LLM Mart Basic

Apply MCAF ML/AI delivery guidance for data exploration, feasibility, experimentation, testing, responsible AI, and operating ML systems. Use when the repo includes model training, inference, data science workflows, or ML-specific delivery planning.

Apply MCAF non-functional-requirements guidance to capture or refine explicit quality attributes such as accessibility, reliability, scalability, maintainability, performance, and compliance. Use when a feature or architecture change needs explicit quality attributes and trade-of

Apply MCAF source-control guidance for repository structure, branch naming, merge strategy, commit hygiene, and secrets-in-git discipline. Use when bootstrapping a repo, tightening PR flow, or documenting branch and release policy.

Apply MCAF UI/UX guidance for design systems, accessibility, front-end technology selection, and design-to-development collaboration. Use when bootstrapping a UI project, choosing front-end stack, or tightening design and accessibility practices.

Build or consume Model Context Protocol (MCP) servers and clients in .NET using the official MCP C# SDK, including stdio, Streamable HTTP, tools, prompts, resources, and capability negotiation.

Use Metalint in .NET repositories that ship Node-based frontend assets and want one CLI entrypoint over several underlying linters. Use when a repo wants to orchestrate ESLint, Stylelint, HTMLHint, and related frontend checks from a single checked-in `.metalint/` configuration.

Use the open-source free `Meziantou.Analyzer` package for design, usage, security, performance, and style rules in .NET. Use when a repo wants broader analyzer coverage with a single NuGet package.

Build .NET AI agents and multi-agent workflows with Microsoft Agent Framework using the right agent type, threads, tools, workflows, hosting protocols, and enterprise guardrails.

Use the Microsoft.Extensions stack correctly across Generic Host, dependency injection, configuration, logging, options, HttpClientFactory, and other shared infrastructure patterns.

Build provider-agnostic .NET AI integrations with `Microsoft.Extensions.AI`, `IChatClient`, embeddings, middleware, structured output, vector search, and evaluation.

Design and implement Minimal APIs in ASP.NET Core using handler-first endpoints, route groups, filters, and lightweight composition suited to modern .NET services.

Work on C# and .NET-adjacent mixed-reality solutions around HoloLens, MRTK, OpenXR, Azure services, and integration boundaries where .NET participates in the stack.

Use ML.NET to train, evaluate, or integrate machine-learning models into .NET applications with realistic data preparation, inference, and deployment expectations.

Write modern, version-aware C# for .NET repositories. Use when choosing language features across C# versions, especially C# 13 and C# 14, while staying compatible with the repo's target framework and `LangVersion`.

Write, run, or repair .NET tests that use MSTest. Use when a repo uses `MSTest.Sdk`, `MSTest`, `[TestClass]`, `[TestMethod]`, `DataRow`, or Microsoft.Testing.Platform-based MSTest execution.

Implement the Model-View-ViewModel pattern in .NET applications with proper separation of concerns, data binding, commands, and testable ViewModels using MVVM Toolkit.

Use the open-source free `NetArchTest.Rules` library for architecture rules in .NET unit tests. Use when a repo wants lightweight, fluent architecture assertions for namespaces, dependencies, or layering.

Write, run, or repair .NET tests that use NUnit. Use when a repo uses `NUnit`, `[Test]`, `[TestCase]`, `[TestFixture]`, or NUnit3TestAdapter for VSTest or Microsoft.Testing.Platform execution.

Build or review distributed .NET applications with Orleans grains, silos, persistence, streaming, reminders, placement, transactions, serialization, event sourcing, testing, and cloud-native hosting.

Use the free official .NET diagnostics CLI tools for profiling and runtime investigation in .NET repositories. Use when a repo needs CPU tracing, live counters, GC and allocation investigation, exception or contention tracing, heap snapshots, or startup diagnostics without GUI-on

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.

Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

Agent OS: the agent gets smarter on its own. We just hold the line: the grading command and expected result never make it into the success contract we hand it.…

Curated systems, benchmarks, and papers etc. on memory for LLMs/MLLMs --- long-term context, retrieval, and reasoning.

:memo: Vimlike Modal Text Editor in Rust

CI-native security testing for MCP servers. Attack simulation, schema drift detection, and health scoring before agents depend on them.

Hermes Agent memory plugin/provider for scope-aware recall, SQLite truth, LanceDB semantic search, and hybrid retrieval.

For You Agent——AI 时代的个人随身数字人格。把你的模型、AI 账号、技能、提示词和工作方式，带到每一个 AI 工具里。

A coding agent: give it a prompt and it reads, writes, runs commands, and searches code in a loop until the work is done, using native tool-calling across OpenA…

A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord, Teams, and…

Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

DeepSeek Harness Desktop (dsh-desktop). EAC: Embracing All Creation (揽尽万象). Bundled Node.js runtime with full dsh-CLI kernel, one-click startup, 10 built-in UI…

See your agent think. Zero-config observability & governance for 26 AI agent runtimes: Claude Code, Cursor, OpenAI Codex, GitHub Copilot, Gemini CLI, Cline, Ope…

Save 94% on AI coding tokens. Index your codebase, agents search instead of reading files. Works with Claude Code, Codex, Copilot, Cursor, Gemini CLI. Local MCP…

Yet another coding agent harness, lightweight and written in go.

a coding Agent from pi. ∞ providers, sub-agents, hashline edits, and a permission gate

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting…

🧠 Leon is your open-source personal assistant.

The Station, an open-world multi-agent environment that models a miniature scientific ecosystem.

The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Protocol

VelaTerm = iTerm2 + Codex, The Best Terminal for AI Coding