DevOps & Infra

uygnoey Bundle

Adopt the MCP 2026-07-28 specification — the fifth Model Context Protocol spec release, which moves MCP to a stateless request/response core, graduates MCP Apps and Tasks into a versioned extensions framework, and hardens authorization to align with production OAuth 2.0 and OIDC. Use when planning an MCP server against the new spec, when deciding whether to deploy a server on serverless or edge infrastructure, when connecting a server to an enterprise identity provider such as Entra or Okta, when adding interactive UI or long-running work to a server, or when preparing a connector for the Claude connectors directory. Also covers what shipped on the Claude side — MCP Apps, enterprise-managed auth, connector observability, and MCP tunnels.

uygnoey Bundle

Plan and run a staged rollout of an agentic AI research workbench inside a life sciences organization — choosing the right surface for each kind of work, getting the install next to real data and compute, and moving from foundation to pilot to scale with metrics that show it is working. Use when a research org is deciding where AI fits across analysis, document, and pipeline work, when Research IT must review install footprint and governance before controlled data is touched, or when a pilot needs measurable criteria rather than enthusiasm.

uygnoey Skill

Decide whether to run Claude via Microsoft Foundry hosted on Azure or hosted on Anthropic, based on Azure-native requirements vs. needing full API feature/model availability.

uygnoey Bundle

Evaluate a consulting or engineering firm's demonstrated capacity to deploy Claude, using the signals the Claude Certification Program and the Claude Partner Network actually produce — proctored role-based credentials, certified practitioner counts, deployed customers, and public customer references. Use when selecting a delivery partner for a Claude deployment, when vetting who will work on your systems, when a firm cites certification numbers and you need to know what they mean, or when a firm is planning its own advance through the partner network tiers.

uygnoey Skill

Key takeaways and a short, compliant checklist for enabling Claude models on Google Cloud Vertex AI in FedRAMP High / IL2 environments.

uygnoey Bundle

Checklist for implementing model usage on Amazon Bedrock based on this Claude GA announcement, including considerations for agentic orchestration via AWS Lambda and enterprise customization.

uygnoey Bundle

Decision checklist for using latency-optimized Claude 3.5 Haiku on AWS Trainium2 and Amazon Bedrock Model Distillation for Claude 3 Haiku, based on the official announcement.

ksmaster03 Skill

ตัวขับเคลื่อนการพัฒนาซอฟต์แวร์ครบวงจรแบบ SDLC + Agile ตั้งแต่เก็บ requirement, FR/NFR, business logic, design/architecture, authentication & authorization, Segregation of Duties (SoD), threat model, dev, test, regression/non-regression, security test, pen test, deployment, ไปจนถึง monitoring & observability — จัดเป็นเฟส มี quality gate และ artifact ทุกเฟส แล้ว delegate ไปยัง sub-skill รายเฟส. Trigger เมื่อผู้ใช้พิมพ์ /sdlc-agile หรือขอ "เริ่มโปรเจกต์ซอฟต์แวร์ใหม่ / วาง process พัฒนา / ทำ SDLC / เก็บ requirement ไปจนถึง deploy / กระบวนการ Agile / software lifecycle".

ksmaster03 Skill

วางแผน + สร้าง + ประกอบคลิปวิดีโอให้ "น่าสนใจ หยุดนิ้ว" — director's playbook (hook/retention/pacing/SFX-as-hook) + pipeline ประกอบคลิปนำเสนอ/explainer จากสไลด์ภาพ+VO (Ken Burns, xfade, Netflix subs, progress bar, intro hook, outro CTA, SFX) + ffmpeg recipe cookbook & gotchas. Trigger เมื่อผู้ใช้พิมพ์ /vidcraft หรือขอ "วางแผนคลิป / ทำคลิปให้น่าสนใจ / ทำคลิปนำเสนอ / explainer / presentation video / คลิปจากสไลด์ / hook / สคริปต์คลิป / ทำคลิปจากภาพ+เสียงพากย์". ใช้คู่กับ [[vdocut]] (ตัดฟุตเทจ) และ [[reel-factory]] (รีลข่าว 9:16).

ksmaster03 Skill

วาง monitoring & observability หลัง deploy — สามเสา logs/metrics/traces, นิยาม SLI/SLO + error budget, golden signals, alerting และ incident management + runbook ให้ระบบ "บอกได้ว่าตอนนี้สุขภาพเป็นยังไง" และ "เมื่อพังจะรู้ก่อนลูกค้า". Trigger เมื่อผู้ใช้พิมพ์ /observability หรือขอ "monitoring / observability / logging / metrics / tracing / SLI / SLO / alerting / on-call / incident / runbook / เฝ้าระวังระบบ".

uygnoey Bundle

Design and operate security controls for a software development lifecycle where agents author most of the code. Use when the security review queue has become the bottleneck on shipping, when deciding where human gates belong once the build step takes hours instead of months, when setting agent identity and permission boundaries (including agent-to-agent access), when introducing AI reviewers that must earn trust before they can block or approve, or when a security program needs an audit trail for decisions made by agents rather than people. Covers the Plan, Code, Test/CI, Deploy/CD, Monitor, and Governance stages with an enduring principle for each.

