DevOps & Infra

crozzbite Bundle

Auditoría de calidad, arquitectura y performance para proyectos Python. Trigger: Cuando se audita un repositorio Python, se inicia un refactor o se configura CI/CD.

crozzbite Skill

Logistics for digital service delivery, including SLAs, Support Tiers, and CI/CD from a business perspective.

kao273183 Bundle

整合主流安全掃描工具（SAST / DAST / SCA / Secret scan）到 CI pipeline，自動生成安全 TC、產出含 CVSS 評分的安全報告。支援 Semgrep / Snyk / OWASP ZAP / Trivy / gitleaks / Bandit。當使用者提到「安全掃描 / SAST / DAST / SCA / Semgrep / Snyk / OWASP ZAP / Trivy / 漏洞掃描 / CVE / 安全測試 / 合規測試」時觸發。配套：test-master（規劃 security TC）、bug-report（追安全漏洞）、regression-test（release 前安全回歸）。

kao273183 Bundle

為微服務 / 多前後端架構生成 Contract Test（契約測試）腳本，支援 Pact（consumer-driven）/ Schemathesis（schema-driven OpenAPI fuzz）/ Spring Cloud Contract。確保 Provider 改 API 時 Consumer 不會壞、Consumer 改用法時 Provider 仍滿足契約。當使用者提到「contract test / 契約測試 / Pact / Schemathesis / consumer-driven / provider verification / API breaking change / OpenAPI fuzz / microservices 測試」時觸發。配套：tc-to-pytest（傳統 API test）、test-master（規劃 contract TC）、test-review（審契約覆蓋）。

kao273183 Bundle

Analyze existing automated tests (iOS + Android) to select which should run in Daily Smoke CI. Scans unit and UI tests across both platforms, scores each for smoke suitability, classifies into tiers (PR Smoke / Daily / Release / Manual), and generates CI configurations (.xctestplan for iOS, Gradle filters for Android). Use whenever the user mentions 'smoke test', 'daily test', 'CI test selection', 'which tests should run daily', 'optimize CI', 'test plan config', 'flaky test analysis', or wants to curate which automated tests belong in the daily smoke suite. Also trigger when discussing CI pipeline optimization or test execution time budgets.

ryzhakar Skill

Extension of agentic-delegation for the Playwright test lifecycle. Adds the Plan->Generate->Execute->Heal->Report loop, four-agent orchestration, confidence-based PR routing, circuit breaker safety, and session persistence. Hard preference: orchestration plugin (agentic-delegation skill). Same-plugin agents: planner-agent, generator-agent, executor-agent, healer-agent. Triggers: "run QA", "automate testing", "create and run Playwright tests", "set up E2E testing", "generate and execute tests", "run the full test pipeline", "heal broken tests", or mentions running the full Playwright test lifecycle.

madappgang Skill

Provides Bun.js production patterns — Docker, AWS ECS/Fargate, Redis caching, security hardening, CI/CD. Use when deploying or operationalizing a Bun.js service.

daboggieman Skill

Comprehensive GitHub engineering skill for repository inspection, remote state analysis, branches, commits, pull requests, issues, GitHub Actions, CI/CD, releases, repository configuration, API operations, security, troubleshooting, and verified GitHub workflows using the authenticated GitHub CLI.

impertio-studio Bundle

Use when explaining MariaDB process model, threading, the query execution pipeline, plug-in architecture, in-memory caches, or when reasoning about why a query behaves as it does at the engine layer. Prevents the mistake of treating MariaDB as a black box ; surfaces the buffer-pool, log-buffer, thread-pool, and storage-engine boundaries that drive performance. Covers mysqld process model, connection threads vs thread-pool plug-in, parser-optimizer-executor stages, storage-engine plug-in API, buffer pool, redo log, undo log, binlog, query cache history, MariaDB vs MySQL optimizer divergence. Keywords: mariadb architecture, mysqld process, thread pool, buffer pool, query execution pipeline, storage engine plug-in, why is my query slow, what does mariadb do internally, how does mariadb work, redo log, undo log, binlog, mariadb internals, mariadb architecture diagram, innodb buffer pool, optimizer switch, handler interface, connection lifecycle

luokai0 Skill

Hub1

luokai0 Skill

Ambit Cli

luokai0 Skill

Agentguard

luokai0 Skill

Grafana Lens

luokai0 Bundle

Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention

luokai0 Skill

Aetherlang Chef

luokai0 Skill

Ai Act Risk Check

luokai0 Skill

K8S Memory Tune

luokai0 Skill

Ghl Crm For Realtors

luokai0 Skill

Hostinger Vps Optimizer

luokai0 Skill

Agent Self Governance

taosdata Bundle

自动编译和部署 TDengine 用户自定义函数（UDF）。支持将 C/C++ 代码编译成动态库并部署至本地、Docker 容器或远程环境中，同时支持 Python UDF 部署与在 TDengine 实例中自动注册和测试。触发关键词：自动编译和部署 UDF，编译并部署 UDF，部署 UDF，UDF 自动编译，编译 UDF。

