This workspace is part of a role-based chip collaboration team.

> Track AI trading agents across Solana (pump.fun) and Monad (nad.fun) blockchains with real-time trade monitoring, performance analytics, and token charts.

Storage backends and indexing for vector databases in Elixir. Use when choosing persistence, implementing exact vs approximate k-NN, or integrating pgvector, file, or ETS for vector storage.

INVOKE THIS SKILL at the START of any LangChain/LangGraph/Deep Agents project, before writing any agent code. Determines which framework layer is right for the task: LangChain, LangGraph, Deep Agents, or a combination. Must be consulted before other agent skills.

Streaming, pagination, count strategies, bulk operations

Guidance for `effect/MutableHashMap` focused on APIs like get, set, and make. Load after `effect-skill-router` when this module is the primary owner.

Log a milestone, finding, or result to ~/memory/. Invoke explicitly with /memory-log or proactively when a session produces something worth remembering.

System health check (MOT) for skills, agents, hooks, memory, ROADMAP, knowledge tree, and Braintrust

>

>

Codified knowledge for the no∅ agent system — Nex, Vox, personas, memory, multi-channel, inline apps.

Talk to Nick Theriot Youtuber about their expertise. Nick Theriot Youtuber provides authentic advice using their mental models, core beliefs, and real-world examples.

How to use Randal's persistent memory system. Memories are stored in Meilisearch and automatically injected into context based on relevance.

Fournit les bonnes pratiques Vanilla JavaScript ES6+, HTML5 et CSS3 pour le projet demo-app. Couvre la structure du code, l'accessibilite WCAG AA, la performance, la securite XSS, le CSS responsive (BEM, Grid, Flexbox), la gestion d'etat, les formulaires et la communication API Fetch. S'active lors de la generation ou modification de fichiers frontend (JS, HTML, CSS).

CRITICAL: Use for generics, traits, zero-cost abstraction. Triggers: E0277, E0308, E0599, generic, trait, impl, dyn, where, monomorphization, static dispatch, dynamic dispatch, impl Trait, trait bound not satisfied, 泛型, 特征, 零成本抽象, 单态化

>-

hologres-query-optimizer

TypeScript-first schema validation library with static type inference and runtime validation

Memory management, profiling, optimization techniques, and Instruments usage for high-performance iOS apps

Analyze Swift and mixed-language compile hotspots using build timing summaries and Swift frontend diagnostics, then produce a recommend-first source-level optimization plan. Use when a developer reports slow compilation, type-checking warnings, expensive clean-build compile phases, long CompileSwiftSources tasks, warn-long-function-bodies output, or wants to speed up Swift type checking.

Integrate on-device AI using Foundation Models framework, Core ML, and open-source LLM runtimes on Apple Silicon. Covers Foundation Models (LanguageModelSession, @Generable, @Guide, SystemLanguageModel, structured output, tool calling), Core ML (coremltools, model conversion, quantization, palettization, pruning, Neural Engine, MLTensor), MLX Swift (transformer inference, unified memory), and llama.cpp (GGUF, cross-platform LLM). Use when building tool-calling AI features, working with guided generation schemas, converting models, or running on-device inference.

Collect and analyze on-device performance metrics and crash diagnostics using MetricKit. Use when setting up MXMetricManager, handling MXMetricPayload or MXDiagnosticPayload, processing crash/hang/disk-write diagnostics via MXCallStackTree, adding custom signpost metrics, or uploading telemetry to an analytics backend.

You help plan, implement, and optimize App Clips — lightweight iOS experiences (max 15MB) that users can launch instantly without installing the full app.

You help the user plan, write, and optimize **App Store In-App Events** — event cards that surface in search, the Today tab, and the product page, driving installs and re-engagement without paid media

You optimize the first-run experience to maximize activation — the moment a new user completes the core action that predicts long-term retention.

You optimize every stage of the subscription journey: trial → paid → renewal → cancellation recovery → win-back.

You are an expert in mobile app user acquisition across all major ad platforms. Your goal is to help the user plan, launch, and optimize paid campaigns that drive profitable installs.

Set up bundle IDs, capabilities, signing certificates, provisioning profiles, and encrypted signing sync with the asc cli. Use when onboarding a new app, rotating signing assets, or sharing them across a team.

Build, archive, export, and manage Xcode version/build numbers with asc and xcodebuild before uploading to App Store Connect. Use when you need to create an IPA or PKG for upload.

>

>

Work with MongoDB databases using best practices. Use when designing schemas, writing queries, building aggregation pipelines, or optimizing performance. Triggers on MongoDB, Mongoose, NoSQL, aggregation pipeline, document database, MongoDB Atlas.

Local database and persistence selection for Flutter including SharedPreferences, SecureStorage, Hive, and Drift. Use when implementing offline storage, encrypted data persistence, or choosing between key-value and relational local databases.

Hive CE (Community Edition v2.19.x) NoSQL object database for Flutter providing blazing-fast key-value and object storage with TypeAdapters. Use this skill when implementing offline-first architecture, high-performance local data caching, NoSQL document-style object stores, custom TypeAdapter serialization for complex objects, lazy loading boxes for memory efficiency, encrypted boxes (HiveAES encryption), database compaction for size optimization, storing large datasets without SQL schema overhead, implementing local-first sync patterns, or migrating from SQLite to NoSQL. Supports primitive types, custom objects, lists, and maps. Ideal for apps requiring ultra-fast read/write operations (microsecond latency), object persistence without ORM complexity, or local-first data architecture.

Integrates Sentry error tracking and performance monitoring into Flutter apps using `sentry_flutter`. Use when setting up crash reporting in Flutter, calling `SentryFlutter.init`, adding `SentryNavigatorObserver` to GoRouter, tracing HTTP requests with `sentry_dio`, capturing handled exceptions via `Sentry.captureException`, adding breadcrumbs, configuring session replay (`replay.onErrorSampleRate`), tuning `tracesSampleRate` or `profilesSampleRate`, controlling PII with `sendDefaultPii`, or setting user context after login and logout.

<<<<<<< HEAD

You are Proposal Machine, an AI-powered proposal generation engine for service businesses. You take raw client context and produce complete, persuasion-optimized proposals that close deals. You don't

> Track sales rep metrics: calls, close rate, pipeline value, and churn risk scoring.

Clean, optimize, and standardize SVG files. Remove metadata, editor artifacts, unnecessary attributes. Reduce file size 30-70% with zero visual change.

>

Evolutionary algorithm discovery for Claude Code. Evolves novel solutions to hard problems through parallel mutation and selection, with Rust benchmarks for precise performance measurement.

Play turn-based RPGs autonomously via Game Boy emulation. Use when the user asks to 'play pokemon', 'emulate a game boy game', 'automate pokemon battles', 'grind pokemon', 'run a pokemon nuzlocke', 'play an RPG for me', or mentions headless emulation, PyBoy, or turn-based game automation.

- `docker/` holds the Dockerfile, launch profile, and helper scripts for building Redmine-ready devcontainers. Keep new tooling scripts here.

This repository contains a Next.js application for blockchain network performance monitoring and analysis. When working on the project interactively with an agent (e.g. the Codex CLI) please follow th

This document is intended for AI agents (like yourself) to quickly understand the architecture, conventions, and safety requirements of the `lodum` codebase.

**Purpose**: Operate AI agent tasks in this repo while honoring user preferences and house style.\

Launch 10 independent agents to build the cognitive memory schema foundation. All agents work in the same worktree with file-level isolation.

**Version 1.0.0**

Sandbox agents are now available in the Python Agents SDK. Use them when your

BEFORE doing ANYTHING else, when starting ANY session: