LLM Mart Basic

Design, tune, or review EF Core data access with proper modeling, migrations, query translation, performance, and lifetime management for modern .NET applications.

Maintain or migrate EF6-based applications with realistic guidance on what to keep, what to modernize, and when EF Core is or is not the right next step. Use when working in an EF6 codebase or planning a data layer migration.

Use ESLint in .NET repositories that ship JavaScript, TypeScript, React, or other Node-based frontend assets. Use when a repo needs a configurable CLI lint gate for frontend correctness, import hygiene, unsafe patterns, or framework-specific rules.

Use the free first-party `dotnet format` CLI for .NET formatting and analyzer fixes. Use when a .NET repo needs formatting commands, `--verify-no-changes` CI checks, or `.editorconfig`-driven code style enforcement.

Build or review gRPC services and clients in .NET with correct contract-first design, streaming behavior, transport assumptions, and backend service integration.

Use HTMLHint in .NET repositories that ship static HTML output or standalone frontend templates. Use when a repo needs a focused CLI lint gate for DOM structure, invalid attributes, and basic HTML correctness checks on static pages.

Maintain classic ASP.NET applications on .NET Framework, including Web Forms, older MVC, and legacy hosting patterns, while planning realistic modernization boundaries.

Expert knowledge of the libvlc C API (3.x and 4.x), the multimedia framework behind VLC media player. Use when helping with LibVLC or LibVLCSharp for media playback, streaming, or transcoding.

Use ManagedCode.Communication when a .NET application needs explicit result objects, structured errors, and predictable service or API boundaries instead of exception-driven control flow.

Use ManagedCode.MarkItDown when a .NET application needs deterministic document-to-Markdown conversion for ingestion, indexing, summarization, or content-processing workflows.

Use ManagedCode.MimeTypes when a .NET application needs consistent MIME type detection, extension mapping, and content-type decisions for uploads, downloads, or HTTP responses.

Integrate ManagedCode.Orleans.Graph into an Orleans-based .NET application for graph-oriented relationships, edge management, and traversal logic on top of Orleans grains. Use when the application models graph structures in a distributed Orleans system.

Use ManagedCode.Orleans.SignalR when a distributed .NET application needs Orleans-based coordination of SignalR real-time messaging, hub delivery, and grain-driven push flows.

Use ManagedCode.Storage when a .NET application needs a provider-agnostic storage abstraction with explicit configuration, container selection, upload and download flows, and backend-specific integration kept behind one library contract.

Build, review, or migrate .NET MAUI applications across Android, iOS, macOS, and Windows with correct cross-platform UI, platform integration, and native packaging assumptions.

Adopt MCAF governance in a .NET repository with the right AGENTS.md layout, repo-native docs, skill installation, verification rules, and non-trivial task workflow. Use when bootstrapping or updating MCAF alongside the dotnet-skills catalog.

Apply MCAF agile-delivery guidance for backlog quality, roles, ceremonies, and engineering feedback. Use when defining how the team plans, tracks work, and turns feedback into durable improvements.

Apply MCAF developer-experience guidance for onboarding, F5 contract, cross-platform tasks, local inner loop, and reproducible setup. Use when the repo is hard to run, debug, test, or onboard into.

Apply MCAF documentation guidance for docs structure, navigation, source-of-truth placement, and writing quality. Use when a repo’s docs are missing, stale, duplicated, or hard to navigate, or when adding new durable engineering guidance.

Apply MCAF human-review-planning guidance for a large AI-generated code drop by reading the target area, tracing the natural user and system flows, identifying the riskiest boundaries, and prioritizing the files a human should inspect first. Use when the codebase is too large to

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.

Use MCP Inspector to connect to local or remote servers, inspect capabilities, call tools, read resources, test prompts, and diagnose failures before release.

Panic-rollback button — reverses /migrate-all-to-hardened by restoring every MCP server from its archived original. Sequential to avoid ~/.claude.json collisions.

