DevOps & Infra

loulanyue Skill

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

loulanyue Skill

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

loulanyue Skill

基于RFC驱动的多智能体DAG执行模式，包含质量门、合并队列和工作单元编排。

loulanyue Skill

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

loulanyue Skill

Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.

loulanyue Skill

Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.

loulanyue Skill

Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.

loulanyue Skill

Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.

loulanyue Skill

LLM API 使用成本优化模式 —— 基于任务复杂度的模型路由、预算跟踪、重试逻辑和提示缓存。

loulanyue Skill

Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.

leynier Bundle

Validate and deploy this generated Python project using its selected target, portable Docker base, and optional Pulumi or Terraform configuration. Use for deployment preparation, local container checks, cloud previews, release rollout, health verification, or deployment troubleshooting.

barastrong Bundle

Use when conducting IT audits, evaluating IT controls, assessing IT risks, or reviewing IT governance and compliance. Trigger phrases: "IT audit", "IT controls", "IT risk assessment", "ITGC", "IT general controls", "SOX IT", "IT audit findings", "control testing", "change management audit", "access control audit", "IT governance audit", "COBIT audit", "cybersecurity audit", "cloud audit", "IT audit report".

barastrong Bundle

Use when building IoT systems, device connectivity, IoT platform integration, sensor data pipelines, or edge computing. Trigger phrases: "IoT", "Internet of Things", "MQTT", "IoT platform", "sensor data", "edge computing", "AWS IoT", "Azure IoT", "device management", "OTA update", "telemetry", "SCADA", "industrial IoT", "IIoT", "device shadow", "IoT gateway", "Raspberry Pi", "Arduino IoT", "LoRaWAN".

barastrong Bundle

Use when building data pipelines, ETL/ELT workflows, data warehouse design, streaming data infrastructure, or data platform engineering. Trigger phrases: "data pipeline", "ETL", "ELT", "data warehouse", "dbt model", "Airflow DAG", "Spark job", "Kafka stream", "data ingestion", "Snowflake", "BigQuery", "Redshift", "data lake", "data platform", "schema design", "data modeling", "data quality", "data orchestration".

barastrong Bundle

Use when designing and implementing security infrastructure, hardening systems, building security automation, or integrating security into CI/CD (DevSecOps). Trigger phrases: "security engineering", "DevSecOps", "security architecture", "IAM design", "zero trust", "encryption implementation", "secrets management", "SAST", "DAST", "container security", "supply chain security", "security automation", "WAF configuration", "PKI", "certificate management", "security hardening".

barastrong Bundle

Use when managing ML infrastructure lifecycle, CI/CD for ML models, LLM operations, model deployment automation, or AI platform engineering. Trigger phrases: "MLOps", "LLMOps", "model CI/CD", "model deployment", "model versioning", "ML platform", "LLM fine-tuning pipeline", "RAG pipeline", "LLM serving", "vector database", "prompt management", "model governance", "AI infrastructure", "GPU infrastructure", "Kubernetes ML".

barastrong Bundle

Use when designing, building, or integrating APIs and system integrations — REST API design, GraphQL schemas, gRPC services, webhook handlers, API gateways, third-party API integration, or ETL pipelines between systems. Trigger phrases: "API design", "integration", "webhook", "API gateway", "OpenAPI spec", "GraphQL schema", "gRPC proto", "third-party API", "data sync", "ETL pipeline", "middleware integration", "iPaaS", "API versioning", "rate limiting".

barastrong Bundle

Use when building ML systems, training pipelines, model serving infrastructure, or productionizing ML models at scale. Trigger phrases: "ML pipeline", "model training", "model serving", "inference API", "feature store", "model registry", "training job", "GPU training", "PyTorch model", "TensorFlow serving", "ONNX", "TorchServe", "Triton", "model optimization", "quantization", "distributed training", "ML platform".

open-fox Skill

Create and initialize a new TanStarter SaaS project from the official template. Use when a user asks to create, scaffold, initialize, or deploy a TanStarter project, including provisioning Cloudflare D1, R2, and KV resources, configuring an optional custom domain, creating a GitHub repository, or enabling Waffo test payments.

barastrong Bundle

Use when building automated test suites, UI test automation, API test automation, CI/CD test integration, or test framework design. Trigger phrases: "test automation", "automated testing", "Selenium", "Playwright", "Cypress", "WebdriverIO", "automated regression", "UI automation", "API test automation", "test framework", "pytest", "JUnit", "test CI/CD", "end-to-end test", "BDD", "Cucumber", "Gherkin".

barastrong Bundle

Use when working with cloud platforms, cloud architecture, cloud migrations, serverless, or managed cloud services. Trigger phrases: "AWS", "Azure", "GCP", "cloud architecture", "cloud migration", "serverless", "Lambda", "S3", "EC2", "CloudFormation", "cloud cost", "VPC", "cloud networking", "managed services", "cloud security", "multi-cloud", "cloud native", "CDK", "cloud storage", "cloud compute".

barastrong Bundle

Use when setting up CI/CD pipelines, containerization, infrastructure automation, deployment workflows, or bridging development and operations. Trigger phrases: "CI/CD", "pipeline", "Docker", "Kubernetes", "Terraform", "Ansible", "deployment automation", "GitOps", "GitHub Actions", "Jenkins", "ArgoCD", "Helm chart", "container orchestration", "infrastructure as code", "blue-green deployment", "canary deployment", "DevOps".

s0ld13rr Skill

CI/CD gotchas — default creds, instant-RCE paths, secret leaks in logs. Use when a CI/CD service is found. Triggers - Jenkins, GitLab, ArgoCD, Vault, pipeline, runner token.

