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.

{{SKILL_ENTRY:refactor}}

{{SKILL_ENTRY:release}}

Review a diff with the reviewer fleet, funneled to one triaged verdict. Targets the current working diff, a path, or an inbound GitHub PR.

Exploratory spike on a throwaway branch — answer a named question with disposable code. Never merges; exits to a findings note or {{CMD:feature}}.

Autonomous sprint — one interactive spec gate, then plan-to-PR execution with every auto-decision SMARTS-scored and logged. Hard gates remain true stops.

Daily repo hygiene — review the day's repo state, then perform the cleanups under per-action confirmation. Fast-forward only, never destructive without a yes.

Show the project's current state at a glance — stage, open tasks, open questions, overrides since the last checkpoint, current branch. Read-only.

Wire codeArbiter's statusline into ~/.claude/settings.json, or remove it.

The sanctioned task-board mutator — add a queued task, start one (flips to in-progress and stamps the date, minting a dotted ID on pick-up), or mark an in-progress task done. The only blessed write to open-tasks.md.

{{SKILL_ENTRY:security-architecture}}

{{SKILL_ENTRY:tribunal}}

Watch a PR's CI to completion — diagnose on red, notify and offer the merge on green. Never auto-merges.

Copy a file OUT of a running sandbox box to the host — host-initiated egress only (docker cp). The reverse, a host→container bind, is impossible by construction.

Tear down a sandbox box — remove its container and named volume. --keep-volume leaves the volume; with no id, prune reclaims any leaked ca.sandbox=1-labeled object. Cached images are retained.

Run a single command inside a running sandbox box and capture a JSON result — exitCode, separate stdout/stderr, and a truncated flag past the byte cap. The scriptable exec seam.

Open an interactive shell inside a running sandbox box at /work/repo. Read-only root, non-root user, no host-FS access — explore the untrusted code interactively, then exit.

Pull an untrusted repo into an ephemeral, host-FS-isolated Docker container — clone into a named volume, build a dep-cached image, run under structural isolation. Network defaults to offline. Requires Docker and nixpacks.

Vet a new or changed third-party dependency for license, provenance, and supply-chain risk before any install runs.

Inspect ADR health read-only; optionally select one ADR with --adr N.

Record user-decided ADRs or inspect their health read-only. Preserve attribution and acceptance evidence.

Atom Agent, Open-Source Governed AI Agent Platform for Self-Hosted Automation

The agent engineering intelligence harness, optimized tools, memory system, subagents and mixture of models packages ⚚

Sesori iOS/Android app and the Sesori Bridge CLI — drive Claude, Codex, OpenCode, Cursor, Pi, OMP, Hermes coding sessions from your phone

🧠 RepoBrain (formerly Antigravity) — Give your repo a brain. ChatGPT for your codebase: works in Claude Code, Cursor, Codex, Windsurf & more.

Use ChatGPT (Codex), Claude, and Grok (X Premium) subscriptions as DeepSeek Harness LLM providers — OAuth login in the web UI, no API keys

Latitude is the open-source AI monitoring platform.

Open-source AI browser agent for Chrome and Firefox (monorepo) 🧠

Official Model Studio CLI（阿里云百炼 CLI）built for AI Agent frameworks, exposing models, search, multimodal, and workflow capabilities as structured tool calls.

Curated DeepSeek Harness (DSH) plugins, extensions, tools, skills, clients, runtimes, integrations, and verified references — English and Chinese.

Turn papers, code, and docs into presentation-ready, natively editable PPTX in Codex / Claude Code. Native charts and equations, speaker notes, click-build anim…

Grix : Work with agents like talking to people.

Local First Ai Agent. Optimized for Local Ai models. Long context window. Proper tools callings. Runs privately on your device.

Model Context Protocol server that integrates AgentQL's data extraction capabilities.

AI that ships your tickets.

Metadata-driven CLI for AI Agent Bots — 48 operations across 7 domains, structured JSON envelope I/O, zero interactive prompts.

An open-source, extensible, self-hosted agent workspace with multi-runtime support for Codex, Claude Code, and more, plus reusable local apps for custom interfa…

Open-source Windows desktop client and GUI for DeepSeek Harness — zero-setup installer with Codex, plugins, skills, SSH, mobile remote access, and 11 skins.

The open-source AI workbench for scientific research

DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.

A Fully free agentic browser driver for AI , few tools, full control, real stealth, top-tier token efficiency.