LLM Mart Basic

Observability patterns for Python applications. Triggers on: logging, metrics, tracing, opentelemetry, prometheus, observability, monitoring, structlog, correlation id.

pytest testing patterns for Python. Triggers on: pytest, fixture, mark, parametrize, mock, conftest, test coverage, unit test, integration test, pytest.raises.

Python type hints and type safety patterns. Triggers on: type hints, typing, TypeVar, Generic, Protocol, mypy, pyright, type annotation, overload, TypedDict.

Modern R for data analysis and statistics — tidyverse-first (dplyr, tidyr, ggplot2, native |> pipe), with base R and data.table as alternatives. Triggers on: R, Rstats, tidyverse, dplyr, tidyr, ggplot2, pivot/join/group, data.table, purrr map, broom, renv, Quarto.

React development patterns, hooks, state management, Server Components, and performance optimization. Use for: react, hooks, useState, useEffect, jsx, tsx, server components, RSC, zustand, react query, component patterns, react testing library, error boundary, suspense, react 19.

Safe refactoring patterns - extract, rename, restructure with test-driven methodology and dead code detection. Use for: refactor, refactoring, extract function, extract component, rename, move file, restructure, dead code, unused imports, code smell, duplicate code, long function

Transparent-PNG cutouts / background removal for flat illustration, sticker, cartoon and avatar art — rembg (isnet-anime) with a deterministic fallback ladder for the cases ML drops. Triggers on: rembg, remove background, background removal, transparent PNG, cutout, die-cut stick

Audit any repo against the agentic-quality doctrine — score entry docs, structure, and enforcement gates, then map each finding to its fix. Triggers on: repo doctor, repo audit, agentic quality, is this repo agent-friendly, doc drift, stale AGENTS.md, monorepo structure, nested C

Quick reference for RESTful API design patterns, HTTP semantics, caching, and rate limiting. Triggers on: rest api, http methods, status codes, api design, endpoint design, api versioning, rate limiting, caching headers.

Code review with semantic diffs, expert routing, and auto-TaskCreate. Triggers on: code review, review changes, check code, review PR, security audit.

Rust development patterns, ownership, async, error handling, and ecosystem. Use for: rust, cargo, ownership, borrow checker, lifetime, tokio, serde, trait, Result, Option, async rust, crate, derive, impl, enum, pattern matching, Arc, Mutex, Send, Sync, thiserror, anyhow, clap, ax

Find and display recent screenshots. Triggers: screenshot, check screenshot, show screenshot, recent screenshot, last screenshot.

Generate PhD-level expert-agent prompt files (.md) for Claude Code - authoring, not runtime. For spawning parallel RUNTIME workers use fleet-worker/fleetflow (via parallel-ops). Triggers: spawn agent, create agent file, generate expert prompt, new agent persona.

Quick reference for common SQL patterns, CTEs, window functions, and indexing strategies. Triggers on: sql patterns, cte example, window functions, sql join, index strategy, pagination sql.

SQLite across every host and engine - query performance, concurrency, schema, feature modules, operations. Triggers on: sqlite, slow query, EXPLAIN QUERY PLAN, query plan, SCAN vs SEARCH, covering index, index not used, rows read, rows_read, sql_duration_ms, ANALYZE, sqlite_stat1

Search code by AST structure using ast-grep. Find semantic patterns like function calls, imports, class definitions instead of text patterns. Triggers on: find all calls to X, search for pattern, refactor usages, find where function is used, structural search, ast-grep, sg.

Claude Desktop session toolbox: transfer sessions between accounts, recover an old session via a picker + AI handover brief, rebind cwd after a folder move, audit broken bindings, render an in-chat picker. Triggers on: summon, transfer/recover session, session picker, rebind, ses

Recolour, vectorise, and theme any SVG to a brand palette with a zero-dependency studio that emits a copy-paste CSS filter. Triggers on: recolour svg, brand tint an svg, duotone svg, recolour a diagram, cloudcraft/draw.io/figma svg to brand, svg css filter, png to svg, vectorise

Tailwind CSS utility patterns, responsive design, component patterns, v4 migration, and configuration. Use for: tailwind, tailwindcss, utility classes, responsive design, dark mode, tailwind v4, tailwind config, tw, container queries, @apply, prose, typography, animation.

Run project commands with just. Check for justfile in project root, list available tasks, execute common operations like test, build, lint. Triggers on: run tests, build project, list tasks, check available commands, run script, project commands.

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 inspect` prints the full record for a single lease: state, provider,

Run named, repo-local jobs defined in your Crabbox config.

`crabbox list` shows the current Crabbox machines (leases) for a provider. It is

`crabbox login` authenticates the CLI against a coordinator, stores the

`crabbox logout` clears the stored broker token from your user config so the CLI

`crabbox logs` prints the retained command output for a recorded run.

`crabbox marketplace` previews the Crabbox credits gateway: one Crabbox billing

`crabbox media` turns a recorded desktop video into lightweight review

`crabbox open` prepares an existing SSH-capable lease for an external editor.

`crabbox pause` pauses a single lease, freeing the remote compute while

`crabbox pond` is the cross-provider peer-discovery and lifecycle surface for a

`crabbox pool` contains machine-pool helpers. `pool list` keeps the older

`crabbox ports` bridges provider-native port publishing for an existing Crabbox

`crabbox prewarm` leases a reusable box and prepares it for test runs. For

`crabbox providers` prints the provider capability matrix that the CLI compiles

`crabbox receipt <run-id>` retrieves a brokered run's committed terminal

`crabbox results` prints the structured test summary attached to a recorded

`crabbox resume` resumes a lease previously paused with [`pause`](pause.md),

`crabbox run` syncs the current dirty checkout to a box, runs a command there,

`crabbox screenshot` captures a single PNG from a desktop lease without opening a

Your efficient agentic AI coding CLI assistant

AI coding with Aegis governance built into execution: baseline-aware changes, evidence-backed delivery. Free desktop client, your choice of model. 将哲科思维融入 AI 开发…

Android in docker solution with noVNC supported, video recording, mcp server and AI-agent

Your AI assistant, built for the agentic era. Open source and local: talk to it, and it runs your agents, your coding CLIs, your browser and your apps. Windows,…

Verifiable program-level self-evolution for AI-for-Science agents: Skills and typed Operators grow from replay-verified executions.

Let Claude Code and other coding agents drive and debug Chrome from the shell. DOM, network, console and raw CDP as short commands, no screenshots and no MCP ne…

Unofficial, agent-friendly Mercadona shopping CLI (Go) — search products, read prices, build a cart and prepare checkout from the terminal. BYO credentials.

Local-first AI canvas for visual workflows, AI short drama, image/video generation, storyboarding and asset management. ComfyUI, AI agents, MCP & Blender. 本地优先…

Let any AI coding tool — Claude Code, Cursor, Codex — drive your real Chrome. One-prompt setup, muscle memory, local-first.

runs anywhere. uses anything