AI & ML

lev-os Bundle

Portable coding-agent bootstrap bundle (CLI toolchain, PATH wiring, ops skills). Use when a local, remote, or container env is missing dcg, ntm, cass, ubs, defendr, or agentmail-cli.

lev-os Bundle

Handle blocked destructive commands. Use when dcg blocks rm -rf, git reset --hard, DROP DATABASE, kubectl delete, or when configuring agent safety guardrails.

lev-os Bundle

Execute multi-agent workflows from YAML definitions. Claude Code IS the runtime - reads workflow, creates artifacts, dispatches agents via Task tool.

techwavedev Skill

Iteratively reviews and fixes Claude Code skill quality issues until they meet standards. Runs automated fix-review cycles using the skill-reviewer agent. Use to fix skill quality issues, improve skill descriptions, run automated skill review loops, or iteratively refine a...

lev-os Skill

Drafts FDA Establishment Registration and Device Listing documents compliant with 21 CFR Part 807. Structures filings with establishment details, owner/operator information, device inventories, compliance certifications, and signature blocks mirroring FDA Form 2830. Triggers on initial registrations, annual renewals, listing updates, or foreign establishment filings requiring US agent designations.

lev-os Bundle

Multi-perspective project analysis via NTM reasoning-mode agent swarm. Use when "modes of reasoning", "multi-perspective analysis", or "epistemological review" of any project.

lev-os Skill

Contract surface for Lev's 4-slot memory model (working, episodic, semantic, procedural) with pluggable providers.

techwavedev Skill

Scoped CLAUDE.md memory system that reduces context token spend. Creates directory-level context files, tracks savings via dashboard, and routes agents to the right sub-context.

techwavedev Skill

Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them. Key insight: Memory isn't just storage - it's retrieval. A million stored facts mean nothing if you can't find the right one. Chunking, embedding, and retrieval strategies determine whether your agent remembers or forgets. The field is fragm

techwavedev Bundle

Scaffold, write, debug, and enhance enterprise-grade Playwright E2E tests in Java using Page Object Model, JUnit 5, Allure reporting, and parallel execution.

techwavedev Skill

Senior PM agent with 6 knowledge domains, 30+ frameworks, 12 templates, and 32 SaaS metrics with formulas. Pure Markdown, zero scripts.

lev-os Skill

Separate user interface logic into Model (data), View (presentation), and Controller (input handling) for maintainable, testable GUI applications

techwavedev Skill

Master the LangChain framework for building sophisticated LLM applications with agents, chains, memory, and tool integration.

techwavedev Skill

Expert in vector databases, embedding strategies, and semantic search implementation. Masters Pinecone, Weaviate, Qdrant, Milvus, and pgvector for RAG applications, recommendation systems, and similar

techwavedev Skill

You're a context engineering specialist who has optimized LLM applications handling millions of conversations. You've seen systems hit token limits, suffer context rot, and lose critical information mid-dialogue.

techwavedev Skill

Pre-ingestion verification for epistemic quality in RAG systems. Ensures documents are properly qualified before entering knowledge bases. Produces CGD (Clarity-Gated Documents) and validates SOT (Source of Truth) files.

techwavedev Bundle

Update the AGI Agent Kit to the latest version from NPM

lev-os Bundle

Design agent-friendly MCP servers with optimal UX. Use when building MCP tools, designing agent APIs, writing tool documentation, implementing error handling, or creating multi-agent coordination systems.

techwavedev Skill

Train or fine-tune TRL language models on Hugging Face Jobs, including SFT, DPO, GRPO, and GGUF export.

techwavedev Skill

This skill should be used when the user asks to \\\"create financial projections", "build a financial model", "forecast revenue", "calculate burn rate", "estimate runway", "model cash flow", or...

techwavedev Skill

Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications. Use when: building RAG, ...

techwavedev Bundle

Use when creating, updating, or improving agent skills.

lev-os Bundle

Product planning and design workflow for UI components, data models, and agent handoffs. Use when starting a new product, defining features, or preparing coding-agent export packages.

lev-os Skill

Helps users discover and install external agent skills, but only after local `skill-discovery` results are low quality or clearly insufficient.

lev-os Bundle

Export a ChatGPT-ready Question / Plan / Review prompt using rp-cli

lev-os Bundle

[WHAT] Rust knowledge ingestion and semantic search system. Indexes Rust books, patterns, error examples, and crate documentation into Qdrant for agent-accessible retrieval. [HOW] Clones Rust book sources (markdown), chunks by chapter/section/concept, embeds via sentence-transformers (all-mpnet-base-v2, 768D), upserts to Qdrant collections following the os/agent/performance-engine schema. Provides search commands for agents. [WHEN] Use when ingesting new Rust learning material, querying Rust patterns during planning, or looking up idiomatic solutions to Rust compiler errors. [WHY] Agents writing Rust need access to canonical patterns, not just LLM training data. RAG over curated Rust books produces more idiomatic, correct code.

techwavedev Skill

Automate Freshservice ITSM tasks via Rube MCP (Composio): create/update tickets, bulk operations, service requests, and outbound emails. Always search tools first for current schemas.

techwavedev Skill

Lightweight Google Drive integration with standalone OAuth authentication. No MCP server required. Full read/write access.

techwavedev Skill

Automate Google Sheets operations (read, write, format, filter, manage spreadsheets) via Rube MCP (Composio). Read/write data, manage tabs, apply formatting, and search rows programmatically.

techwavedev Skill

This skill should be used when the user asks to "design multi-agent system", "implement supervisor pattern", "create swarm architecture", "coordinate multiple agents", or mentions multi-agent patterns, context isolation, agent handoffs, sub-agents, or parallel agent execution.

lev-os Skill

Guides attorneys through deposition witness preparation using a two-session model with document review, practice examination, and day-of logistics. Covers party witnesses, fact witnesses, 30(b)(6) corporate representatives, and experts. Produces preparation memos, document review lists, topic summaries, and day-of checklists. Enforces ABA Opinion 508 ethical boundaries. Use when preparing any witness for deposition, scheduling prep sessions, or building witness preparation materials.

lev-os Skill

Drafts a non-binding instruction letter (values letter / legacy letter) from a client to their designated health care agent, translating personal values, quality-of-life thresholds, and scenario-based treatment preferences into operational bedside guidance for substituted judgment. Trigger when the user mentions values letter, legacy letter, instruction letter to healthcare proxy, substituted judgment guidance, supplementing an advance directive with personal guidance, or communicating treatment wishes to a designated agent. Also trigger for family conflict around medical decision-making authority.

techwavedev Skill

Automate DocuSign tasks via Rube MCP (Composio): templates, envelopes, signatures, document management. Always search tools first for current schemas.

techwavedev Bundle

Train or fine-tune vision models on Hugging Face Jobs for detection, classification, and SAM or SAM2 segmentation.

lev-os Bundle

Deterministic browser auth extraction for agent workflows. Use when you need to stop a running Brave/Chrome/Edge session, relaunch with CDP, extract cookie/localStorage/sessionStorage auth values, and restore normal browser state.

lev-os Skill

Code organization and modularity audit with parallel agent inspection. Creates XDG-compatible artifact reports using lev-ref validation patterns. Use when auditing code structure, checking fractal compliance, or reviewing module organization.