LLM Mart Basic

Creates .NET projects from templates with validated parameters, smart defaults, Central Package Management adaptation, and latest NuGet version resolution. USE FOR: creating new dotnet projects, scaffolding solutions with multiple projects, installing or uninstalling template pac

Applies cross-parameter default rules when creating .NET projects with dotnet new, filling gaps consistently without overriding values the user set explicitly. USE FOR: choosing which target framework to pair with native AOT, deciding whether to keep HTTPS when authentication is

Validates custom dotnet new templates for correctness before publishing. Catches missing fields, parameter bugs, shortName conflicts, constraint issues, and common authoring mistakes that cause templates to fail silently. USE FOR: checking template.json files for errors before pu

MANDATORY for reviewing assertion strength, depth, and variety in existing tests. Invoke when the user asks whether individual assertions are weak, shallow, trivial, always true, self-referential, or diverse; asks which tests are assertion-free or rely only on presence/truthiness

Generate or add unit tests for existing code, from one function to a complete project-wide suite. ALWAYS USE when asked to "write unit tests", "add tests", "generate tests", "cover this untested method", scaffold tests where none exist, or create comprehensive tests across multip

Provides file paths to language-specific extension files for the code-testing pipeline. Call this skill to discover available extension guidance files (e.g., dotnet.md for .NET, cpp.md for C++). Do not use directly — invoked by code-testing agents and skills that need language-sp

Project-wide code coverage and CRAP (Change Risk Anti-Patterns) score analysis for .NET projects. Calculates CRAP scores per method and surfaces risk hotspots — complex code with low coverage that is dangerous to modify. Use to diagnose why coverage is stuck or plateaued, identif

Calculates targeted CRAP (Change Risk Anti-Patterns) scores for a named .NET method, class, or single source file. Use when the user explicitly asks to compute CRAP scores or assess risky untested code for a specific target, combining Cobertura coverage data with cyclomatic compl

Scan C# source files for hard-to-test static dependencies — DateTime.Now/UtcNow, File.*, Directory.*, Environment.*, HttpClient, Console.*, Process.*, and other untestable statics. Produces a ranked report of static call sites by frequency. USE FOR: find untestable statics, scan

Reference data for test filter syntax across all platform and framework combinations: VSTest --filter expressions, MTP filters for MSTest/NUnit/xUnit v3/TUnit, and VSTest-to-MTP filter translation. DO NOT USE directly — loaded by run-tests, mtp-hot-reload, and migrate-vstest-to-m

MANDATORY for static requests to find, identify, or list untested source files or modules, sources without tests, source-to-test pairing, test-gap worklists, or suggested test locations. Invoke even for a tiny package; do not substitute manual globbing. Uses Roslyn for C#/.NET an

Generate wrapper interfaces and DI registration for hard-to-test static dependencies in C#, when the abstraction does NOT exist yet. Produces IFileSystem, IEnvironmentProvider, IConsole, IProcessRunner wrappers, or guides first-time adoption of TimeProvider and IHttpClientFactory

Grades a specified set of test methods individually and produces a concise table mapping each test (fully-qualified name) to a letter grade (A–F), a score band, and a one-line note — designed to be posted as a PR comment. Use when the caller wants per-test feedback on a curated l

Replace existing static dependency call sites with a wrapper or built-in abstraction that already exists or is registered in DI, across a bounded scope (file, project, namespace). USE FOR: replace DateTime.UtcNow/DateTime.Now with TimeProvider and add the constructor parameter, m

Suggests using Microsoft Testing Platform (MTP) hot reload to iterate fixes on failing tests without rebuilding. Use when user says "hot reload tests", "iterate on test fix", "run tests without rebuilding", "speed up test loop", "fix test faster", or needs to set up MTP hot reloa

Detect a .NET project's test platform/framework and SDK-style vs classic project system. ALWAYS USE for "which test platform/framework?", "VSTest or MTP?", a wrong dotnet test runner, or hidden runner settings in global.json, .csproj, packages.config, Directory.Build.props, or Di

Run or recommend the exact .NET test command. ALWAYS USE when asked to run, filter, or troubleshoot .NET tests or provide precise flags/argument order. Supports SDK-style dotnet test and classic non-SDK projects using MSBuild plus vstest.console/MSTest or repository scripts. USE

Create the first .NET test project. USE FOR: "solution has no tests", xUnit tests, Tests.csproj/ProjectReference, add an omitted test project to .sln/.slnx/.slnf, central packages, or tests missing from CI. DO NOT USE FOR: a suitable project already registered in the requested bu

Provides file paths to language-specific reference files for the test ANALYSIS skills (assertion-quality, test-anti-patterns, test-gap-analysis, test-smell-detection, test-tagging). Call this skill to discover available extension files (e.g., dotnet.md for .NET/MSTest/xUnit/NUnit

Audits an existing test file or suite in any language for anti-patterns and quality issues — produces a severity-ranked report (Critical/Warning/Info). INVOKE whenever asked to audit or review tests, find what's wrong with a suite, judge whether tests are any good, or check for:

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.

