LLM Mart Basic
@llm-mart · Joined Jun 2026
Support development of .NET MAUI cross-platform apps with controls, XAML, handlers, and performance best practices.
Senior .NET architect for complex delivery: designs .NET 6+ systems, decides between parallel subagents and orchestrated team execution, documents lessons learned, and captures durable project memory for future work.
Perform janitorial tasks on C#/.NET code including cleanup, modernization, and tech debt remediation.
Provides installation guidance, usage examples, and automation patterns for the Droid CLI, with emphasis on droid exec for CI/CD and non-interactive automation
Expert assistant for Drupal development, architecture, and best practices using PHP 8.3+ and modern Drupal patterns
Our expert AI assistant for debugging code (O11y), optimizing vector search (RAG), and remediating security threats using live Elastic data.
Code Review Mode tailored for Electron app with Node.js backend (main), Angular frontend (render), and native integration layer (e.g., AppleScript, shell, or native tooling). Services in other repos are not reviewed here.
An AI partner, not an assistant. Ember carries fire from person to person — helping humans discover that AI partnership isn't something you learn, it's something you find.
Provide expert C++ software engineering guidance using modern C++ and industry best practices.
Provide expert .NET software engineering guidance using modern software design patterns.
Expert embedded C guidance for safety-critical systems — covers MISRA C:2012/2025 rule compliance, CERT C secure coding, static analysis tooling (Coverity, QAC, PC-lint), and defensive programming patterns that frontier models do not handle reliably by default.
Expert Next.js 16 developer specializing in App Router, Server Components, Cache Components, Turbopack, and modern React patterns with TypeScript
Expert React 19.2 frontend engineer specializing in modern hooks, Server Components, Actions, TypeScript, and performance optimization
Runtime web-performance specialist for diagnosing Core Web Vitals, Lighthouse regressions, layout shifts, long tasks, and slow network paths with Chrome DevTools MCP.
E2E browser testing, UI/UX validation, visual regression.
Refactoring specialist: removes dead code, reduces complexity, consolidates duplicates.
Root-cause analysis, stack trace diagnosis, regression bisection, error reproduction.
UI/UX design specialist: layouts, themes, color schemes, design systems, accessibility.
Infrastructure deployment, CI/CD pipelines, container management.
Technical documentation, README files, API docs, diagrams, walkthroughs.
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.
/update-agentskills
Update agentskills
Apply a reusable lesson to ~/.agentskills (rules/skills/templates/commands), backup + commit + push
/vendor-rotation-calendar
Vendor rotation calendar
Generate a quarterly vendor secret-rotation calendar for all load-bearing vendors; emit .ics + ROTATIONS-DUE-NEXT-30-DAYS table; optionally create Google Calendar events
/find-contact
Find contact
Resolve a 3CX contact or extension by email, extension, or name
/pbx-health-check
Pbx health check
Quick health check for a connected 3CX PBX
/queue-status
Queue status
Snapshot of 3CX queue staffing and active call load
/case-review
Case review
Review and triage abuse mailbox cases in Abnormal Security
/search-threats
Search threats
Search for specific threat patterns in Abnormal Security by sender, recipient, attack type, or keywords
/threat-triage
Threat triage
Triage recent email threats detected by Abnormal Security by severity and attack type
/list-overdue-invoices
List overdue invoices
List open and overdue Alternative Payments invoices and optionally generate hosted payment links for them
/reconcile-payout
Reconcile payout
Reconcile an Alternative Payments payout by listing its transactions and matching them against invoices and customers
/eol-report
Eol report
EOL/EOS risk report — devices, OS versions, and firmware approaching or past end-of-life/end-of-support, prioritized by criticality
/refresh-calendar
Refresh calendar
Forward-looking hardware refresh calendar for the given window — replace-now / plan-this-year / monitor tiers
/warranty-status
Warranty status
Warranty status snapshot — expired, expiring-soon, and unknown-coverage devices for one client or the whole portfolio
/create-monitor
Create monitor
Create a threshold-based monitor for an Atera agent
/create-ticket
Create ticket
Create a new service ticket in Atera
/get-kb-articles
Get kb articles
Search the Atera knowledge base for articles
/list-alerts
List alerts
List active RMM alerts from Atera
/log-time
Log time
Log work hours on an Atera ticket
/resolve-alert
Resolve alert
Resolve an RMM alert in Atera
/run-powershell
Run powershell
Execute a PowerShell script on an Atera agent
Open-source, self-hosted AI media server. One server replaces your entire media stack, with a web app, native iPhone app, and an AI agent that gets things done.…
2 views 0 likesA curated list of tools built for Jev — TypeSafe AI's System One model for typed decisions.
2 views 0 likes🦦 Crayotter: A Multimodal AI-Agent for Video-Editing, Video-Composing, and Video Production. Powered by Multimodal LLMs for autonomous Text-to-Video agentic fr…
2 views 0 likesWebextension tool for Odoo
2 views 0 likes