LLM Mart Basic
@llm-mart · Joined Jun 2026
Audit ML experiment tracking infrastructure for reproducibility gaps, parameter logging completeness, metric capture, artifact management, and pipeline orchestration. Covers MLflow, Weights and Biases, DVC, Sacred, Neptune, Hydra configs, model registries, and produces a reproduc
Optimize mining extraction operations by analyzing ore grade control, processing plant throughput, metallurgical recovery rates, energy consumption, and water balance.
Audit commercial building energy performance including HVAC optimization, ENERGY STAR scoring, utility cost analysis, demand response readiness, and sustainability compliance.
Analyze fleet maintenance programs for preventive maintenance scheduling effectiveness, parts inventory forecasting, vehicle downtime minimization, total cost of ownership modeling, and telematics integration.
Analyze fleet safety programs including driver behavior scoring, accident trend analysis, CSA BASIC score monitoring, DOT audit readiness, Hours of Service compliance, and drug and alcohol testing programs.
Manage the full Freedom of Information Act (FOIA) and state public records request lifecycle — intake form generation, agency-specific portal routing (FOIA.gov, FBI eFOIA, USCIS, FOIAonline successor portals).
Analyze food supply chain systems for waste reduction opportunities including shelf life prediction models, FIFO and FEFO inventory rotation enforcement, demand forecasting accuracy and bias, donation logistics workflows, cold chain temperature monitoring, and sustainability repo
Benchmark franchise locations by comparing top and bottom quartile performance across revenue, profitability, and operational scores.
Analyze franchise inventory management for par level optimization, waste tracking and root cause analysis, and theoretical vs. actual usage variance.
Analyze fraud detection systems including rule engines, ML scoring models, real-time transaction monitoring, alert triage workflows, false positive management, SAR/CTR regulatory reporting, adversarial robustness testing, and adaptive retraining pipelines for payment fraud, accou
Analyze fleet fuel optimization systems including MPG consumption analytics, eco-driving behavior scoring, route fuel cost modeling, idling detection and anti-idle programs, IFTA tax compliance reporting, alternative fuel transition planning, EV charging infrastructure readiness,
Analyze university and research institution funding allocation systems including RCM revenue attribution, performance-based budgeting, faculty startup package management, F&A indirect cost recovery distribution, equipment sharing and core facility recharge rates.
Analyze game AI systems including behavior trees, finite state machines, GOAP planning, utility AI scoring, A-star and NavMesh pathfinding, steering and flocking behaviors, perception and awareness models, dynamic difficulty adjustment, NPC dialogue trees and scheduling, boss AI
Analyze game design documents and implementations for core gameplay loop clarity and depth, XP leveling curves and unlock pacing, difficulty curve spikes and plateaus, skill tree viability, player motivation via Self-Determination Theory.
Analyze in-game economy systems including soft and hard currency source-sink balance, inflation projection modeling, loot table drop rate fairness and pity system evaluation, gacha probability disclosure, player marketplace health and price manipulation risks.
Analyze game monetization implementations including IAP purchase flow and server-side receipt validation, ad mediation waterfall and rewarded video placement, subscription lifecycle and grace period handling, battle pass XP progression.
Analyze game code for performance bottlenecks including draw call batching and overdraw, shader complexity and LOD strategy, per-frame GC allocation pressure, object pooling gaps, physics timestep and collision matrix tuning, spatial partitioning for entity queries.
Whole-codebase analysis powered by Gemini 2.5 Pro's 2M token context window. Triggers: bounded per-module analysis misses inter-module patterns or when you need a full-graph view before a major refactor.
Generative Engine Optimization (GEO) / Answer Engine Optimization (AEO) — make a site citable by ChatGPT, Perplexity, Claude, Gemini, and Google AI Overviews. Triggers: "GEO", "generative engine optimization", "AEO", "answer engine optimization", "AI search optimization".
Analyze grant management and sponsored research operations including proposal lifecycle tracking, pre-award routing and budget development, post-award expenditure monitoring and burn rate analysis, 2 CFR 200 Uniform Guidance cost allowability enforcement.
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.
/lookup-company
Lookup company
Find a HubSpot company by name or domain and show associated contacts and deals
/pipeline-summary
Pipeline summary
Summarize the HubSpot deal pipeline - deals per stage, total value, and expected close dates
/search-contacts
Search contacts
Search HubSpot contacts by name, email, or company
/search-deals
Search deals
Search HubSpot deals by name, stage, or company
/find-company
Find company
Find a company in Hudu by name
/get-password
Get password
Retrieve a password from Hudu (with security logging)
/lookup-asset
Lookup asset
Find an asset in Hudu by name, hostname, serial number, or IP address
/search-articles
Search articles
Search Hudu knowledge base articles by keyword or phrase
/agent-inventory
Agent inventory
List and filter Huntress agents across organizations
/billing-report
Billing report
Generate a Huntress billing summary for a period
/incident-triage
Incident triage
Triage open Huntress incidents by severity
/investigate-incident
Investigate incident
Deep dive investigation into a specific Huntress incident with remediations
/org-health
Org health
Organization health check covering agents, incidents, and escalations
/resolve-escalation
Resolve escalation
Review and resolve a Huntress escalation
/compliance-report
Compliance report
Generate an ImmyBot software-compliance scorecard for a tenant or the whole fleet
/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)
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