`crabbox attach` follows the recorded events of an active coordinator run and

`crabbox azure` groups Azure provider setup commands. It currently has a single

`crabbox bench` records and reports local benchmark timing observations. It is a

`crabbox cache` inspects, purges, or warms package and build caches on a

`crabbox capsule` captures, replays, and tracks lightweight failure capsules.

Save the state of a lease, then restore it onto another box or fork it into a

`crabbox claims list` prints the lease claims stored on the current machine. It

`crabbox cleanup` sweeps direct-provider machines and local provider state that

`crabbox code` bridges a Linux lease's `code-server` workspace into the

`crabbox config` inspects and updates user configuration. It has three

`crabbox connect` resolves a lease and opens an interactive SSH session to it.

`crabbox cp` copies files or directories between the host and a Crabbox-owned

`crabbox desktop` drives a visible desktop session on a lease that was warmed

`crabbox doctor` runs a preflight before you commit to a long workflow. It is

`crabbox egress` gives a lease mediated outbound network: a lease-local browser

`crabbox events` prints the broker's event log for a recorded run.

`crabbox heartbeat` refreshes the idle deadline for one owned lease and prints

`crabbox history` lists recorded remote command runs from the broker. Each run is

`crabbox image` holds the trusted-operator controls for provider base images:

`crabbox init` onboards the current repository: it writes the minimal config

Okou connects to the tools your team already uses and does the work — across marketing, sales, engineering, and operations, under your control.

An open-source Digital Worker platform for reliable execution, continuous co-evolution, and building Enterprise AI assets.

A curated list of AI Agent evolution, memory systems, multi-agent architectures, and self-improvement projects. | evomap.ai

A governance harness for AI coding.

DeepSeek Harness 手机版：可直接安装的 Android APK，AI 免 Root 操作手机（Shizuku/root 可选），文件编辑只需所有文件访问权限，前台保活 + AI 通知

Local-first, governed AI agent runtime for Python — embed it in your app, or run it as a CLI or ACP server. Permissions, MCP, memory and audit replay built in.

Orbi — the factory that builds and operates AI software factories. GitHub Issues in, releases and runnable system out

Open-source AI agent harness in native Rust — GUI, CLI, headless, and webapp from one binary. Multi-provider, MCP, skills, plugins, agent teams.

The SDK for browser agents. Interact, search, extract, and fetch any site reliably across the web

Agent-native shopping for extreme value: verifiable same-product price evidence, checkout, orders, delivery, and after-sales.

The extensible power-user platform for Google Antigravity. Adds a native In-App Browser, animated Desktop Pets, revamped Gemini UI, and custom BYOK Gemini Pro k…

Open-source, single-binary, self-hosted AI agent — your models and data stay on your machine. A coding agent on par with Claude Code and a personal assistant li…

Your pocket agent. Local-first AI agents on iOS and Android — real workspaces, tool execution with approvals, and your choice of model (DSH · Claude Code · Code…

Bridge between QQ (SnowLuma OneBot v11) and DeepSeek Harness agents: social simulation, safe MCP tools, slang learning and more.

A 7×6 framework for agent architecture. 28 patterns, each placed at a coordinate, runnable Python code with verified engineering slices from Claude Code, Aider,…

针对 AI 自动化渗透 Agent 的新一代反制蜜罐，通过反向代理将API密饵载入真实业务、反向提示词注入等方式反制自动化渗透 Agent，实现多款主流通用Agent的反制上线控制。

Open-source, local-first AI agent for coding and real work. BYOK models, MCP, skills, plugins, workflows, and private knowledge bases.

A free AI-agent toolbox for Android, 一站式安卓AI Agent工具箱

Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. I…

Independent, unofficial CLI to edit CapCut and JianYing (剪映) projects — subtitles, timing, speed, volume, templates, cut long-form to shorts. No API needed, rea…