LLM Mart Basic
@llm-mart · Joined Jun 2026
Pino, Axiom, Sentry installation - one-time project setup for logging and error tracking with source maps upload
Query optimization, caching, indexing, connection pooling, async patterns
Job queues, background processing, and task scheduling with BullMQ v5
Elasticsearch patterns -- client setup, index management, search DSL, aggregations, vector search, bulk operations, deep pagination
Meilisearch search engine patterns -- client setup, indexing, search, filtering, facets, geo search, multi-tenancy, task management
OpenAPI 3.1 specification, schema design, code generation
Chroma vector database -- collection management, automatic embedding, metadata filtering, document storage, query patterns
Pinecone serverless vector database -- index management, vector operations, metadata filtering, namespaces, hybrid search, inference API
Qdrant vector database -- collection management, point operations, payload filtering, named vectors, quantization, recommendations, snapshots
Weaviate vector database patterns with weaviate-client v3 -- collection management, vectorizer modules, hybrid search, filtering, generative search (RAG), multi-tenancy, batch imports
Modern CLI development combining oclif's command framework with Ink's React-based terminal rendering
Beautiful interactive CLI prompts with @clack/prompts and custom prompts with @clack/core
Tauri 2.x Rust command patterns, state management, error handling, events, channels, testing
Type-safe Electron IPC patterns with typed channels, electron-trpc, MessagePort, and utility process communication
Tauri 2.x mobile development - iOS via WKWebView, Android via Android WebView, mobile plugins, Swift/Kotlin native code, permissions, debugging
Multi-window management, WebContentsView, BaseWindow, window lifecycle, inter-window communication, state persistence
Tauri 2.x multi-window creation, event system, window state persistence, parent/child and modal windows
Electron Forge build toolchain -- makers, publishers, code signing, fuses, hooks, CI/CD packaging
Tauri 2.x bundling, code signing, auto-updater, platform installers, CI/CD
Tauri 2.x official plugin ecosystem, plugin APIs, permissions, and custom plugin development
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.
/deploy-software
Deploy software
Stage and reconcile an ImmyBot desired-state software deployment to a tenant or computer
/list-computers
List computers
List and filter ImmyBot-managed computers, optionally scoped to a tenant
/maintenance-status
Maintenance status
Show ImmyBot maintenance session status — active sessions, or detail and logs for a specific session
/run-script
Run script
Find and execute an ImmyBot PowerShell script on a target computer (destructive, SYSTEM context)
/search-software
Search software
Search the ImmyBot software catalog (per-tenant + global)
/drift-report
Drift report
Portfolio-wide Inforcer baseline drift report — every managed tenant's alignment vs its assigned baseline, classified aligned / semi-aligned / drifted and sorted drifted-first, with secure score
/tenant-posture
Tenant posture
Single-tenant Microsoft 365 posture snapshot from Inforcer — secure score plus alignment score, band, and the per-policy drift detail against the tenant's assigned baseline
/classify-email
Classify email
Get an Ironscales AI verdict on a raw email, then act on it with a remediation action
/triage-incidents
Triage incidents
Triage open Ironscales phishing incidents — list by status and severity, investigate, and remediate
/get-quote
Get quote
Get a Kaseya Quote Manager quote with its sections and line items
/get-sales-order
Get sales order
Get a Kaseya Quote Manager sales order with its lines and payments
/list-quotes
List quotes
List Kaseya Quote Manager quotes, optionally scoped to a recent window
/add-note
Add note
Add a note or comment to an existing Autotask ticket
/check-contract
Check contract
View contract status, entitlements, and remaining hours for a company or specific contract
/check-pricing
Check pricing
Check pricing details for an Autotask product or service from price lists
/create-quote
Create quote
Create a new Autotask quote with line items for products, services, and service bundles
/create-ticket
Create ticket
Create a new service ticket in Autotask PSA
/expenses
Expenses
Use this skill when working with Autotask expense reports - creating reports, adding expense items, searching by status or submitter, and tracking reimbursable and billable expenses
/lookup-asset
Lookup asset
Search for Autotask configuration items/assets by name, serial number, or company
/lookup-company
Lookup company
Search for Autotask companies by name, ID, or other attributes
Your efficient agentic AI coding CLI assistant
2 views 0 likesAI coding with Aegis governance built into execution: baseline-aware changes, evidence-backed delivery. Free desktop client, your choice of model. 将哲科思维融入 AI 开发…
1 views 0 likesAndroid in docker solution with noVNC supported, video recording, mcp server and AI-agent
2 views 0 likesYour AI assistant, built for the agentic era. Open source and local: talk to it, and it runs your agents, your coding CLIs, your browser and your apps. Windows,…
0 views 0 likesVerifiable program-level self-evolution for AI-for-Science agents: Skills and typed Operators grow from replay-verified executions.
3 views 0 likesLet Claude Code and other coding agents drive and debug Chrome from the shell. DOM, network, console and raw CDP as short commands, no screenshots and no MCP ne…
3 views 0 likesUnofficial, agent-friendly Mercadona shopping CLI (Go) — search products, read prices, build a cart and prepare checkout from the terminal. BYO credentials.
3 views 0 likesLocal-first AI canvas for visual workflows, AI short drama, image/video generation, storyboarding and asset management. ComfyUI, AI agents, MCP & Blender. 本地优先…
3 views 0 likesLet any AI coding tool — Claude Code, Cursor, Codex — drive your real Chrome. One-prompt setup, muscle memory, local-first.
3 views 0 likesruns anywhere. uses anything
3 views 0 likesOpen-source dots for the web: an AI agent with its own browser, one that does not get blocked.
0 views 0 likesFree MIT AI coding agent — no API key needed. Built-in free model, or bring Claude, GPT, Gemini, DeepSeek, Ollama +50 more. Swarm mode, 40+ tools, browser & des…
0 views 0 likesOpen-source AI customer support system. AI-first support, human-ready operations.
0 views 0 likesA durable, multiplayer, mobile-first web app for Pi agents, built on Pi Durable
0 views 0 likesEmbedded Cypher knowledge graph for Python and Rust. Bundled MCP server, describe() schema, and code-graph parser for LLM agents.
0 views 0 likesTurn PDFs, books and papers into interactive learning webpages|将复杂材料转化为可追溯、可测验、可做笔记的学习网页
0 views 0 likesPhysicsOS 是一个面向初高中物理学习的公益可视化智能体,通过 AI 理解题目并结合物理引擎,将抽象物理过程转化为可交互、可观察、可计算、可验证的真实物理场景。
0 views 0 likes