DevOps & Infra

ricmmartins Skill

Audit Azure environment for compliance and governance posture. Checks Azure Policy, RBAC, tagging, resource locks, naming conventions, and regulatory alignment. Use when asked about compliance, governance, audit readiness, or policy violations.

ricmmartins Skill

Monitor and improve Microsoft Defender for Cloud Secure Score. Tracks score trends, identifies quick wins to improve the score, checks Defender plan coverage, and highlights critical security recommendations. Use when asked about secure score, security posture, Defender status, or security improvements.

ricmmartins Skill

Run a Well-Architected Framework (WAF) review against Azure resources in scope. Use when asked about best practices, architecture review, WAF assessment, or pillar compliance (Reliability, Security, Cost, Operational Excellence, Performance Efficiency).

ricmmartins Skill

Assess Azure governance maturity for Digital Natives and startups. Detects the most common anti-patterns from the "Digital Natives on Azure" series: incomplete Service Health alerts, flat subscription topology without Management Groups, excessive RBAC (everyone is Owner), missing budget alerts, no Managed Identity usage, unprotected web apps without WAF/DDoS, and missing environment separation. Produces a scored maturity report (Foundation → Developing → Established → Optimized). Use when asked about startup readiness, governance maturity, "are we production-ready?", or before a customer security questionnaire.

rossoctl Bundle

Bring up a local "rossoctl cortex" — an AuthBridge plugin pipeline that hosts a command (e.g. Claude Code) via `rossoctl authbridge exec`. Guides the user through choosing plugins, generates the authbridge YAML config, and runs the agent behind it. Specializes in per-agent LiteLLM usage/budget tracking where each agent's spend is isolated by an environment variable. Use /byo-rossoctl-cortex.

igmarin Skill

Use when bootstrapping a Rails project: context, onboarding, CI. Trigger words: setup project, rails new, CI/CD, dev environment, Gemfile.

cristhianzl Bundle

Apply platform-agnostic engineering rules so Langflow code, tests, and Docker images behave identically on Ubuntu, macOS (Intel x86_64 + Apple Silicon arm64), and native Windows — plus the linux/amd64 + linux/arm64 Docker matrix and the separate Langflow Desktop distribution for Windows and macOS. Use when writing or reviewing code that touches the filesystem, shell, subprocess, encoding, time, paths, native dependencies, the cross-platform-test workflow, or Docker — or when the user mentions Windows, macOS, Linux, ARM, Desktop, "works on my machine", or Docker in a Langflow context.

promovaweb Bundle

Projetar e revisar CI/CD, artefatos, releases, promoções, migrations, rollout, rollback e supply chain. Use para pipelines, workflows, ambientes, deploys ou estratégia de entrega; use também para escolher entre rolling, blue-green, canary ou feature flag; não publique, promova ou altere produção sem autorização explícita, e para a métrica que decide o rollout use `$specsfy-specialist-observability`.

rohankhullar24-oss Bundle

Read this skill before the first step of any request to do something in an app on the person's own computer (Notes, Finder, System Settings, any desktop app), to look at their screen, or for "computer use". Computer use (desktop control) lets Claude take screenshots of the person's desktop and control it with clicks, typing and scrolling through the Claude desktop app; its tools are named mcp__computer-use__* when the session runs in the desktop app and mcp__remote-devices__computer_* when a cloud session is linked to the person's computer; before a conversation is linked there may be no such tools, only an enable__mcp__remote-devices__computer tool, which links it. It covers getting linked, picking the right tool, the access flow, and what to do when computer use is off or out of reach. It is not for websites, which go through Claude in Chrome or the built-in browser and their own skills.

aradotso Skill

CLI and skills for building, evaluating, and deploying AI agents on Google Cloud's Gemini Enterprise Agent Platform using ADK

giordanorogers Bundle

Use when committing, pushing, deploying, or changing AgentNet/coralbots red-team range code, Helm charts, Kubernetes manifests, live services, rollout scripts, or range handoff documentation.

giordanorogers Bundle

Use before any deployment, rollout, Helm upgrade, kubectl apply/replace/restart, live ConfigMap patch, release, or beta/main environment change from a git repo. This skill requires Codex to fetch and integrate origin/main first, check for merge conflicts including dirty local changes, run verification, and block deployment when main cannot be merged cleanly or tests fail.

