LLM Mart Basic

Benchmark clean and incremental Xcode builds, surface compile and configuration hotspots, and produce an approval-first optimization plan before changing project files.

Compare browser-agent reliability on a repeatable task and anti-bot suite before choosing a stack or claiming progress.

Run a repeatable evaluation suite for browser agents against static web task snapshots instead of judging them from demos or one-off tests.

Run Claude Code, Codex CLI, Gemini CLI, or OpenCode through bounded H100 post-training tasks and compare how well each agent improves a base LLM.

Score deep research agents on benchmark tasks using factual verification, report-quality scoring, and process evaluation before model or workflow changes ship.

Use EnterpriseRAG-Bench to evaluate an enterprise RAG or knowledge-agent system against a realistic synthetic company corpus with answer, recall, and comparative scoring.

Run realistic enterprise-style IT scenarios before trusting an automation agent in production operations.

Run CIS benchmark checks against cluster nodes and control planes when an agent needs a narrow Kubernetes hardening audit, not a general platform listing.

Run a real-task benchmark suite against OpenClaw agents so model or harness changes can be compared before they hit production workflows.

Run structured prompt-injection attack and defense experiments against an LLM-integrated app before production by measuring attack success and testing detection or recovery pipelines.

Run concurrent scripted conversations against a target agent to measure whether it stays on task, responds correctly, and holds up in repeatable test cases.

Better Auth is an open source authentication framework for TypeScript apps. It gives agents a concrete way to wire sign-in, sessions, passkeys, OAuth providers, and plugins into modern web stacks with real package and docs support.

A fast, configurable secrets scanner built by the creator of Gitleaks and backed by Aikido Security. Betterleaks detects leaked passwords, API keys, and tokens in git repositories, directories, and stdin with CEL-based validation and parallelized scanning.

Automates migration from ESLint and Prettier to Biome (formerly Rome) by parsing .eslintrc and .prettierrc configs, mapping rules to biome.json equivalents, and running biome check --apply for bulk reformatting.

Generates Blender Python (bpy) scripts that programmatically create Geometry Nodes modifier trees, using the node_groups API and GeometryNodeTree interface for parametric 3D asset generation.

Put an inline firewall and containment layer in front of agent network traffic, tool calls, and MCP traffic before you trust an agent with local secrets.

Add hard pre-execution guardrails to Claude Code so destructive shell commands are blocked before an agent can run them.

Use CC Safety Net when coding-agent CLIs need pre-execution hooks that block destructive commands, secret access, and unsafe file operations before tools run.

Scan staged changes, commits, or repositories for secrets before they leave the workstation or CI job, instead of relying on a later platform-side catch.

Add a runtime guard that evaluates agent actions, blocks dangerous commands or secret exposure, and audits new skills before they run.

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.

Treat an AI agent skill as both an instruction package and a software dependency: inspect what it says, what it runs, what it can access, and how it updates.

Single-tenant Auvik snapshot - devices, alerts, networks, billing usage

Phishing-simulation results and click-rate trend for a given window

Human risk score report for one client or the whole portfolio, built from training completion and phishing-simulation performance

Training completion snapshot for one client or the whole portfolio — completion rates, overdue users, and cadence status

Check backup health for one Axcient-protected device

Backup health overview across every device for one Axcient client

Azure cost and pricing analysis for a subscription — Advisor cost recommendations, retail pricing lookups, and quota-driven right-sizing signals, scoped to one subscription

Resource health and diagnostics triage for an Azure resource or subscription — Resource Health status, AppLens deep diagnostics, and Azure Monitor alert state

Portfolio-wide backup job health snapshot - failure count, at-risk clients, and storage trends

Restore-readiness check - has this actually been restore-tested, for one client or the whole portfolio

Retention and RPO compliance audit against contracted requirements, for one client or the whole portfolio

Create a new Better Stack uptime monitor

Triage current Better Stack incidents

Check all Better Stack monitor statuses and identify downtime

Search logs via Better Stack Logtail

Update a Better Stack status page with current status or maintenance

Investigate a single Blackpoint Cyber / CompassOne detection end-to-end

Portfolio-level Blackpoint Cyber / CompassOne rollup of detections and exposure across all tenants

List recent Blackpoint Cyber detections for a tenant

Build a prioritized exposure report for a Blackpoint Cyber / CompassOne tenant

AI skill for OpenClaw & Claude Code — recommend from 10000+ Nano Banana Pro (Gemini) image prompts. Smart search by use case, content remix, sample images.

嘉立创EDA专业版(EasyEDA Pro)自动化：给 AI harness 装上画板的「手」—— 一套 typed 原理图/PCB 动作，CLI / Agent Skill / stdio MCP 三形态融合接入。承接嘉立创「不以卖板赚钱，以培养中国工程师为己任」 | EasyEDA Pro automation:…

Claude Code session log viewer for JSONL files in ~/.claude/projects. Browse conversations, tool calls, tokens, and live tail sessions on desktop, web, and TUI.

Shared memory MCP server — persistent, searchable, cross-client Claude, Opencode

OpenAI Codex CLI session log viewer for JSONL files in ~/.codex/sessions. Browse conversations, tool calls, tokens, collaboration chains, and live sessions on d…

High-performance Google Drive CLI and Model Context Protocol (MCP) Server for LLM/AI agents. Natively execute Google Apps Script (GAS) under a secure whiteliste…

"Vibe-Trading: Your Personal Trading Agent"

Local-first chat history analyzer with AI. | 本地优先的 AI 聊天记录分析工具

Official Oxylabs MCP integration

Persistent memory for Claude Code & Codex CLI. Auto-extracted knowledge graph, multi-representation embeddings, 3D WebGL visualization. LongMemEval R@5=97.45%.…

One person, a team of agents. Multi-session CLI that collaborates across terminals; /goal keeps long tasks running; WeChat/WeCom/Feishu gateway lets you call th…

AI 基础知识 - GPU 架构、CUDA 编程、大模型基础及AI Agent 相关知识。

Self-hosted, open-source agent skill registry for enterprises. Publish & version skill packages, govern with RBAC and audit logs, deploy on-premise with Docke…

深度调研报告生成 Skill — 一条命令，十分钟出券商级深度调研报告 / Professional deep research report generation Skill · Supports 19 languages

The OKF toolkit for Claude Code — author, maintain, validate & visualize Open Knowledge Format bundles. Plugin, agent skills, and a GitHub Action.

Autonomous AI pentesting agents — real-time reconnaissance, vulnerability detection, and exploitation orchestration. Go + TypeScript.

Native macOS and iOS App for the Hermes AI agent — multi-window, multi-server (local + remote over SSH). Chat, dashboard, sessions, memory, cron, MCP, and more.

Multiplayer Claude Code and Codex. Self-hosted team workspace for Claude Code and Codex. Multi-user, browser-based, AI mates with memory.

Every past session, subagent, and workflow -- queryable by your agent, browsable by you

盯盘侠 PanWatch · 自托管 AI 盯盘助手，集成 TradingAgents 多 Agent 投资决策 | A股/港股/美股实时监控、持仓管理、智能分析、全渠道推送