DevOps & Infra

genkovich Skill

Use to classify a feature into XS/S/M/L/XL and write docs/features/{slug}/.size plus the pipeline route docs/features/{slug}/.route (quick|standard|full) so later skills know how much of each artifact to produce and how handoffs resolve skips. Triggers on "classify size", "feature size", "is this XS or M for {slug}", "size {slug}", "change route", "/sdd:classify-size {slug}", "класифікуй розмір {slug}", "який розмір фічі", "XS чи M". Asks four AskUserQuestion (PR count / time / new module-API-migration / breaking changes), maps to a size class via the shared size matrix, derives the default route (XS/S→quick, M→standard, L/XL→full), confirms size + route in ONE question, and writes the one-line .size and .route files — the source of truth; the feature_size: frontmatter mirrors in spec.md and sad.md are re-synced to it on every (re)classification.

genkovich Bundle

Use to create and tune the per-project settings file `.claude/sdd.local.md` — the one place that decides how deeply the pipeline interviews you, which model tier its judgment agents run at, how strict the TDD gates are, how tasks execute and commit, and what language your documents are written in. Triggers on "config", "settings", "configure sdd", "tune the pipeline", "change the judgment model", "set the interview depth", "write documents in Ukrainian", "/sdd:config", "налаштування", "налаштуй sdd", "зміни модель", "глибина опитування", "мова документів". Creates the file with documented defaults FIRST (so you have a working config before answering anything), reads what already differs from the defaults, then asks six grouped questions and patches only the keys you confirm — preserving your comments, key order and unknown keys. Never touches the pipeline's artifacts; the settings file is gitignored, only the .gitignore patch is committed.

genkovich Bundle

Use to establish the repo's architecture map the rest of the pipeline reads. Two modes: on an EXISTING codebase it scans once and persists what's there; on an EMPTY/greenfield repo it runs a short, level-adaptive foundation session — picks the stack / folder structure / data approach / conventions WITH you (defaults-heavy), fixes them as the foundation + foundational ADRs, and emits a scaffold tasks.json that the scaffold skill materializes into a real skeleton. Triggers on "survey the codebase", "map the architecture", "set up a new project", "bootstrap the foundation", "/sdd:survey", "вивчи кодову базу", "карта архітектури", "новий проєкт", "заклади фундамент". Output: docs/architecture-map.md (+ adr/ + scaffold tasks.json on greenfield). Records reflects_commit for staleness; reads, never overwrites, an authored architecture doc.

loulanyue Skill

Playwright E2E test kalıpları, Page Object Model, yapılandırma, CI/CD entegrasyonu, artifact yönetimi ve kararsız test stratejileri.

dreamers-laboratory Bundle

Plan, provision, deploy, or audit a guarded AWS static website using S3, ACM, Route53, and CloudFront. Use when the agent is asked to make a static site live on AWS, create or review an S3/CloudFront/ACM/Route53 setup, publish a local static site, debug a static-site AWS deployment, or prepare a safe deployment plan with rollback. Includes account-verification guardrails, read-only-by-default AWS CLI handling, and target-aware-security requirements for public cloud/DNS changes.

dreamers-laboratory Skill

Apply an adversarial security posture to infrastructure, server, database, DNS, firewall, credential, deployment, and automation work. Use when the agent is changing or reviewing anything exposed to networks or other users, handling secrets, creating public URLs, configuring SSH/sudo/systemd/databases/cloud/DNS, or when the user says security is important, the host is a target, or attack vectors must be considered.

dreamers-laboratory Skill

Disciplined git, release, and deployment workflow. Use when the agent is asked to commit, push, branch, merge, release, deploy, publish, clean up git state, or prepare production web changes; enforces main-first work, semantic version increments when present, local testing before deploy, live testing after deploy, and neutral branch/commit naming.

dreamers-laboratory Skill

Plan, provision, deploy, migrate, or audit a static site on Cloudflare (Pages, DNS, Redirect Rules, Workers). Use when the agent is asked to host a static site or SPA on Cloudflare Pages, move a domain's DNS from Route53 to Cloudflare, set up a Pages custom domain, build redirects between hosts, retire an S3/CloudFront/ACM stack in favour of Pages, or debug a Cloudflare-hosted site that serves stale content. Includes account guardrails, an email-safe DNS migration gate, and the service-worker and cache traps specific to Pages.

