of this project right now" report. Use when sitting back down on a project after time away ("where was I", "catch me up", "what's the state", "status check"). Read-only, never mutates git, gh, Render, Docker, or project files.

eranw2000 Skill

Ship to production. The single "ship it" verb for any project, handling both PR mode (merges open PRs targeting main) and trunk mode (commits straight to main). Updates README.md + project notes, pushes to all remotes, verifies the auto-deploy (Render / Vercel / etc.), and rebuilds the local Docker container so localhost matches prod. Triggers on "release", "ship it", "deploy", "ship to prod", "merge and release", "push to prod".

eranw2000 Skill

Run the codified three-reviewer loop on a diff or PR: author adversarial per-agent prompts pointing at the riskiest spots, launch code-reviewer + deploy-guard + pr-validator in parallel, reproduce every finding by execution before fixing, prove each fix with a non-vacuous regression test, and post the PR verdict comment that /release gates on. Use before shipping, or when the user says 'review round', 'run the reviewers', 'full review pass', or wants the pre-release review loop. For a spec-anchored review against your requirements or spec docs, run a spec-review pass instead.

eranw2000 Skill

Snapshot in-progress work as a GitHub PR and rebuild the local Docker container so you can test the feature branch on localhost. Does NOT merge, does NOT touch production, does NOT update README or project notes (premature, that happens at /release time). Use when you want to capture a checkpoint of feature work, open a PR for review, and test locally before deciding it's ready to ship. Triggers on "checkpoint", "open a PR", "draft a PR", "snapshot this", "let me test this locally".

eranw2000 Skill

Post-deploy smoke test of a live production service. Verifies the deploy landed (live commit matches what /release pushed), hits the health endpoint and 2-4 key user-facing endpoints, checks the DEBUG-off 404 behavior, and scans recent host logs for tracebacks and 5xx. Read-only, never mutates the service; reports pass/fail per check and recommends rollback or fix-forward on failure. Use after /release, or when the user says "production smoke", "smoke test prod", "verify the deploy", "is prod healthy", "check the live site after the release".

nvidia-bionemo Bundle

Agent runbook for first-time Proteina-Complexa setup, dotenv configuration, runtime activation, model-weight installation, GPU preflight, and environment validation. Use for "set up complexa", "install complexa", "complexa init", "complexa download", checkpoint installation or status, UV versus Docker selection, and fresh checkouts. SKILL.md invokes the first-party CLI; bundled executables safely inspect local readiness and write a private setup manifest.

nvidia-bionemo Bundle

Use this skill whenever the user wants to add, register, edit, list, show, or validate a Proteina-Complexa design target for any pipeline — protein binder (default), ligand binder, or AME / enzyme scaffolding. Triggers include "add a target", "define a new target for binder design", "register a hotspot", "set up a PDL1 binder target", "ligand binder pocket", "SMILES target", "AME task", "enzyme motif", "M0024_1nzy", "complexa target add", "complexa target show", "configure target X", "what targets are available", "where do hotspots live", "what does target_input mean", "chain-spec syntax", "binder length range", or any question about `configs/targets/{,ligand_}targets_dict.yaml` and `configs/design_tasks/ame_dict_v2.yaml`. Also covers `complexa validate target`. This is the only skill that touches the three targets dict files.

pnx2003 Bundle

Research, map, compare, design, reproduce, or evaluate multi-agent systems across classical MAS, game theory, multi-agent reinforcement learning, LLM agent teams, debate, social simulation, agent protocols, and enterprise platforms. Use for literature reviews, related-work sections, paper or code surveys, framework selection, architecture design, benchmark construction, failure analysis, scaling studies, reproduction plans, or questions about work from OpenAI, Anthropic, Google, Microsoft, AWS, Salesforce, IBM, Alibaba, and open-source agent ecosystems.

podman-desktop Skill

Guides writing and maintaining Playwright E2E tests for the bootc Podman Desktop extension. Covers the webview-aware test framework, extension lifecycle management, Page Object Models, and spec file patterns. Triggers when creating or modifying E2E spec files, building page object models, debugging Playwright failures, or asking about the test framework.

rodri-oliveira-dev Skill

Use esta skill ao alterar a aplicacao .NET deste repositorio, incluindo API, Business, Data, EF Core, autenticacao, configuracao ou testes relacionados. Nao use para mudancas apenas em governanca, CI/CD puro ou documentacao sem impacto tecnico.

rpeeyush Bundle

Conduct realistic technical and behavioral mock interviews, primarily for cybersecurity/security-engineering roles (CrowdStrike, Zscaler, Splunk, Windows, PowerShell, cloud security, etc.), though the framework generalizes to any topic, resume, or job description. Automatically detects mode from what the user provides — a topic name, a pasted job description, a resume, a company name, or a custom weighting spec — and conducts a one-question-at-a-time interview with follow-ups, scoring, and a final readiness report. Use this whenever the user says things like "interview me on X", "quiz me on X", "ask me questions about X", pastes a job description and wants to prep, wants mock interview practice, wants to be tested/grilled on a topic, or wants an interview readiness/gap analysis against a JD or resume. Trigger even if they don't use the word "interview" — "grill me on Zscaler ZPA" or "test my Windows internals knowledge" both apply.

s3644 Skill

Full academic research pipeline orchestrator. Use when the user wants to go through the complete research-to-publication workflow: research → write → integrity check → review → revise → re-review → finalize. Coordinates deep-research, academic-paper, and academic-paper-reviewer. Triggers: full pipeline, complete research paper, research to publication, end-to-end paper, I want to write a complete research paper, 完整研究流程, 從研究到發表.

vodoslopper Bundle

Run and manage virtual machines with the local `vml` CLI. Use when an agent needs to create or run a VM, inspect VM state, start or stop VMs, execute commands over SSH, transfer files, discover or add cloud images, manage VM images, use graphical or headless-automated displays, access the QEMU monitor, or remove and clean up VMs.

vodoslopper Bundle

Create, inspect, edit, and troubleshoot Lineup orchestration manifests (`LM.toml` and `LM.local.toml`) for tasks running on host, SSH, Docker, Podman, Incus, or VML workers, with a strong preference for reusable Lineup modules over ad hoc shell commands. Use for Lineup manifest structure, built-in or project modules, workers, tasklines, tasksets and dependencies, variables and Tera templates, networks, storages, file transfers, retries, conditional execution, nested manifests, cleanup, and resume behavior.