LLM Mart Basic
@llm-mart · Joined Jun 2026
Pre-change blast radius analysis for Alibaba Cloud — Resource Directory OU scope mapping, RAM policy cascade effects, VPC peering and CEN impact, SLB backend pool changes, RDS connection pool disruption, and safe change sequencing.
Advise on MLPS 2.0 grading and technical controls, DSL Article 31 cross-border data transfer, CSL network operator obligations, PIPL personal data requirements, and ICP Beian filing for mainland China CN-* region workloads.
Detect and coordinate response to Alibaba Cloud cost anomalies — MaxCompute CU vs on-demand billing mismatch, ECS spot instance interruption cascades, CDN traffic spike billing, OSS API request cost explosions, budget alert → DingTalk notification → remediation playbook.
Analyze Alibaba Cloud spend via Cost Manager, optimize Savings Plans and Reserved Instance coverage, design resource tagging strategy, investigate budget drift, and right-size over-provisioned ECS, RDS, and MaxCompute resources.
Coordinate the daily Alibaba Cloud operations standup — cost delta from Cost Manager, ActionTrail anomaly review, ACK pod failure triage, quota utilization warnings, Security Center finding review, and action item assignment.
Build CI/CD pipelines with RDC (Research and Development Collaboration), Cloud Build, Flow pipeline automation, ACR (Container Registry) image lifecycle, and environment promotion strategies.
Operate ECS instances, Auto Scaling groups, ECI serverless containers, and Cloud Assistant O&M automation. Handle instance lifecycle, image management, placement groups, spot/preemptible instances, and scheduled scaling.
Review Alibaba Cloud EventBridge, MNS (Message Notification Service), RocketMQ, and MSE event-driven designs — dead-letter queues, message ordering, idempotency, retry storm prevention, schema registry, and consumer group lag monitoring.
Deploy and operate Function Compute 3.0, SAE (Serverless App Engine) applications, and EDAS microservice apps. Guide the serverless vs. PaaS vs. container platform choice for each workload type.
Review Terraform and ROS (Resource Orchestration Service) changes targeting Alibaba Cloud — blast radius analysis, resource deletion detection, cross-stack dependency impact, Resource Directory scope, and rollback plan completeness.
Audit and govern Alibaba Cloud KMS key lifecycles, Certificate Manager, SSM (Secrets Manager), and HSM key operations. Ensure encryption-at-rest coverage and rotation compliance across CMKs, envelope encryption, and certificate lifecycle.
Design Alibaba Cloud landing zone — Resource Management org tree, Cloud SSO, Control Policy (SCP equivalent), multi-account governance baseline, billing account structure, and ActionTrail centralization.
Gate ACK deployment mutations, node pool scaling, and cluster version upgrades against rollback posture and workload disruption budget. Prevents irreversible cluster version upgrades from proceeding without PodDisruptionBudget verification, node drain confirmation, and explicit o
Gate live financial authority actions — budget threshold changes, Savings Plan purchases, and Reserved Instance commitments. These are committed spend or can trigger immediate service suspension.
Gate KMS key deletion and disable operations. All data encrypted with a deleted CMK (OSS SSE-KMS, ECS encrypted disks, RDS/PolarDB TDE) becomes permanently and irrecoverably inaccessible. This guard enforces complete CMK dependency audits, deletion window confirmation, and explic
Gate OSS bucket ACL and policy mutations — public-read/write ACL exposes data to internet crawlers within seconds; CN-* cross-border replication requires DSL Article 31 assessment.
Gate RAM policy/role mutations against the Alibaba Cloud account hierarchy. RAM AdministratorAccess assignment, policy deletion with active STS tokens, and Resource Directory Control Policy changes carry account-wide or org-wide blast radius. This guard enforces blast-radius asse
Gate RDS/PolarDB instance deletion, spec downgrade, and backup policy removal — database deletion without verified backup is permanently destructive.
Traffic engineering for Alibaba Cloud load balancers — CLB (Classic, legacy), ALB (Application Load Balancer, Layer 7 advanced routing), NLB (Network Load Balancer, Layer 4 high throughput), and GA (Global Accelerator) — type selection, health check design, WAF integration, and t
Alibaba Cloud Maestro routing skill. Classify the user's Alibaba Cloud task, select the narrowest specialist agent or the right team of specialists from the catalog, and dispatch them — single specialist for focused tasks, parallel team (max 4) for multi-domain tasks. Never auto-
Fourteen posts of being wrong in production, compressed to checkboxes
Healthy nodes, a quiet network, 300 restarts in three days, and a latency budget measured in milliseconds
Discovery worked. Ping worked. Every TCP connection timed out, and later the tunnel only worked when someone had a terminal open.
Every VM came back. The cluster did not. Declarative systems converge on config, and the datapath isn't config.
A surprising share of AI-in-the-terminal failures aren't the AI. They're zsh, and a version of bash from 2006.
A Claude Code plugin turns standalone project configuration into a namespaced, installable extension that teams and communities can update as one unit.
None of the safety came from the model. It came from six boring habits.
Skills package instructions and references. Subagents run work in a separate context and return results. They solve different problems and can be composed deliberately.
Six hours in, one step left, everything green, and the incident that didn't happen
CLAUDE.md carries persistent project context. Skills load reusable procedures when relevant. Separating stable facts from task-specific workflows keeps both easier to maintain.