dreamers-laboratory Skill

Rigorously verify web application changes before claiming they are done. Use when the agent builds, debugs, reviews, deploys, or regression-tests any web UI, browser flow, API-backed page, or full-stack web feature and must prove behavior with multiple checks such as code audit, targeted tests, Playwright/browser automation, screenshots, raw API probes, and post-deploy live verification.

shepnerd Bundle

Extract useful methods, patterns, writing, code, or UI ideas from one or more external references, compare them with the current project’s goals and capabilities, and propose safe, checkpoint-aware adaptations. Implement only after the user selects what to adopt and explicitly authorizes changes; do not use for ordinary CI/CD work.

nhutnguyengkimvn Skill

Standalone Form.io order-services form creator. Reads a lab PDF, classifies its fields, and builds + saves the Form.io JSON schema in the dashboard builder — without running the full import-lab-recform pipeline. Use when W01–W03 are already done and only the Form.io form needs to be created or re-created for a recform.

nhutnguyengkimvn Bundle

Imports Lab Req Forms into the DNA Insights admin dashboard from explicit PDF paths. Invoked as `import-lab-recform <path1.pdf> [<path2.pdf> ...]`. Use this skill whenever the user says things like "import lab recform <file>.pdf", "run import-lab-recform on these PDFs", or "create medical req forms from these files". The skill validates every supplied path, asks for the dashboard URL, reads each PDF's content to detect its Test Type + Lab, then runs the per-recform pipeline (create Medical Specialty if missing → create ReqForm + sync CSV → flatten PDF + upload → create Form.io order services form) for each PDF in turn, pausing for user confirmation before moving to the next one.

nhutnguyengkimvn Bundle

Generates the AnnotsJSON for a lab PDF form by running the CommonForms pipeline: ML field detection → key assignment → Claude visual verification. Outputs a JSON array of annotated form fields (AnnotsJSON format) ready to be pasted into the medicalpdf admin page. Called from import-lab-recform W05 when AnnotsJSON is null, or standalone.

loulanyue Skill

AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.

loulanyue Skill

Playwright E2E 测试模式、页面对象模型、配置、CI/CD 集成、工件管理和不稳定测试策略。

loulanyue Skill

Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies.

loulanyue Skill

Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies.

loulanyue Skill

Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies.

loulanyue Skill

Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies.

loulanyue Skill

AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.

loulanyue Skill

Yerel geliştirme, konteyner güvenliği, ağ, volume stratejileri ve multi-servis orkestrasyon için Docker ve Docker Compose kalıpları.

loulanyue Skill

Docker and Docker Compose patterns for local development, container security, networking, volume strategies, and multi-service orchestration.

loulanyue Skill

AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.

loulanyue Skill

Docker and Docker Compose patterns for local development, container security, networking, volume strategies, and multi-service orchestration.

loulanyue Skill

AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.

loulanyue Skill

AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.

loulanyue Skill

用于本地开发的Docker和Docker Compose模式，包括容器安全、网络、卷策略和多服务编排。

loulanyue Skill

Docker and Docker Compose patterns for local development, container security, networking, volume strategies, and multi-service orchestration.

loulanyue Skill

Docker and Docker Compose patterns for local development, container security, networking, volume strategies, and multi-service orchestration.

loulanyue Skill

Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications.

loulanyue Skill

Deployment iş akışları, CI/CD pipeline kalıpları, Docker konteynerizasyonu, sağlık kontrolleri, rollback stratejileri ve web uygulamaları için üretim hazırlığı kontrol listeleri.

loulanyue Skill

Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications.

loulanyue Skill

RFC-driven multi-agent DAG execution pattern with quality gates, merge queues, and work unit orchestration.

loulanyue Skill

RFC-driven multi-agent DAG execution pattern with quality gates, merge queues, and work unit orchestration.

loulanyue Skill

RFC-driven multi-agent DAG execution pattern with quality gates, merge queues, and work unit orchestration.

loulanyue Skill

RFC-driven multi-agent DAG execution pattern with quality gates, merge queues, and work unit orchestration.