LLM Mart Basic

When GitHub Actions fails, fetch failing job logs and assign each failing job to a separate subagent that fixes its slice of the problem in parallel. Use for multi-job CI failures where jobs are independent.

Run four parallel read-only subagents that each review the same diff from a different lens — security, performance, correctness, and readability — then merge findings into one report. Use before merging large or risky PRs.

Explore a large codebase in parallel by launching multiple explore subagents that each investigate a different area simultaneously. Use when onboarding onto a new project, understanding architecture, or investigating a cross-cutting concern.

When multiple tests fail, assign each failing test file to a separate subagent that fixes it independently in parallel.

Profile a running web application's CPU performance using Cursor's built-in browser profiler. Captures call stacks, identifies slow functions, and suggests optimizations. Use when a page feels slow or janky.

Write effective prompts for LLMs — structure, few-shot examples, chain-of-thought, system prompts, and output parsing.

Test-driven development in Python using uv as the package manager. Covers the red-green-refactor cycle, vertical slicing, and uv project setup.

Build mobile apps with React Native and Expo — navigation, platform-specific code, performance, and native modules.

Execute a user flow step-by-step in Cursor's built-in browser while documenting each action, then emit a Playwright test that replays the same flow using stable selectors derived from the accessibility tree.

Open the app in Cursor's browser at multiple viewport sizes, screenshot each, and report any layout breakage.

Perform a thorough code review focused on correctness, maintainability, performance, and best practices.

Automatically persist useful context — research, decisions, learnings, templates — to workspace files so knowledge survives across conversations.

Generate a visual changelog or PR description by taking before/after screenshots of UI changes using Cursor's built-in browser. Use when preparing a PR with visual changes.

Audit technical SEO — meta tags, structured data, Open Graph, sitemaps, robots.txt, performance, and accessibility signals.

Set up a GitHub Actions CI/CD pipeline with linting, testing, type-checking, and deployment steps.

Set up Terraform infrastructure-as-code for cloud resources, including provider configuration, modules, state management, and CI integration.

When the user keeps asking for the same check to run (lint, tests, type-check), suggest a Cursor hook to automate it.

When the user repeats the same correction or convention multiple times, suggest a Cursor rule to encode it permanently.

When the user struggles with a task that a known skill could handle, suggest installing it.

Switch the current Cursor workspace to a different project directory using the cursor-app-control MCP. Use when the user asks to switch projects, open another repo, jump to a different codebase, or move to a worktree.

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.

Build an MCP server in TypeScript with focused tools, validated schemas, local and remote transports, Inspector tests, and production security controls.

An MCP server exposes tools, resources, or prompts through a standard protocol so an AI application can discover and use external capabilities.

`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

AI coding platform for teams

AI Multi-Agent Framework in .NET

Production-ready code examples for Telnyx AI Communications Infrastructure — Voice AI, SMS, SIP, and IoT APIs

UltraGameStudio - AI coding agent for game development: engine workflows, gameplay code, and asset generation.

🦞 ResearchClawBench: Evaluating AI Agents for Automated Research from Re-Discovery to New-Discovery

The context-aware model router that learns & adapts to your long-horizon coding agent workflows. Lightweight & extensible, works with any harnesses, any models,…

Open-source sandboxes where coding agents build and deploy. Spin up isolated environments where Claude Code, Cursor, and other agents code and deploy software.

Native desktop UI for Claude Code with orchestration, streaming, background agents, and multi-provider support. Built with Tauri + React.

OpenCode mobile client via Telegram: run and monitor AI coding tasks from your phone while everything runs locally on your machine. Scheduled tasks support.

Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.

Exposes internet search tools for use by LLM-backed Assist in Home Assistant

Templates and workflow for generating PRDs, Tech Designs, and MVP and more using LLMs for AI IDEs

Versus Incident is the self-hosted AI SRE agent. It learns what your system normally look like and escalates only what is new or unexpected issues — routing to…

Browser-native side panel for Hermes Agent — connect web context to your local Hermes runtime.

Agentic-friendly CLI generator for APIs: turn Swagger, OpenAPI, and google.api.http protos into single-binary CLIs with catalogs and generated Skills.

Open-source agent platform for Global × China enterprises — wire every system through one agent core. Self-hosted, any LLM.

Official python implementation of UTCP. UTCP is an open standard that lets AI agents call any API directly, without extra middleware.

An agent small enough to run anywhere. A minimal agentic runtime in C — ~380 lines, 54KB binary, ~2MB RAM. A skill file + an LLM + a shell loop, no framework.

AgentiLoop Agent! An Autonomous Agentic Agent for Mac, and exclusive Apple only harnesss. Suppprtd automation, scripting, coding, build anything and more. Power…

微信公众号 AI 运营助手 | 选题、写稿、审稿、排版、配图、发布全流程 Skill，支持 OpenClaw / Claude Code / Cursor / Codex