Batch-run all LLM eval cases in tools/evals/cases/*.json; aggregate pass/fail, cost, regression vs last run; exit nonzero in CI mode

Run golden-test eval suites against one or all MCP servers in mcp-servers/; compares actual tool responses to expected via exact-match + regex + min-count tiers; supports mock-mode so CI runs without API keys

One-line SaaS — from a description, scaffold a complete CF-native multi-tenant SaaS (Hono + D1 + Drizzle + Better Auth + Stripe + shadcn) deployed to a real URL

Unified supply-chain audit. Checks GitHub Actions SHA-pinning (`sha-pin:check`), package.json git+https deps (per `no-gitlab-megabytelabs-deps` semgrep), gitleaks scan, and trufflehog verified-only sweep. Surfaces any tag-mutable, git-URL, or secret-exposed surface. Per rules/ai-agent-security.md § Supply chain.

Run a learning pass after a major run; fold reusable lessons into global config

Summarize recent CHANGELOG.md entries for context restoration. Parses the canonical heading shape `## YYYY-MM-DD — pass-N — summary`. Filters: last N (default 10), YYYY-MM date prefix, or "today". Supports --json for machine-readable output.

Run quality-scores + token-budget + dep-graph, interpret results, flag missing budgets, orphans, and oversize skills

Apply a reusable lesson to ~/.agentskills (rules/skills/templates/commands), backup + commit + push

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

Resolve a 3CX contact or extension by email, extension, or name

Quick health check for a connected 3CX PBX

Snapshot of 3CX queue staffing and active call load

Review and triage abuse mailbox cases in Abnormal Security

Search for specific threat patterns in Abnormal Security by sender, recipient, attack type, or keywords

Triage recent email threats detected by Abnormal Security by severity and attack type

List open and overdue Alternative Payments invoices and optionally generate hosted payment links for them

Reconcile an Alternative Payments payout by listing its transactions and matching them against invoices and customers

EOL/EOS risk report — devices, OS versions, and firmware approaching or past end-of-life/end-of-support, prioritized by criticality

Forward-looking hardware refresh calendar for the given window — replace-now / plan-this-year / monitor tiers

Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat ap…

Governance framework for AI coding agents. It runs them through a five-step workflow (plan, build, review, test, ship) where no step counts as done without evid…

Ultimate Multi-Agent OS for Autonomous AI NPCs 2026

Personal AI Agent Hub 2026 — Build Your 24/7 Autonomous Assistant

Proven 2026 Multi-Agent AI Review System – Verdict-Driven Quality Control

Slash API Batch: Cut AI Costs by 50% in 2026

Web dashboard for Hermes Agent — multi-platform AI chat, session management, scheduled jobs, usage analytics

Agent Skills for Solopreneurs

AirLLM dramatically reduces inference memory usage, letting 70B large language models run on a single 4GB GPU card

Zero, your trustworthy AI teammate for real work.

一套 DSH runtime，Desktop、Web 与 TUI 三种开发体验。

Open-source operational advisor for ClickHouse — real-time monitoring plus AI-driven index/partition/materialized-view recommendations.

⚙️ TypeScript Style Guide and Agent Skill. A concise set of conventions and best practices for consistent, maintainable code.

Framework for AI agents to build and maintain a digital brain through Obsidian wiki

Apache Maka (Incubating) is a local-first AI agent workspace. Model messages, tool calls, tool results, permission decisions, and termination events are recorde…

Neo.mjs is a self-evolving software organism: a professional end-to-end AI engineering team whose cross-model swarm inhabits live apps via Neural Link, Active H…

Agentic development harness for Claude Code — SPEC-driven plan/run/sync, TRUST 5 quality gates, model+effort routing, and Claude×GLM multi-LLM cost control. Sin…

NocoBase is an open-source AI + no-code platform for building business systems fast. Instead of generating everything from scratch, AI works on top of productio…

An open-source AI coding agent that lives in your terminal.

PawWork — free, open-source desktop AI agent for macOS and Windows. Alternative to Codex App and Claude Cowork. BYOK with 75+ providers, ChatGPT OAuth, local mo…