DevOps & Infra

garyld1962 Skill

Retrieve a work item from Azure DevOps or Linear. Extracts title, description, acceptance criteria, status, assignee, and tags. Presents in clean markdown format for use by other skills.

garyld1962 Skill

Post-deploy verification for Kubernetes: checks pod health, service endpoints, recent events, log errors, and rollout status. Use after any K8s deployment to verify it succeeded.

garyld1962 Bundle

Domain-based PR review controller (formerly code-review). Preferred over the built-in /code-review when you need the 11-domain controller/worker review with per-domain findings; use the built-in for a fast single-pass diff review or the ultra cloud review. Supports two profiles: 'breakpoint' (light mid-flow review covering security, correctness, and tests only) and 'full' (comprehensive PR-boundary review covering all 11 domains). Conditional domains fire only when triggers match: data-integrity fires when the diff touches persistence (migrations, schemas, SQL, repositories, ORM models); api-contract fires when the diff touches a public surface (API routes, controllers, handlers, .proto files, OpenAPI/Swagger specs, library surface, message schema, CLI, or SDK). Do NOT use for trivial changes (typo fixes, mechanical refactors, dependency bumps with no logic changes). Do NOT use for reviewing a GitHub PR by number where a standard pass suffices — the built-in /review handles that. Do NOT use when you want prof

garyld1962 Skill

Retrieval and normalization workflow for Azure DevOps work items used as planning or implementation inputs.

hmbown Skill

Teleport is FULL-CONTEXT migration, not partial transformation. The defining characteristic is that EVERYTHING must move together and keep working: data, dependencies, auth, traffic routing, background jobs, secrets, and human workflows. The old system must remain recoverable until the new one is proven. This spell IS: Database migrations (RDS→Cloud SQL, self-managed→Atlas), cloud provider moves (on-prem→AWS, Heroku→K8s), environment promotions (staging→prod), account/tenant consolidations, platform migrations (Jenkins→GitHub Actions, SendGrid→SES), identity migrations (AD→Azure AD), cluster upgrades with relocation

hmbown Skill

Use this spell for preflight certainty: dry runs, validation checks, dependency verification, and rehearsals that make the next deploy, query, or command much more likely to succeed. It trades a little time up front for fewer blind swings and fewer expensive misses.

hmbown Skill

Feather Fall is the spell for bad situations that are already in motion. A deploy is going sideways, a service is thrashing, a queue is backing up, or an integration is failing faster than the humans can think. Instead of pretending you can teleport back to normal instantly, you slow the fall: circuit breakers, degraded modes, load shedding, safe defaults, and graceful shutdown paths. The point is not elegance. The point is buying time without multiplying damage. A good Feather Fall plan makes failure survivable and visible enough to recover from.

hmbown Skill

Hold Monster is Hold Person scaled to larger targets. The real-world version is the emergency circuit breaker: halting an entire service, freezing a deployment pipeline, or stopping a runaway process at the infrastructure level. This is the big red button — it stops everything, and it should only be pressed when the alternative is worse.

hmbown Skill

In D&D, Locate Object senses the direction to a specific object within range. The real-world version is artifact search: finding that config file you know exists somewhere, locating a document someone mentioned but did not link, tracking down the source of a data value through a pipeline, or finding where a specific resource is defined in a sprawling repository.

hmbown Skill

Use this spell when you need to summon a powerful external entity - a third-party API, a cloud service, another agent - and lock it into serving your workflow under explicit terms.

hmbown Skill

In D&D, Stinking Cloud fills an area with nauseating gas — creatures inside are incapacitated but the terrain itself is undamaged. The real-world version is area denial: making a zone, endpoint, or resource unusable to unwanted traffic without permanently destroying or modifying it. Rate limiting, IP-range blocks, honeypots, tarpits, geographic restrictions. Stinking Cloud is defensive — it protects a perimeter by making the area inside it miserable for intruders while leaving the underlying infrastructure intact.

hmbown Skill

Use this spell when you need a permanent, reliable portal between two environments — a CI/CD pipeline, a standing data sync, a repeatable deployment, or a migration path you will use more than once.

shengdabai 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". (gstack) Voice triggers (speech-to-text aliases): "see-so", "see so", "security review", "security check", "vulnerability scan", "run security".

shengdabai 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". (gstack)

shengdabai Bundle

Auto-review pipeline — reads the full CEO, design, eng, and DX 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. (gstack) Voice triggers (speech-to-text aliases): "auto plan", "automatic review".

