LLM Mart Basic
@llm-mart · Joined Jun 2026
When the user wants to optimize brand search for a company with multiple domains (e.g. parent company.com vs product.ai). Ensure the parent/company domain ranks first for brand queries. Also use when the user mentions "brand search," "multi-domain SEO," "company domain first," "p
When the user wants to plan, implement, or optimize discount and promotional pricing strategy. Also use when the user mentions "discount strategy," "promo code," "coupon," "redeem code," "lifetime deal," "LTD," "AppSumo," "Black Friday," "Cyber Monday," "BFCM," "seasonal sale," o
When the user wants to plan, design, or optimize pricing strategy and structure. Also use when the user mentions "pricing strategy," "pricing model," "pricing tiers," "freemium," "value-based pricing," "anchoring," "price structure," or "monetization strategy." For pricing page,
Use when assigning Roblox feature ownership, code location, dependencies, startup, or client-server boundaries without imposing a framework.
Load BEFORE any Roblox task, including direct build requests: sets initiative level, when to warn vs act, and which decisions need the user.
Use when implementing player data persistence with DataStore, session ownership, schemas, migrations, or save and load flows.
Use for Luau language semantics, tables, control flow, string patterns, scope, closures, and cross-language translation errors.
Use for Roblox module boundaries, object lifecycles, signals, task scheduling, fallible calls, and cleanup in Luau.
Use for Luau annotations, generics, unions, narrowing, strictness, sealed tables, module type exports, typed metatables, or new-solver features.
Use when validating RemoteEvent or RemoteFunction arguments, adding rate limits, designing server-authoritative systems, or preventing exploits.
Use when profiling Roblox performance or diagnosing FPS, memory, network, mobile, or hot-path problems.
Use when auditing Roblox code for exploit vectors, authority models, remotes, economy, and DataStore flows.
Use for Roblox server or cross-server data: OrderedDataStore leaderboards, MessagingService, world state, seasons, or guilds.
Use when tracking player behavior, economy events, or funnels with AnalyticsService, including event taxonomy, rate limits, and batching.
Use when designing core loops, tutorials/FTUE, levels, economies, retention phases, juice, Bartle balance, grind avoidance, or curation readiness.
Use for growth diagnosis, discovery, retention, onboarding, experiments, LiveOps, and packaging.
Use when implementing Roblox GamePasses, Developer Products, subscriptions, private servers, Creator Rewards, or purchase policy checks.
Use when designing persuasion/behavior mechanics: first minute, reward schedules, streaks, pricing, RNG/pity, community loop.
Use when implementing Roblox character animations, particles, beams, trails, tweens, camera shake, or other visual effects.
Use when implementing Roblox audio playback, spatial sound, music, sound effects, SoundGroups, or dynamic audio effects.
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.
/attach
Attach
`crabbox attach` follows the recorded events of an active coordinator run and
/azure
Azure
`crabbox azure` groups Azure provider setup commands. It currently has a single
/bench
Bench
`crabbox bench` records and reports local benchmark timing observations. It is a
/cache
Cache
`crabbox cache` inspects, purges, or warms package and build caches on a
/capsule
Capsule
`crabbox capsule` captures, replays, and tracks lightweight failure capsules.
/checkpoint
Checkpoint
Save the state of a lease, then restore it onto another box or fork it into a
/claims
Claims
`crabbox claims list` prints the lease claims stored on the current machine. It
/cleanup
Cleanup
`crabbox cleanup` sweeps direct-provider machines and local provider state that
/code
Code
`crabbox code` bridges a Linux lease's `code-server` workspace into the
/config
Config
`crabbox config` inspects and updates user configuration. It has three
/connect
Connect
`crabbox connect` resolves a lease and opens an interactive SSH session to it.
/cp
Cp
`crabbox cp` copies files or directories between the host and a Crabbox-owned
/desktop
Desktop
`crabbox desktop` drives a visible desktop session on a lease that was warmed
/doctor
Doctor
`crabbox doctor` runs a preflight before you commit to a long workflow. It is
/egress
Egress
`crabbox egress` gives a lease mediated outbound network: a lease-local browser
/events
Events
`crabbox events` prints the broker's event log for a recorded run.
/heartbeat
Heartbeat
`crabbox heartbeat` refreshes the idle deadline for one owned lease and prints
/history
History
`crabbox history` lists recorded remote command runs from the broker. Each run is
/image
Image
`crabbox image` holds the trusted-operator controls for provider base images:
/init
Init
`crabbox init` onboards the current repository: it writes the minimal config
Your efficient agentic AI coding CLI assistant
2 views 0 likesAI 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…
1 views 0 likesAndroid in docker solution with noVNC supported, video recording, mcp server and AI-agent
2 views 0 likesYour 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,…
0 views 0 likesVerifiable program-level self-evolution for AI-for-Science agents: Skills and typed Operators grow from replay-verified executions.
0 views 0 likesLet 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…
0 views 0 likesUnofficial, agent-friendly Mercadona shopping CLI (Go) — search products, read prices, build a cart and prepare checkout from the terminal. BYO credentials.
0 views 0 likesLocal-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…
0 views 0 likesLet any AI coding tool — Claude Code, Cursor, Codex — drive your real Chrome. One-prompt setup, muscle memory, local-first.
0 views 0 likesruns anywhere. uses anything
0 views 0 likes