Twenty minutes recovering secrets that never existed, and the one sentence from a human that ended it
An API request routing a model's tool call through an approval gate to a remote MCP server
31 config keys, two audits, and why the first one was wrong in both directions
The official MCP Registry stores standardized server metadata rather than package code. Publishers verify a namespace, describe installation or remote access, and submit immutable versions.
Everyone looks at the Dockerfile. The file that actually leaked the key was the project file.
Remote MCP authorization uses established OAuth standards, but secure integration still requires issuer validation, least-privilege scopes, protected token handling, and server-side enforcement.
"Copy it over and switch the reference" is two steps, and the outage lives in the one nobody checks
stdio fits local processes and prototypes. Streamable HTTP fits hosted services and shared integrations. The right choice follows where the capability runs and who must reach it.
The most important rule wasn't about what I could change. It was about what I was allowed to display.
Tools perform operations, resources expose readable context, and prompts provide reusable templates. Choosing the correct primitive makes an MCP server easier to understand and govern.
/offboard-user
Offboard user
Run the complete M365 offboarding workflow for a departing user - revoke access, handle mailbox, transfer data
/block-sender
Block sender
Create a Mailprotector block rule for a sender address or domain at a chosen scope
/check-quarantine
Check quarantine
Review the Mailprotector quarantine at any scope and summarize held messages
/onboard-customer
Onboard customer
Onboard a new customer onto Mailprotector - customer, domain, user group, services, users
/release-message
Release message
Release one or more quarantined Mailprotector messages to their recipients
/meraki-find-device
Meraki find device
Locate a Meraki device by serial, name, or MAC across an organization's networks
/meraki-firewall-review
Meraki firewall review
Pull and summarize a Meraki network's L3 firewall rules and flag overly-permissive (any/any allow) rules
/meraki-network-health
Meraki network health
Sweep an organization's networks, devices, and appliance VPN status for a site-health overview
/entra-audit
Entra audit
Run a read-only Microsoft Entra identity hygiene audit via the Graph Enterprise MCP — inactive user accounts, admins without MFA registered, unassigned/wasted licenses, and a guest user inventory
/entra-report
Entra report
Conversational Microsoft Entra directory reporting via the Graph Enterprise MCP — license usage, user and group counts, application inventory, and directory composition, formatted for client check-ins and QBRs
/check-queue
Check queue
Check Mimecast email delivery queue status and identify stuck or deferred messages
/review-threats
Review threats
Review Mimecast TTP threat logs for URL clicks, malicious attachments, and impersonation attempts
/trace-message
Trace message
Trace an email through Mimecast by sender, recipient, subject, or date range
/device-inventory
Device inventory
Inventory devices for an N-central customer or site with class, warranty, and monitor-health breakdown
/issue-sweep
Issue sweep
Sweep active issues across N-central customers, grouped by severity and probable root cause
/browse-files
browse-files
List, search, and inspect ENCODE files by format, type, and assembly
/cite-encode
cite-encode
Generate ENCODE citations for publications, grants, and presentations
/compare-experiments
compare-experiments
Check if two ENCODE experiments are compatible for combined analysis
/cross-reference
cross-reference
Cross-reference ENCODE data with PubMed, GEO, ClinicalTrials, and bioRxiv
/download-encode
download-encode
Download ENCODE files (BED, FASTQ, BAM, bigWig) with MD5 verification
Offline-first Python AI agent that runs a tiny research business: quotes each job against its own costs, collects via Stripe, fulfils with NVIDIA Nemotron, pays…
0 views 0 likesDSH 插件 · 注入式优化器 0.8(主线):你照常说话,它在你发送后,AI接收前把"这一轮到底要什么"理清楚,再把这份理解交给工作 AI(上下文注入) —— 原话不改写,条条带逐字依据。含控制界面(档位/权限/模型/上下文/只读工具)、拦截浮层(思维层+产出层)与真实 token 用量。可明显提升大多数模型的发挥稳…
0 views 0 likesReliable AI Skill + MCP toolkit for agent-driven desktop CAD automation.
0 views 0 likesCurated real-world use cases for Hermes Agent — the self-improving AI agent from Nous Research. Backed by primary sources.
0 views 0 likesAI Agent 教学仓库 | 系统化 LangChain、RAG、LangGraph、MCP 全栈实战代码 | 万字博客详解 | 开源可运行示例 | 从零构建智能体
0 views 0 likes从 0 复刻 WorkBuddy-style 桌面 AI 助手 Harness:24 章 Python 教程,覆盖 Agent Loop、工具调用、记忆系统、Sidecar、沙盒审计、DeepSeek/OpenAI 评测轨迹
1 views 0 likesMCP server and CLI tools for web search and crawling, built on SearXNG and Crawl4AI
2 views 0 likesDelta MCP is a free app that sits between your AI apps and their MCP servers: one program per task instead of one tool call per step, up to 24.1× fewer tokens i…
2 views 0 likesAva turns any Android 5+ device into a voice-first Home Assistant kiosk. Native C++ under the hood, so a 10-year-old tablet still listens, talks, and runs the h…
0 views 0 likesRoblox Studio macOS Window Capture Fix 2026: Real Screenshot Tool Instead of Magenta Playtest Glitch
2 views 0 likesLabTether
2 views 0 likes