LLM Mart Basic

Design engineering principles for making interfaces feel polished. Use when building UI components, reviewing frontend code, implementing animations, hover states, shadows, borders, typography, micro-interactions, enter/exit animations, or any visual detail work. Triggers on UI p

Study a market - size, trends, players, pricing, regulation, and opportunities - with sourced findings. Use before entering a market or positioning an offer.

Measure CAC, conversion rates, attribution, ROAS, CPL, and pipeline contribution from marketing data. Use to evaluate channels and build marketing reports.

Build positioning, ICP, offer, channel mix, and an execution plan. Use when marketing lacks direction or before investing in campaigns.

Produce meeting minutes, action lists, and follow-up emails within hours of a meeting. Use after every client, prospect, or internal meeting that matters.

Run the Navin Meeting studio desk - capture notes/transcripts, custom summary templates, speaker labels, calendar-linked meetings, chat-with-meeting Q&A, exports, and local audit-aware reports. Use when the user opens #/meeting or runs /meeting.

Two-layer memory system with Dream-managed knowledge files.

Measure project and product health - code metrics, complexity, dependency freshness, test coverage, technical debt, and product KPIs. Use for /pulse, health dashboards, or "how is the project doing?" questions.

Magentic-style Task/Progress Ledger orchestration for /blueprint, /forge, /cruise, and /mission. Use whenever planning or executing multi-step work on the board.

Build, run, and debug Expo and React Native mobile apps - detect the stack, doctor the Android/Node toolchain, start Metro/Expo, fix redbox errors, and ship UI changes with hot reload. Use for mobile Dev sessions and any React Native / Expo task.

Recommend which model or provider preset to use based on cost, latency, context size, and task difficulty. Use when the user asks which model to pick or when work is mismatched to the current model.

Swing / momentum skill for the Trading Agent OS. Require uptrend, constructive RSI, and specialist consensus before a buy.

Project marketing montage - analyze the workspace, record live browser demos, package platform video exports, propose calendars, generate images/videos/music, and lazily set up HyperFrames. Use in Montage mode (/montage) or Studio → Montage. Never auto-publish.

Coordinate specialized subagents (architect, implementer, reviewer, analyst, researcher) with clear roles, handoffs, and validation. Use spawn for parallel independent tracks.

Inspect and optionally adjust the agent's runtime state. Use to check the current model or preset, context window, iteration progress and limits, token usage, workspace and tool configuration, subagent status, and request routing metadata such as channel, chat ID, and sender ID;

Paper NFT collection skill. Live CoinGecko floors only. No invented floors, no wash trades.

Build and use objection response playbooks - price, security, integration, competition, status quo. Use to prepare answers and battlecards for sales conversations.

Query metrics, logs, and traces (Prometheus, Grafana, Loki, Sentry, OpenTelemetry) to diagnose incidents. Use during outages or performance investigations.

Compare a job or freelance offer to the Career profile - compensation, risk, visa, stack, and a clear accept / negotiate / walk-away. Use when a written offer arrives.

Optimize existing pages - titles, meta descriptions, heading hierarchy, internal links, and content depth. Use to improve pages that rank on page 2-3 or underperform.

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 Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

Agent OS: the agent gets smarter on its own. We just hold the line: the grading command and expected result never make it into the success contract we hand it.…

Curated systems, benchmarks, and papers etc. on memory for LLMs/MLLMs --- long-term context, retrieval, and reasoning.

:memo: Vimlike Modal Text Editor in Rust

CI-native security testing for MCP servers. Attack simulation, schema drift detection, and health scoring before agents depend on them.

Hermes Agent memory plugin/provider for scope-aware recall, SQLite truth, LanceDB semantic search, and hybrid retrieval.

For You Agent——AI 时代的个人随身数字人格。把你的模型、AI 账号、技能、提示词和工作方式，带到每一个 AI 工具里。

A coding agent: give it a prompt and it reads, writes, runs commands, and searches code in a loop until the work is done, using native tool-calling across OpenA…

A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord, Teams, and…

Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

DeepSeek Harness Desktop (dsh-desktop). EAC: Embracing All Creation (揽尽万象). Bundled Node.js runtime with full dsh-CLI kernel, one-click startup, 10 built-in UI…

See your agent think. Zero-config observability & governance for 26 AI agent runtimes: Claude Code, Cursor, OpenAI Codex, GitHub Copilot, Gemini CLI, Cline, Ope…

Save 94% on AI coding tokens. Index your codebase, agents search instead of reading files. Works with Claude Code, Codex, Copilot, Cursor, Gemini CLI. Local MCP…

Yet another coding agent harness, lightweight and written in go.

a coding Agent from pi. ∞ providers, sub-agents, hashline edits, and a permission gate

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting…

🧠 Leon is your open-source personal assistant.

The Station, an open-world multi-agent environment that models a miniature scientific ecosystem.

The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Protocol

VelaTerm = iTerm2 + Codex, The Best Terminal for AI Coding