s0ld13rr Skill

Cloud IAM privesc paths and metadata endpoints per provider. Load when the target is cloud or you obtain cloud creds/metadata. Triggers - AWS/GCP/Azure, IAM, S3/blob, 169.254.169.254, access key.

s0ld13rr Skill

Docker/Kubernetes attack techniques — exposed API abuse, container escape, RBAC/privileged-pod issues, secret theft. Use when a container/orchestration surface is found. Triggers - Docker 2375/2376, Kubernetes API 6443, kubelet 10250, etcd 2379, /version, privileged pod, service-account token, docker.sock.

samin12 Bundle

Chief Security Officer mode. Infrastructure-first security audit: secrets archaeology, dependency supply chain, CI/CD pipeline security, LLM/AI security, skill supply chain scanning, plus OWASP Top 10, STRIDE threat modeling, and active verification. Two modes: daily (zero-noise, 8/10 confidence gate) and comprehensive (monthly deep scan, 2/10 bar). Trend tracking across audit runs. Use when: "security audit", "threat model", "pentest review", "OWASP", "CSO review".

samin12 Bundle

Configure deployment settings for /land-and-deploy. Detects your deploy platform (Fly.io, Render, Vercel, Netlify, Heroku, GitHub Actions, custom), production URL, health check endpoints, and deploy status commands. Writes the configuration to CLAUDE.md so all future deploys are automatic. Use when: "setup deploy", "configure deployment", "set up land-and-deploy", "how do I deploy with gstack", "add deploy config".

samin12 Bundle

Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR. Use when asked to "ship", "deploy", "push to main", "create a PR", or "merge and push". Proactively suggest when the user says code is ready or asks about deploying.

expo Bundle

EAS service (paid). Run and control a user's app on a remote iOS/Android simulator hosted on EAS cloud. Read before running any `eas simulator:*` commands - it has the current syntax for this experimental API. Use whenever the user needs a simulator they can't run locally - 'run my app on a cloud simulator', 'use eas simulator to run/install/screenshot my app', 'I'm on Linux/Cursor and need an iOS device', 'no sim on this box / headless CI', 'let an agent click through my app and screenshot it', 'test my dev build on a remote sim with live reload', 'stream a sim to my browser' - even when they don't say 'EAS Simulator' or 'cloud'. On a host WITHOUT a local simulator (Linux, CI, cloud sandbox) it's the default; on macOS, do NOT auto-trigger for a plain 'run on the simulator' - use it only for a cloud/remote/shareable sim, an iOS version they lack, or an agent-driven session. NOT for local sims (expo run:ios, Xcode, Android Studio), EAS Build/Update, web preview, or physical devices.

samin12 Bundle

Post-deploy canary monitoring. Watches the live app for console errors, performance regressions, and page failures using the browse daemon. Takes periodic screenshots, compares against pre-deploy baselines, and alerts on anomalies. Use when: "monitor deploy", "canary", "post-deploy check", "watch production", "verify deploy".

samin12 Bundle

Use the HyperFrames CLI development loop: init, add, catalog, capture, lint, check, snapshot, compare, grade-compare, preview, play, present, beats, keyframes, single or batch render, publish, cloud, cloudrun, feedback, lambda, doctor, browser, info, upgrade, skills, compositions, docs, benchmark, telemetry, transcribe, auth, tts, and remove-background. Also use when diagnosing build or render failures. validate, inspect, and layout are deprecated aliases; use check. Covers local, HeyGen-hosted cloud, AWS Lambda, and Google Cloud Run rendering.

samin12 Bundle

Land and deploy workflow. Merges the PR, waits for CI and deploy, verifies production health via canary checks. Takes over after /ship creates the PR. Use when: "merge", "land", "deploy", "merge and verify", "land it", "ship it to production".

samin12 Bundle

Auto-review pipeline — reads the full CEO, design, and eng review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. Surfaces taste decisions (close approaches, borderline scope, codex disagreements) at a final approval gate. One command, fully reviewed plan out. Use when asked to "auto review", "autoplan", "run all reviews", "review this plan automatically", or "make the decisions for me". Proactively suggest when the user has a plan file and wants to run the full review gauntlet without answering 15-30 intermediate questions.

samin12 Bundle

Use the HyperFrames CLI development loop: init, add, catalog, capture, lint, check, snapshot, compare, grade-compare, preview, play, present, beats, keyframes, single or batch render, publish, cloud, cloudrun, feedback, lambda, doctor, browser, info, upgrade, skills, compositions, docs, benchmark, telemetry, transcribe, auth, tts, and remove-background. Also use when diagnosing build or render failures. validate, inspect, and layout are deprecated aliases; use check. Covers local, HeyGen-hosted cloud, AWS Lambda, and Google Cloud Run rendering.

samin12 Bundle

Teams meeting summaries, job replay, Graph subscriptions.

samin12 Bundle

Inspect an agent codebase to decide where tracing belongs, turn on Ratel's native OTLP telemetry, and pick the OTel backend the team already runs to export to, then write a proposal covering instrumentation, backend selection, and the dashboards that prove value. Use when mounting observability, asking where tracing goes or what to instrument/measure, turning on Ratel telemetry, choosing an OTel backend (Langfuse/LangSmith/collector/Ratel Cloud), designing dashboards, asking what proves Ratel's value, or `/ratel-observability-assessment`. Entry point of the funnel (reached from /ratel-assessment); hands off to /ratel-integrate for rollout. Writes one living markdown file to repo/.ratel/; does not edit code or call a backend API; skips when there's no agent surface.