taosdata Skill

协助部署 TDGPT 模型，包括环境配置、网络接入、依赖项安装以及模型验证。触发关键词：部署 tdgpt，部署 TDengine GPT，部署大模型，tdgpt 部署。

taosdata Bundle

协助自动编写符合 TDgpt 规范的时序预测模型及多特征对齐 Pipeline 代码。触发关键词：写时序预测模型，生成时序模型，TDGPT模型，特征对齐，tdgpt-model-writer，时序预测模型。

iamneilroberts Bundle

Use when work may have been dropped between sessions — after a crash, a lockup, parallel-session churn, or on a "did we drop anything?" hunch. Crawls worktrees, local AND remote branches, stashes, deploy targets, and intent docs (handoffs, checklists, plans, coordination journals); triages every item against ground truth (patch-id merge equivalence vs fetched origin/main, live BUILD_SHA/bundle provenance, PR state); presents a ranked loose-end ledger for ONE batch approval; then methodically recovers approved items via playbooks (adopt stray WIP, resume handoffs, rebase→test→push→PR). Never deploys, merges to main, force-pushes, or prunes autonomously. Complements /sitrep (read-only state-of-union) and a live project-board skill if you have one (e.g. /pm); triggers on /sweep, "sweep for dropped work", "what did we lose in the crash", "find stranded work", "recover dropped work", "loose ends sweep".

iamneilroberts Skill

Verify a session's or handoff's factual claims against ground truth before trusting them. Dispatches the read-only `curator` subagent to check claims against git, files, and read-only environment checks, plus the repo's invariants doc if any, and returns a confabulation report for human spot-check. Use at pass boundaries — resuming from a handoff, before a deploy, or whenever a prior session's summary looks suspiciously clean. Triggers on `/curate`, "curate this", "verify these claims", "check the handoff for confabulation", "is this actually done".

iamneilroberts Bundle

Get a second opinion on the current change or a plan from a different model (Codex), and enforce its verdict mechanically. Codex returns a structured JSON verdict — findings scored by priority (0 critical, 1 important, 2 minor, 3 nit) against sev.schema.json — and a gate script turns that into a pass/fail exit code, so a critical or important finding gets fixed or escalated rather than re-argued by the model that wrote the code. Infra failures (rate limit, model reject, empty output) are their own outcome and never count as a clean pass. Use after writing tests, before a deploy or merge, or to review a plan before execution. Triggers on `/codex-review`, `/codex-review --plan <file>`, `/codex-review --base <ref>`, "run a codex review", "get an external review of this diff", "codex-review this before I ship".

magnus919 Skill

Reverse proxy, load balancer, and ingress controller — dynamic routing, TLS automation, middleware chains, and integration with Docker, Kubernetes, and file-based providers.

magnus919 Bundle

Machine learning engineering methodology — model training, fine-tuning (LoRA/QLoRA), evaluation, quantization, deployment, and MLOps pipeline design. Grounded in practical engineering patterns for production ML systems.

magnus919 Bundle

Data engineering methodology — database operations (vector, relational, graph, time-series), ETL/ELT pipeline design (dbt patterns, incremental loading), SQL analytical patterns, data quality monitoring, schema migration, and storage infrastructure management. Grounded in operational patterns for production data systems.

magnus919 Bundle

CTO methodology for technology evaluation, architecture governance, build-vs-buy decisions, engineering metrics, technical debt quantification, and innovation pipeline management. Covers technology radar framework (Adopt/Trial/Assess/Hold), TCO analysis, architecture review boards, RFC processes, DORA/SPACE/DevEx metrics, debt interest calculation, and POC-to-production readiness criteria.

magnus919 Bundle

Infrastructure as code, CI/CD, container orchestration, service networking — methodology and reference patterns for building and operating internal developer platforms.

hack23 Skill

GitHub secrets and environment variables for MCP servers and CI/CD workflows

hack23 Skill

GitHub Actions workflow patterns for static site CI/CD, security scanning, and quality checks

diegosouzapw Bundle

Expert database administrator specializing in modern cloud databases, automation, and reliability engineering. Masters AWS/Azure/GCP database services, Infrastructure as Code, high availability, disas

diegosouzapw Bundle

Automate Pipedrive CRM operations including deals, contacts, organizations, activities, notes, and pipeline management via Rube MCP (Composio). Always search tools first for current schemas.

diegosouzapw Bundle

Documentation Pipeline (Orchestrator)