AI & ML

lev-os Skill

Drafts an FDA Food Facility Registration under FSMA and 21 CFR Part 1, Subpart H (21 U.S.C. 350d). Covers facility identity, food product categories, U.S. agent designation for foreign facilities, and certification language. Use when preparing new FDA facility registrations, biennial renewals, or registration updates for domestic or foreign food facilities.

lev-os Skill

Drafts incident response plans and scenario playbooks for U.S. legal organizations, aligning NIST SP 800-61 Rev. 2 phases with ABA Model Rules 1.1/1.4/1.6 and privilege preservation. Use when creating or updating an incident response plan, breach response policy, ransomware playbook, or regulatory notification checklist. Trigger keywords: incident response, playbook, data breach, ransomware, cybersecurity policy, NIST 800-61.

lev-os Skill

Apply proven architectural patterns from Martin Fowler's PoEAA for building scalable, maintainable enterprise applications - Repository, Unit of Work, Service Layer, Domain Model

lev-os Skill

Systematic techniques for transforming raw data into features that better represent the underlying problem structure, improving ML model performance

lev-os Skill

Mental model for making rough estimates by thinking in powers of 10, enabling quick reasoning about scale, feasibility, and relative importance

techwavedev Skill

Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.

techwavedev Skill

Use when working with error debugging multi agent review

techwavedev Skill

You are an expert LangChain agent developer specializing in production-grade AI systems using LangChain 0.1+ and LangGraph.

techwavedev Bundle

You are an expert prompt engineer specializing in crafting effective prompts for LLMs through advanced techniques including constitutional AI, chain-of-thought reasoning, and model-specific optimizati

lev-os Skill

Drafts HIPAA Release Authorization forms compliant with 45 CFR 164.508 for disclosure of protected health information. Typically used in estate planning or healthcare decision-making packets. Use when a client needs a HIPAA authorization, medical records release, PHI disclosure consent, healthcare agent access form, or advance directive bundle.

lev-os Bundle

Model system dynamics through accumulations (stocks), rates of change (flows), and time lags (delays) to understand inertia, overshoot, oscillation, and equilibrium - map inflows, outflows, buffers, and feedback loops when diagnosing capacity problems, resource depletion, or unexpected system behavior

lev-os Skill

Process unbounded data streams with sub-100ms predictions when real-time ML inference is required

lev-os Bundle

Fungible agent architecture for multi-agent coding. Use when scaling agent swarms, designing multi-agent workflows, recovering from agent failures, or choosing specialized vs. interchangeable agent patterns.

techwavedev Skill

Optimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration. Use when improving agent performance, throughput, or reliability.

lev-os Bundle

Run NTM swarms with Agent Mail, Beads, and BV. Use when sending marching orders, tending parallel coding sessions, coordinating work claims and reservations, or running review loops for an NTM swarm.

lev-os Skill

Deconstructs unit economics with CAC, LTV, payback period, gross margin, and contribution margin analysis. Use when analyzing unit economics, validating SaaS metrics, or assessing business model efficiency.

lev-os Bundle

Generate prompts targeting multiple action surfaces (Telegram, OpenAI Canvas, MCP Apps, CLI, etc.)

lev-os Skill

Drafts Rule 23-compliant class action notices to absent class members for certification or settlement. Agent uses this skill when drafting class action notices, class member notifications, settlement notices, opt-out notices, or fairness hearing notices.

lev-os Skill

Drafts a foreign corporation registration (Certificate of Authority) package to qualify a U.S. corporation for business in a new state. Extracts corporate identity, capital structure, officers, and registered agent details from uploaded records, then produces a jurisdiction-specific application with cover letter, document checklist, and filing instructions. Use when a corporation expands across state lines, opens offices or employs workers in a new state, or needs foreign qualification. Triggers: foreign qualification, certificate of authority, doing business, multi-state expansion.

lev-os Skill

Drafts binding escrow instructions for residential real estate closings. Extracts key terms from purchase agreements, identifies gaps or conflicts, and incorporates jurisdiction-specific requirements. Use when preparing escrow agent directives, closing instructions, escrow arrangements, or residential transaction closing documents.

lev-os Skill

Drafts GLBA-compliant privacy notices using the 16 CFR Part 313 Appendix A model form safe harbor. Use when creating or updating Regulation P privacy notices, annual consumer disclosures, or NPI sharing notices for banks, credit unions, securities firms, insurers, or other covered entities under 15 U.S.C. §§ 6801–6809.

lev-os Skill

Structures model validation with independent testing, limitation documentation, and ongoing monitoring. Use when validating risk models, documenting model limitations, or managing model governance.

lev-os Skill

Evaluates witness preparation activities for ethical compliance under ABA Formal Opinion 508 and Model Rules 3.3, 3.4, 8.4. Distinguishes permissible preparation from prohibited coaching. Use when planning deposition or trial prep, reviewing proposed prep activities, or checking witness coaching ethics. Triggers: witness prep, deposition prep, coaching ethics, ABA 508, testimony preparation.

lev-os Skill

Simulates complex systems from the bottom-up by defining simple rules for individual agents and observing emergent patterns from their interactions

iradoweck Bundle

Run protected AAS maintainer sweeps, PR merge batches, canonical sync, Core preview checks, and scripted releases. Use for repository maintenance, main alignment, CLI/MCP/Workbench changes, or release work; not ordinary contribution tasks.

lev-os Skill

Drafts state-specific Durable Power of Attorney for Finances documents authorizing an agent to manage a principal's financial affairs during incapacity. Use when a user needs a financial POA, DPOA, attorney-in-fact authorization, or incapacity planning document. Triggers on requests involving durable power of attorney, financial agency designation, or springing power of attorney drafting.

lev-os Skill

Drafts HIPAA-compliant PHI release authorizations for estate-planning workflows under 45 CFR §164.508. Use when drafting release forms, healthcare POA support documents, or record-access instruments. Triggers: HIPAA release, PHI authorization, healthcare agent access, advance directive support, medical record release.

lev-os Skill

Drafts federal lead-based paint disclosure forms for pre-1978 residential sales or leases under 42 U.S.C. § 4852d, HUD/EPA rules, and 24 CFR Part 35. Covers seller/landlord knowledge statements, record attachments, EPA pamphlet delivery, purchaser inspection option, acknowledgments, and agent certifications. Use when preparing a lead-based paint disclosure, lead hazard notice, or pre-1978 property disclosure; trigger keywords: lead-based paint, lead hazard, EPA pamphlet, Section 1018.

lev-os Skill

Model complex software to match the problem domain by building ubiquitous language with domain experts and organizing code into bounded contexts

lev-os Skill

Product strategy model that aligns teams around a single metric capturing core customer value, plus supporting input metrics that drive it

lev-os Skill

Systematic testing of how changes in input variables (assumptions) affect output results, revealing which factors drive outcomes and where model risk is concentrated.

lev-os Bundle

Add strategic bridges when teams are siloed but need rapid information diffusion

iradoweck Bundle

Create MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. The quality of an MCP server is measured by how well it enables LLMs to accomplish real-world tasks.

iradoweck Skill

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

iradoweck Skill

Expert in Langfuse - the open-source LLM observability platform. Covers tracing, prompt management, evaluation, datasets, and integration with LangChain, LlamaIndex, and OpenAI. Essential for debugging, monitoring, and improving LLM applications in production.

lev-os Skill

Evaluates and monitors credit risk models (PD, LGD, EAD) with calibration and discrimination metrics. Use when validating credit models, assessing model performance, or calibrating default models.