hassancs91 Skill

Generates one expressive narration MP3 per scene for an English storybook, using the ElevenLabs MCP (text_to_speech). Reads {slug}_scenes.json (from scene-splitter), proposes a warm storyteller voice, drafts the narration text per scene (optionally with Eleven v3 audio tags for emotion), lets the user review, then generates one MP3 per scene saved as {slug}_part_NN.mp3 so it pairs by index with the scene's image. Use this skill whenever the user wants to narrate a story, generate per-scene audio, voice a storybook, create read-along narration, or produce TTS for the storybook pipeline. Trigger on phrases like "narrate this story", "generate the audio", "voice the storybook", "make the narration", "read this story aloud", or whenever scenes.json exists and the user wants spoken audio. Requires the ElevenLabs MCP connected.

hongikarchi Bundle

One-shot "clean up the whole Rhino file" pipeline — runs the dedup + geometry-cleanup sibling skills, then purges unused block definitions / empty groups / empty layers, then assigns a white matte plaster material (named after the layer) to every layer that has no material. Non-destructive diagnose first at every stage, confirms scope, then applies. Trigger when the user wants to clean / tidy / purge / finalize the entire Rhino document (not just the current selection), assign missing materials, or prep a file for hand-off. Fire on Korean or English requests, e.g. "라이노 정리", "파일 전체 정리", "clean rhino", "clean up the whole file", "퍼지", "purge", "안 쓰는 레이어/블록 정리", "재질 없는 레이어 흰색으로", "assign white plaster to layers without material". For selection-only curve work use the sibling skills `clean-similar-curves` / `clean-geometry` directly.

hassancs91 Skill

Step 2 of the AI Video Editor pipeline — build the visual beats (Remotion TSX shots) over a project's master cut and bake a composited preview. Use when the user wants to add/edit overlays or full-screen animation segments, "make a shot / beat", implement an edit plan or a v2 update, retime a beat to the narration, re-render shots, or re-bake the video-N preview in this repo. Covers reading the plan + edited-transcript + brand + reusable kit, authoring shots library-first, syncing reveals to word times, updating timeline.json (cutaway vs overlay), rendering, verifying by screenshot, and baking with tools/bake.py. Defers raw TSX authoring rules to vidtsx-2d-generator and the cut itself to clean-cut.

hassancs91 Skill

Step 1 of the AI Video Editor pipeline — turn raw talking-head footage into a clean master cut. Use when the user wants to "clean cut", "cut the raw footage", "remove filler / dead air / bad takes", "tighten the pacing", produce cuts.json, run the cut editor, or render a cleaned preview/master for a video-N project in this repo. Covers audio extraction, AssemblyAI transcription, authoring cuts.json (keeps/cuts/fluff categorized), the cut policy (content-aggressive, pause-natural ~0.5s), QA + review docs, the local cut-editor UI, tight/natural previews, the final 4K60 render, and producing edited-transcript.json as the handoff to /make-tsx. Not for building TSX overlays (that is /make-tsx) or the raw TSX authoring rules (that is vidtsx-2d-generator).

hassancs91 Skill

Voice/audio cleanup step of the AI Video Editor pipeline — diagnose a video's background noise, pick the right denoise method, and produce a cleaned master (voice isolated, levels preserved, video stream copied). Use when the user wants to "clean the audio / voice", "remove background noise", "denoise", "isolate voice", fix outdoor/room/water/hum/hiss noise, run ElevenLabs Voice Isolator or local RNNoise, A/B denoise methods, or produce a cleaned master for a video-N in this repo. Covers diagnosing the noise (spectrogram + levels), choosing eleven vs rnnoise by noise type, the sample A/B, tools/clean_voice.py, preserving levels (RMS-match, not LUFS), and rewiring the pipeline to the clean master. Not the SFX/music mix (that is /suggest-sfx + the final-mix step) and not the cut (that is /clean-cut).

hassancs91 Skill

Step 4 of the AI Video Editor pipeline — the SFX pass. Analyze a video's beats + narration and propose tasteful sound effects synced to them, drawing from (and growing) a shared, reusable SFX library, then render an SFX-mixed audition preview. Use when the user wants to "add SFX / sound effects", "suggest sfx", "score the transitions", "sound-design this beat", generate/source sound effects, build or extend the sfx library/catalog, author or audit a sfx-plan, or mix SFX over a video-N preview in this repo. Covers reading timeline + edited-transcript + brand §10, the library-first flow, generating misses with the ElevenLabs Sound Effects API, the per-video sfx-plan.json, the hard user-audit gate, and mixing with tools/mix_sfx.py (light voice ducking). Not the music bed (that is the final-mix step) and not the visual beats (that is /make-tsx).

