LLM Mart Basic
@llm-mart · Joined Jun 2026
EAS Build, Update, Submit deployment patterns
Expo managed workflow
React Native mobile development patterns - New Architecture (Fabric, TurboModules, JSI), component architecture, React Navigation 7+, FlashList v2 optimization, gestures with Reanimated 4, platform-specific code, React 19 features
BLE scanning/connecting/GATT operations with react-native-ble-plx, NFC tag reading/writing with react-native-nfc-manager, permissions, background mode, battery-efficient patterns
File-based routing and navigation for Expo/React Native
React Navigation 7+ patterns - static and dynamic APIs, type-safe navigation, stack/tab/drawer navigators, deep linking, authentication flows, screen preloading, header customization
Push notification patterns - expo-notifications (Expo) and @react-native-firebase/messaging (bare RN), permission handling, token management, foreground/background/tap listeners, local scheduling, Android channels, notification categories and actions, badge management, rich notif
React Native performance profiling, optimization, and monitoring - JS/UI thread analysis, re-render prevention, list optimization, image performance, bundle size, startup time, memory leaks, React Compiler, New Architecture benefits
Secure storage, certificate pinning, biometric auth, jailbreak detection, code obfuscation, network security, screenshot prevention for React Native
MMKV high-performance key-value storage for React Native - synchronous JSI-based reads/writes, encryption, typed hooks, multiple instances, listeners, persistence middleware adapters
PowerSync offline-first sync engine on SQLite for React Native - schema definition, watched queries, CRUD operations, backend connectors, sync rules, conflict resolution, attachments
WatermelonDB reactive local database for React Native - schema, models, decorators, reactive queries, relations, writers/readers, batch operations, migrations, sync
NativeWind v4+ - Tailwind CSS utility classes for React Native, className prop, CSS variables, dark mode, platform prefixes, animations, theming, third-party component integration
Unistyles 3.0 styling - C++ powered StyleSheet superset with zero re-renders, theming, breakpoints, variants, dynamic functions, runtime values
Detox E2E gray-box testing for React Native - matchers, actions, expectations, waitFor, device API, synchronization, mocking, artifacts, CI integration
Maestro mobile E2E testing - YAML flows, selectors, flow control, environment variables, JavaScript expressions, device interactions, Maestro Studio, Maestro Cloud CI, tags, test suites
React Native Paper v5+ - Material Design 3 theming, PaperProvider, key components, dynamic color, accessibility, tree-shaking, custom fonts, navigation integration
Tamagui universal UI - styled(), tokens, themes, optimizing compiler, responsive media queries, animations, Sheet/Dialog components
Nx monorepo build system — workspace configuration, project graph, task pipelines, caching, generators, plugins, and release management
pnpm workspace protocol, filtering, catalogs, shared dependencies, publishing, and CI/CD for monorepo management
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.
/schema
Schema
Check frontmatter against the schema
/scope
Scope
Pull knowledge into a project
/secrets
Secrets
Scan for credentials
/sources
Sources
Show what a claim rests on
/split
Split
Split an overloaded page
/stale
Stale
Find concept pages nobody has touched
/tags
Tags
Audit the tag vocabulary
/timeline
Timeline
How my sources developed over time
/trace
Trace
Show which pages an answer used
/typed-links
Typed links
Add relation types where they matter
/weekly
Weekly
The weekly review
/build
Build
Implement an approved plan or issue in its own worktree, run the gate, open the pull request.
/close-out
Close out
Close a finished session: sweep for unfinished work, ask once, land, file the follow-ups, hand off, tell the sessions that depend on this one, then archive.
/handoff
Handoff
Write the repository handoff file for the next session, and record any durable learning.
/land
Land
Merge an approved pull request, clean up its worktree and branch, then check whether a release is due.
/plan
Plan
Turn a topic or issue into a plan the reviewer approves in the native plan pane.
/research
Research
Answer a research question with parallel read-only gatherers and one synthesized digest.
/review
Review
Review the branch's diff in two fresh contexts — scope against the spec, then quality — and report findings only.
/ia-refine-prompt
ia-refine-prompt
Transform a vague prompt into precise, structured AI instructions
/build
Build
Implement an approved plan or issue in its own worktree, run the gate, open the pull request.
Okou connects to the tools your team already uses and does the work — across marketing, sales, engineering, and operations, under your control.
4 views 0 likesAn open-source Digital Worker platform for reliable execution, continuous co-evolution, and building Enterprise AI assets.
5 views 0 likesA curated list of AI Agent evolution, memory systems, multi-agent architectures, and self-improvement projects. | evomap.ai
4 views 0 likesA governance harness for AI coding.
3 views 0 likesDeepSeek Harness 手机版:可直接安装的 Android APK,AI 免 Root 操作手机(Shizuku/root 可选),文件编辑只需所有文件访问权限,前台保活 + AI 通知
1 views 0 likesLocal-first, governed AI agent runtime for Python — embed it in your app, or run it as a CLI or ACP server. Permissions, MCP, memory and audit replay built in.
2 views 0 likesOrbi — the factory that builds and operates AI software factories. GitHub Issues in, releases and runnable system out
3 views 0 likesOpen-source AI agent harness in native Rust — GUI, CLI, headless, and webapp from one binary. Multi-provider, MCP, skills, plugins, agent teams.
1 views 0 likesThe SDK for browser agents. Interact, search, extract, and fetch any site reliably across the web
4 views 0 likesAgent-native shopping for extreme value: verifiable same-product price evidence, checkout, orders, delivery, and after-sales.
5 views 0 likesThe extensible power-user platform for Google Antigravity. Adds a native In-App Browser, animated Desktop Pets, revamped Gemini UI, and custom BYOK Gemini Pro k…
4 views 0 likesOpen-source, single-binary, self-hosted AI agent — your models and data stay on your machine. A coding agent on par with Claude Code and a personal assistant li…
4 views 0 likesYour pocket agent. Local-first AI agents on iOS and Android — real workspaces, tool execution with approvals, and your choice of model (DSH · Claude Code · Code…
3 views 0 likesBridge between QQ (SnowLuma OneBot v11) and DeepSeek Harness agents: social simulation, safe MCP tools, slang learning and more.
2 views 0 likesA 7×6 framework for agent architecture. 28 patterns, each placed at a coordinate, runnable Python code with verified engineering slices from Claude Code, Aider,…
2 views 0 likes针对 AI 自动化渗透 Agent 的新一代反制蜜罐,通过反向代理将API密饵载入真实业务、反向提示词注入等方式反制自动化渗透 Agent,实现多款主流通用Agent的反制上线控制。
2 views 0 likesOpen-source, local-first AI agent for coding and real work. BYOK models, MCP, skills, plugins, workflows, and private knowledge bases.
4 views 0 likesA free AI-agent toolbox for Android, 一站式安卓AI Agent工具箱
4 views 0 likesGoogle Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. I…
4 views 0 likesIndependent, unofficial CLI to edit CapCut and JianYing (剪映) projects — subtitles, timing, speed, volume, templates, cut long-form to shorts. No API needed, rea…
5 views 0 likes