uygnoey Bundle

Set up visibility and cost control for an enterprise AI deployment using admin analytics, model defaults and entitlements, spend-threshold alerts, and programmatic access through the Analytics API and Admin API. Use when an org's usage and cost patterns stop looking like a chat tool's and start looking like agentic work, when finance or IT needs usage and cost data alongside the rest of cloud spend, when routine work is defaulting to the most expensive model, when users are hitting spend limits mid-task, or when someone asks what value the deployment is actually returning per team or per seat.

uygnoey Skill

Roll out Claude Desktop across an organization with cloud-hosted inference and enterprise controls, based on a provider-backed deployment (AWS, Google Cloud, or Microsoft Foundry).

uygnoey Bundle

Keep a CRM current by reading the team's own guidance on opportunity stages, checking it against what is actually happening in email and call recordings, and proposing each update with the evidence behind it for a rep to approve. Use when pipeline data drifts because updating stages is manual; when a stage change should be justified by evidence rather than memory; when an agent must propose rather than write to the system of record; or when rejected proposals should teach the skill instead of being silently discarded.

uygnoey Bundle

Deploy a Slack-based data analytics agent that a whole company can ask ad hoc questions — keep its skill files refreshed like a data model, give it analytical skills beyond table access, wire it into business context, permission its service account deliberately, and instrument every answer so adoption and correctness are measurable.

darker2016 Skill

Makers 开发专家团 CLI 命令参考 Skill — EdgeOne CLI 全部命令速查、 非交互 flag、环境变量管理、本地预览、build。 触发词：CLI 命令、edgeone 命令、命令行参考、makers dev、 makers build、makers deploy、env set、env ls。

darker2016 Skill

Makers 开发专家团部署 Skill — 将前端/全栈项目部署到 EdgeOne Makers。 包含 CLI 安装、登录鉴权、一键部署、JSON 输出解析、URL 铁律。 触发词：部署、发布、上线、发版、deploy、publish、go live、 重新部署、deploy to EdgeOne。 当执行 edgeone makers deploy 命令时必须加载此 skill。

darker2016 Skill

Makers 开发专家团后端工程师 Skill — Edge Functions (V8)、 Cloud Functions (Node.js/Go/Python)、Middleware、KV/Blob 存储开发。 触发词：后端 API、Edge Function、Cloud Function、Middleware、 KV 存储、Blob 存储、Express、FastAPI、Gin、鉴权、数据库。

darker2016 Skill

MVP 开发专家团运维工程师（卜宕机）。负责自动化部署（CloudBase/Docker）、环境验证、健康检查、回滚策略、交付包组装。确保每次部署可验证、每次交付可追溯。 触发词：由 mvp-dev-team-lead 主理人调度执行 Phase 4 部署任务时激活。不直接面向用户。

darker2016 Skill

用户咨询腾讯云产品资源、AWS、阿里云等多云资源时，查看智能顾问架构图、架构目录、架构详情、架构评估结果、绘制架构图、开通智能顾问时、AI智能巡检、AI容量监测、AI混沌演练、AI云诊断、主动预警、架构健康度、云运维问答、云资源查询、云成本优化、安全合规、云资源盘点、闲置资源检查、云产品最佳实践等AIOps、ChatOps、CloudOps操作时使用。

darker2016 Skill

International journal scout — searches candidate SCI/SSCI/EI/Scopus journals via Wanfang foreign journal API, performs L1 deterministic rejection screening, and L2 citation fingerprint analysis.

darker2016 Skill

Chinese journal matcher — performs L3 6-dimensional matching (keywords, cited direction, trend, solicitation, institution, cross-discipline), calculates conditional acceptance probability with review cycle estimation, and outputs tiered submission strategy (aspiration-stable-safety) using 4-layer weighted ranking.

darker2016 Skill

International journal matcher — performs L3 6-dimensional matching for SCI/SSCI/EI/Scopus journals, computes conditional acceptance probability with review cycle estimation, applies 4-layer weighted ranking, and outputs tiered submission strategy including CAS warning screening and Chinese scholar friendliness analysis.

darker2016 Skill

Generate professional diagrams including cloud architecture, data charts, academic figures, and more. Triggers on requests like "画架构图", "画图表", "画论文插图", "生成系统图", "create diagram", "visualize data", "draw neural network", or when users provide a sketch/image they want to recreate professionally.

darker2016 Skill

系统架构图绘制。当需要绘制任何系统架构图、云架构设计图、微服务架构图、Serverless架构图、混合云架构图时使用此技能，支持腾讯云及通用架构场景。基于 Draw.io XML 生成 .drawio 文件，支持二次可视化编辑。

benjaminastera Skill

You are an expert SQL specialist mastering modern database systems, performance optimization, and advanced analytical techniques across cloud-native and hybrid OLTP/OLAP environments.

benjaminastera Skill

Azure Machine Learning SDK v2 for Python

benjaminastera Skill

Azure Cosmos DB SDK for Python

benjaminastera Skill

@azure/cosmos (TypeScript/JavaScript)

benjaminastera Skill

Use this skill when

benjaminastera Skill

Azure Cosmos DB SDK for Java

benjaminastera Skill

Azure Cosmos DB SDK for Rust

benjaminastera Skill

Azure Event Hubs SDK for Python

benjaminastera Skill

Azure Identity SDK for Python

benjaminastera Skill

Azure Key Vault SDK for Python

benjaminastera Skill

Azure PostgreSQL for TypeScript (node-postgres)