merit-systems Skill

Upload files to the cloud and get shareable public URLs using agentupload.dev (x402 micropayments). Use when the user asks to upload a file, share a file via URL, host a file, make a file publicly accessible, or needs a download link for any file. Triggers on phrases like "upload this", "share this file", "get me a link", "host this file", "make this downloadable", or any request to put a local file on the internet.

pupok462 Bundle

Run an end-to-end GEO visibility measurement through a real AI interface, persist the captures, and return a portable JSON run artifact plus optional PDF/dashboard outputs. Use automatically on an explicit request to measure a brand's AI-search visibility, and as a composable data-collection step inside another agent workflow; the user should not have to launch the pipeline or dashboard manually.

pupok462 Bundle

Run an end-to-end GEO visibility measurement through a real AI interface, persist the captures, and return a portable JSON run artifact plus optional PDF/dashboard outputs. Use automatically on an explicit request to measure a brand's AI-search visibility, and as a composable data-collection step inside another agent workflow; the user should not have to launch the pipeline or dashboard manually.

pupok462 Bundle

Run an end-to-end GEO visibility measurement through a real AI interface, persist the captures, and return a portable JSON run artifact plus optional PDF/dashboard outputs. Use automatically on an explicit request to measure a brand's AI-search visibility, and as a composable data-collection step inside another agent workflow; the user should not have to launch the pipeline or dashboard manually.

pupok462 Bundle

Run an end-to-end GEO visibility measurement through a real AI interface, persist the captures, and return a portable JSON run artifact plus optional PDF/dashboard outputs. Use automatically on an explicit request to measure a brand's AI-search visibility, and as a composable data-collection step inside another agent workflow; the user should not have to launch the pipeline or dashboard manually.

stackhawk Bundle

Use when the user wants to WIRE HawkScan into a CI/CD pipeline config file — triggers on "set up hawkscan in CI", "add stackhawk to my pipeline", "scan in CI", "configure github actions / gitlab / jenkins / circleci for hawkscan", "wire hawkscan into ci/cd", or any provider-named variant. Provider-agnostic: detects the CI system from repo files, edits the pipeline file in place to add a HawkScan job, prompts for HAWK_API_KEY storage in the CI's native secrets store (or an approved external manager), and wires commit-SHA + branch traceability. If no local stackhawk.yml exists yet, still trigger and route the local-config work to the hawkscan skill. Do NOT trigger for: documentation-only changes (e.g. editing a README about CI scanning); informational or research questions ("what CI providers does HawkScan support?"); or running / performing a scan — a local scan is the hawkscan skill, whereas this skill only edits CI pipeline config. Explicit trigger only; no autonomous code-change hook.

tuya Bundle

Configure device authorization credentials (UUID, AuthKey, PID) and network provisioning for TuyaOpen devices. Use when the user mentions device auth, authorization, UUID, AuthKey, tuya_config.h, provisioning, pairing, or cloud connection. 设备授权、授权码、配网、UUID、AuthKey、云连接。

shad0wmazt3r Bundle

Use recursive bug-bounty recon to discover, verify, and pivot domains, hosts, IPs, cloud assets, and JS signals into the next testing phase.

dddpaul Bundle

Generate detailed architectural descriptions of IT systems from short prompts. Produces structured output with overview, components list, connections/integrations, and ASCII diagrams with annotated arrows. Use when user asks to describe, explain, or document architecture of any IT system - specific platforms (Camunda, Kafka, Kubernetes), cloud services (AWS, GCP, Azure), databases, microservices, or custom systems.

just1cup Bundle

Use this skill before implementing, modifying, reviewing, or suggesting code when the work should be grounded in official vendor documentation and secure coding guidance. It discovers the repository architecture and technologies, builds and reuses a persistent Reference Set of official documentation findings, and applies official docs, OWASP Top 10, OWASP ASVS, OWASP Proactive Controls, OWASP API Security Top 10, language best practices, framework best practices, vendor security guides, and secure-by-default principles. Trigger for code changes, architecture changes, dependency usage, authentication, authorization, cryptography, payments, API design, security reviews, hardening, validation, data handling, infrastructure, CI/CD, or any request where current official implementation guidance matters.

