LLM Mart Basic

Tailwind CSS v4 patterns, component styling, dark mode, responsive design, and design system integration. Use when styling components or reviewing CSS.

TDD red-green-refactor cycle, test structure, mocking patterns for Vitest/Jest. Use when starting a new feature, fixing a bug, or refactoring — write the test first, then the implementation.

TypeScript type system patterns, generics, utility types, and strict mode best practices. Use when writing or reviewing TypeScript code.

Web design best practices, accessibility, responsive layout, color contrast. Use when auditing a UI for a11y compliance, designing responsive layouts, or establishing design standards across a web app.

Playwright E2E patterns, Testing Library component tests, test selectors. Use when writing browser tests, component tests, or setting up an E2E testing pipeline for a Next.js or React app.

Generating Excel files with xlsx/exceljs in Node.js. Use when generating .xlsx reports, data exports, dashboards, or spreadsheets from database data.

Reports on the health and state of architecture documentation (counts of ADRs, reviews, activity levels, documentation gaps). Use when the user asks "What's our architecture status?", "Show architecture documentation", "How many ADRs do we have?", "What decisions are documented?"

Creates a NEW Architectural Decision Record (ADR) documenting a specific architectural decision. Use when the user requests "Create ADR for [topic]", "Document decision about [topic]", "Write ADR for [choice]", or when documenting technology choices, patterns, or architectural ap

Displays the roster of architecture team members with their specialties and expertise areas. Use when the user asks "Who's on the architecture team?", "List architecture members", "Show me the architects", "What specialists are available?", "Who can I ask for reviews?", or wants

Enables and configures Pragmatic Guard Mode (YAGNI Enforcement) to prevent over-engineering. Use when the user requests "Enable pragmatic mode", "Turn on YAGNI enforcement", "Activate simplicity guard", "Challenge complexity", or similar phrases.

Statistical significance calculator for A/B test results with sample size requirements, segment breakdowns, and hypothesis generation. Use when feeding test results, checking statistical significance, calculating sample sizes, analyzing experiment outcomes, or generating next tes

Designs statistically valid split tests for ads, audiences, landing pages, or bid strategies. Calculates required sample sizes before you start, monitors results during the test, and calls winners when statistical significance is actually reached — not when you feel like one is w

Evaluates your campaign and ad set structure against your actual goals and budget. Flags over-segmentation that fragments your data, under-segmentation that hides performance differences, budget allocation issues, and consolidation opportunities that would improve algorithmic del

Analyzes your top performing ads, identifies what's working in the hooks, CTAs, messaging angles, and formats, then generates new variants that follow the same winning patterns while introducing enough variation to test meaningfully. Platform: Google and Meta.

Reviews all your Google Ads extensions — sitelinks, callouts, structured snippets, call extensions, image extensions, price extensions — across every campaign. Flags what's missing, what's underperforming, what's outdated, and writes replacements based on your best performing ads

Multi-channel budget optimization using MER, marginal ROAS, and diminishing returns analysis. Use when pasting multi-channel spend and results data, requesting reallocation recommendations, analyzing budget shift priorities, or optimizing marketing efficiency across Google, Meta,

Audit how visible your brand is inside AI answers (ChatGPT, Claude, Gemini, Perplexity, AI Overviews). Claude builds a prompt panel for your category, scores where you show up vs competitors, and turns the gaps into a prioritized fix list. Platform: AI visibility.

Catches unusual performance changes across your accounts — CPC spikes, CVR drops, spend surges, impression collapses, CTR shifts — and flags them with context about what likely changed. The goal is to catch problems in hours instead of discovering them days later during a routine

Runs your conversion data through different attribution models side by side — last click, first click, linear, time decay, position based, and data-driven. Shows you how credit shifts between campaigns depending on the model so you can make better budget decisions instead of over

Compares your Meta ad sets and identifies where audiences overlap significantly, causing your ads to compete against each other in the same auctions. Tells you exactly which ad sets are cannibalizing each other and how much it's costing you in inflated CPMs. Platform: Meta.

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.

Trim transcript clutter to extend session lifetime — analyze, prune a copy, or toggle the after-each-turn service. Dry-run by default; gains land at resume/compaction, not the current turn.

Inspect architectural variances with SMARTS; record only explicit user choices. Report-only requests make no changes.

Restructure code without changing observable behavior: rename, extract, inline, move, deduplicate, or replace an internal implementation with an equivalent one. Prove parity through unchanged pre-existing tests. Not for new behavior, bug fixes, explanation-only questions, or committing finished work.

Prepare a declared release target, or preview it with --dry-run. Derive its version and require authorization before publication.

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 /ca: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.

Threat-model a sensitive design with STRIDE on request. Read-only analysis of threats, controls, and implementation constraints.

Run an opt-in deep codebase audit with persisted findings. Confirm cost before dispatch; filing and telemetry need separate approval.

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

Reviews a new or changed third-party dependency before adoption. The read-only

A read-only health scan of every recorded ADR under `.codearbiter/decisions/`. For each one it

Records an architectural decision as a numbered, dated ADR under `.codearbiter/decisions/`.

Assembles everything codeArbiter logs — `overrides.log`, `triage.log`, `decisions/`,

The one exception to codeArbiter's slash-command pipeline: a lightweight question-and-answer

A periodic whole-repository review. The caller supplies the reviewer unit list to

Offline-first Python AI agent that runs a tiny research business: quotes each job against its own costs, collects via Stripe, fulfils with NVIDIA Nemotron, pays…

DSH 插件 · 注入式优化器 0.8（主线）：你照常说话，它在你发送后,AI接收前把"这一轮到底要什么"理清楚，再把这份理解交给工作 AI(上下文注入) —— 原话不改写，条条带逐字依据。含控制界面（档位/权限/模型/上下文/只读工具）、拦截浮层（思维层+产出层）与真实 token 用量。可明显提升大多数模型的发挥稳…

Reliable AI Skill + MCP toolkit for agent-driven desktop CAD automation.

Curated real-world use cases for Hermes Agent — the self-improving AI agent from Nous Research. Backed by primary sources.

AI Agent 教学仓库 | 系统化 LangChain、RAG、LangGraph、MCP 全栈实战代码 | 万字博客详解 | 开源可运行示例 | 从零构建智能体

从 0 复刻 WorkBuddy-style 桌面 AI 助手 Harness：24 章 Python 教程，覆盖 Agent Loop、工具调用、记忆系统、Sidecar、沙盒审计、DeepSeek/OpenAI 评测轨迹

MCP server and CLI tools for web search and crawling, built on SearXNG and Crawl4AI

Delta MCP is a free app that sits between your AI apps and their MCP servers: one program per task instead of one tool call per step, up to 24.1× fewer tokens i…

Ava turns any Android 5+ device into a voice-first Home Assistant kiosk. Native C++ under the hood, so a 10-year-old tablet still listens, talks, and runs the h…

Roblox Studio macOS Window Capture Fix 2026: Real Screenshot Tool Instead of Magenta Playtest Glitch

LabTether