shengdabai Skill

Eight-role expert writing pipeline that turns a vague idea into a finished, fact-checked, on-brand long-form article. Roles run as ordered phases: topic strategist, knowledge steward, researcher, writer, voice-polisher, fact-checker, editor-in-chief, and layout designer. The voice-polisher learns the user's personal style from their past writing (brain + GetNote + Obsidian + AI archive) so the finished piece reads in the user's own voice. Each role runs on a cost-appropriate model per the model-routing convention.

shengdabai 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".

shengdabai 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". (gstack)

delorenj Skill

[BETA] Offload plan phase to Claude Code's ultraplan cloud — drafts remotely while terminal stays free, review in browser with inline comments, import back via $gsd-import. Claude Code only.

vibeeval Skill

Dockerfile best practices, multi-stage builds, docker-compose, container networking, volume management, and image optimization.

vibeeval Skill

Research-to-implement pipeline chaining 5 MCP tools with graceful degradation

vibeeval Skill

Static Application Security Testing patterns, OWASP Top 10 checklist, language-specific vulnerability patterns, Semgrep rule writing guide, and CI/CD integration. Use when scanning code for security vulnerabilities or writing custom SAST rules.

vibeeval Skill

Show how vibecosystem works - agents, skills, hooks, and self-learning pipeline.

vibeeval Skill

Pod design patterns, sidecar containers, init containers, config management, rolling updates, and resource limits.

vibeeval Skill

Ethical security testing methodology - 5-phase pipeline, OWASP checklist, proof levels, structured findings

vibeeval Skill

GitHub Actions workflow templates, matrix builds, caching, and monorepo CI strategies

vibeeval Skill

TOCTOU prevention, distributed locking, idempotency keys, race condition detection for Node.js and serverless environments.

vibeeval Skill

Traffic splitting, health checks, automated rollback, progressive delivery, and canary analysis for safe deployments.

vibeeval Skill

ETL/ELT patterns, batch vs streaming, idempotency, data quality framework, and pipeline orchestration

vibeeval Skill

Orchestrator-only workflow for migrating/rewriting codebases with full TDD and agent delegation

vibeeval Skill

Cloud cost optimization, token/API cost tracking, build time optimization, and FinOps patterns

vibeeval Skill

HashiCorp Vault, cloud secret managers, rotation strategies, and zero-trust secret access

ascend-ai-coding Bundle

当用户需要对华为昇腾 NPU 进行硬件层面的管理、测试或诊断时使用此 skill。典型场景： - 查看 NPU 卡的状态、温度、利用率 - 测试内存带宽（h2d/d2h/d2d/p2p） - 跑算力/功耗基准测试（TFLOPS、TOPS） - 诊断 NPU 硬件故障或做健康检查 - 对 NPU 卡做压力测试（aicore、内存） - 复位/恢复卡住或异常的 NPU 卡 典型用户问题（即使不提 ascend-dmi 也应触发）： - "帮我测一下这台服务器的算力和带宽" - "看看 192.168.1.50 上 NPU 的温度和利用率" - "跑个 fp16 算力测试，看看 TFLOPS 多少" - "d2d 带宽有没有达标" - "3 号卡好像有问题，帮我诊断一下" - "NPU 卡住了，复位一下" - "对 8 张卡做个压力测试" - "跑个功耗测试，edp 模式" Use this skill whenever the user wants to measure, diagnose, or manage Ascend NPU hardware directly — including checking server NPU performance (算力/带宽/功耗), diagnosing hardware faults, or resetting NPU cards. Trigger even when the user only mentions "服务器" + "算力/带宽/NPU状态" without saying "ascend-dmi". Do NOT use for: writing NPU code, installing frameworks, debugging training issues, or Docker configuration.

ascend-ai-coding Skill

Run NPU inference/training tests on a remote SSH server with vllm-ascend Docker container. Use when the user asks to test models on NPU, run inference on Ascend devices, or deploy models to an SSH server.

ascend-ai-coding Bundle

vLLM Ascend plugin for LLM inference serving on Huawei Ascend NPU. Use for offline batch inference, API server deployment, quantization inference (with msmodelslim quantized models), tensor/pipeline parallelism for distributed serving, and OpenAI-compatible API endpoints. Supports Qwen, DeepSeek, GLM, LLaMA models with Ascend-optimized kernels.

ascend-ai-coding Bundle

本地项目部署到远程服务器，支持增量同步、部署钩子、回滚