pavelt-papaya Skill

Deploys a service by updating the image.tag in Helm values YAML files inside one of two CI repos (devops-k8s-resources for Shine, playon-do-argo for Playon), creating a feature branch, committing, and pushing. The target CI repo is chosen automatically from the source project's root folder name (playon-* prefix → Playon, otherwise Shine). Use this skill immediately and automatically whenever the user writes any message starting with "deploy" followed by a version number or a service name and version — for example "deploy 1.2.3", "deploy 1.2.3 to dev", "deploy 1.2.3 to stage", "deploy 1.2.3 to prod", "deploy users 1.2.3", "deploy version 1.2.3". Do not ask for clarification, just execute the workflow.

pavelt-papaya Bundle

Clones a Shine `backend-<service>-service` repo into its `playon-backend-<service>-service` counterpart by mirroring the source files and applying the infra/project/NuGet transformations needed for the playon edition (CI repository name prefix and per-csproj NuGet `PackageId`). Business logic is left untouched. Use this skill immediately and automatically when the user says "clone to playon", "playon clone <service>", "create playon repo for <service>", "playon-ify <service>", or "playonize <service>". Do not ask for clarification, just execute the workflow.

pavelt-papaya Bundle

Port-forward a Kubernetes service pod to localhost on the Shine or Playon EKS clusters, or stop an active forward. Use immediately and automatically when the user says "port-forward", "forward", "pf", or "connect to" followed by a service name — e.g. "port-forward media", "pf identity-management", "forward media to 5200", "connect to graphql-gateway", "pf playon users", "pf playon-dev media", "forward identity-management on playon-staging". Also use when the user says "stop forwarding", "stop forward", "kill forward", or "disconnect" followed by a service name or "all". Do not ask for clarification, just execute the workflow.

pavelt-papaya Skill

Fixes AWS deploy crash "Could not load file or assembly 'Microsoft.Extensions.DependencyModel'" in Shine/Playon .NET services. Root cause is Dockerfile `dotnet publish` of the whole solution into one flat out/ folder — test projects (coverlet.collector) overwrite the host's DependencyModel. Fix by setting IsPublishable false on test projects. Use immediately when this exception, assembly-not-found for DependencyModel, or a coverlet/test-publish version clash appears. Do not add a Host PackageReference for DependencyModel.

vgtitov Bundle

Администрирование и DevOps 1С:Предприятие 8.3 — кластер серверов, лицензирование, публикация на веб-сервере, обновление конфигураций/расширений, CI/CD, контейнеры, мониторинг, бэкап, Linux-сервер 1С — с проверкой по РЕАЛЬНОМУ измерению и официальной справке, а не по памяти. Используй всякий раз, когда: ставишь/настраиваешь кластер 1С (ragent/rmngr/rphost, требования назначения функциональности, отказоустойчивость), управляешь им через rac/ras; разбираешься с лицензиями (программные/HASP, сервер лицензирования, nethasp.ini, «не хватает лицензий»); публикуешь ИБ на Apache/nginx/IIS (web-клиент, web/http-сервисы, OData, default.vrd) и ловишь ошибки публикации; обновляешь типовую/нетиповую конфигурацию или расширение (режим поддержки, сравнение-объединение, cf/cfu/cfe, динамическое обновление и его риски); строишь CI/CD для 1С (GitLab CI/Jenkins, OneScript, gitsync, EDT vs Хранилище, SonarQube+АПК, Vanessa-тесты); заворачиваешь 1С в Docker/Kubernetes (образы сервера/RAS, лицензирование в контейнере, 1С Fresh); на

18816132863 Bundle

Generate and edit professional PPT presentations. Generation uses a 3-stage workflow: gather information & confirm writing approach, generate structured outline, generate PPT via cloud service & deliver. Editing operates directly on existing PPTX files via XML-level manipulation (unpack, modify, repack). TRIGGER when user asks to: generate PPT, create slides, make presentation, edit/modify PPT, adjust slide content/layout, delete/add/reorder slides, use PPT as template, 生成PPT, 做PPT, 制作幻灯片, 做演示文稿, 编辑/修改PPT, 基于模板修改. Supports both document-based and web-search-based content sourcing for generation.

18816132863 Bundle

部署网页应用到云服务器中。当用户需要部署网页应用时，使用本 Skill。

18816132863 Bundle

给网页应用接入云数据库的额外能力。端到端流程：云数据库服务后端应用创建 → 数据库设计 → 前端对接。当用户明确提到需要支持多用户共用数据库实例或者需要部署网站（且不需要端侧能力）时，你可以利用本 skill，如果网页应用需要支持端侧能力（比如相机、端侧数据库等），那就一定不能使用本 skill。如果用户既要多用户共用数据库实例、网站部署，又要支持端侧能力，本 skill 不支持，并告知用户无法支持该请求