LLM Mart Basic

Handles customer situations that have exceeded normal support — severity assessment, incident communication, executive escalation, and recovering a relationship after a failure. Use this when a customer issue is escalating or has gone to leadership, during a customer-affecting ou

Builds the help center, in-product guidance, and knowledge base that let customers resolve problems without contacting anyone — content, findability, maintenance, and deflection measurement. Use this to build or fix a help center, reduce support volume, write documentation for cu

Designs and runs the support function — channels, queues, routing, staffing, service levels, quality, and the metrics that show whether it is working. Use this to set up or fix support operations, choose channels, size a team, set or renegotiate service levels, reduce cost per co

Builds the loop from what customers say to what gets changed — collecting feedback, distinguishing signal from noise, routing it to owners, and closing the loop back to the customer. Use this to set up a feedback program, design or interpret CSAT/NPS, decide what customer feedbac

Governs models and AI systems in production — intended use, evaluation, monitoring, human oversight, documentation, and the decision to deploy or retire. Use this before deploying a model or AI feature, when defining evaluation criteria, when a model's behavior has drifted, when

Builds reporting and self-serve analytics that people actually use — metric trees, dashboard design, distribution, and the discipline that stops dashboards proliferating. Use this to build a dashboard or report, design a metrics framework, set up self-serve analytics, decide what

Owns data as an asset — governance, quality, the warehouse and semantic layer, analytics capability, and the governance of models built on top. Use this for a decision about how data is collected, stored, defined, or shared; when numbers disagree between teams; when deciding what

Builds and operates data pipelines — ingestion, transformation, orchestration, quality testing, and reliability of data delivery. Use this to design or debug a pipeline, decide batch versus streaming, add data quality checks, handle late or duplicate data, or work out why a dashb

Establishes ownership, definitions, quality, access, and lineage for the organization's data. Use this when metrics disagree between teams, when nobody knows which dataset is authoritative, when setting up data ownership or access policy, when data quality is unreliable, or befor

Designs the warehouse and semantic layer — source-to-mart structure, dimensional modeling, grain, slowly changing dimensions, and the metric layer analytics reads through. Use this to design or restructure a warehouse, model a new source, decide on grain or table structure, build

Owns where the business plays and how it wins over a multi-year horizon — portfolio choices, corporate development, strategic partnerships, and planning under uncertainty. Use this for a decision about which markets or businesses to be in, whether to build, buy, or partner, how t

Runs corporate development — deal thesis, target screening, valuation framing, diligence, and integration planning. Use this when considering an acquisition or being approached about one, when evaluating build-versus-buy at company scale, when running or reviewing diligence, or w

Decides where capital and attention go across business lines, products, and markets — what to fund, hold, harvest, or exit, and on what evidence. Use this to allocate budget across businesses, evaluate whether a product line should continue, decide market entry or exit, structure

Plans under genuine uncertainty — building scenarios, identifying which assumptions are load-bearing, setting early-warning indicators, and stress-testing a plan against futures rather than forecasting one. Use this when a decision depends on something unknowable, when a plan ass

Structures partnerships that change what the business can do — technology integrations, channel and reseller arrangements, joint ventures, and OEM relationships. Use this to evaluate or structure a strategic partnership, decide between partnering and building, negotiate commercia

Corporate Strategy (CSO). Owns plugins/corporate-strategy/** and nothing else. Delegate work in this department's remit here.

Customer Experience (CCO). Owns plugins/customer-experience/** and nothing else. Delegate work in this department's remit here.

Data & Analytics (CDO). Owns plugins/data-analytics/** and nothing else. Delegate work in this department's remit here.

Demand Generation (CMO). Owns plugins/demand-generation/** and nothing else. Delegate work in this department's remit here.

Office of the CEO. Owns plugins/executive/** and nothing else. Delegate work in this department's remit here.

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

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