AI & ML

lev-os Skill

Drafts a market-standard At-The-Market (ATM) Equity Distribution Agreement for public issuers conducting continuous shelf offerings under Rule 415(a)(4). Use when establishing or renewing an ATM program under an effective Form S-3, drafting a sales agent agreement, or structuring a continuous equity offering program.

iradoweck Skill

Browser automation powers web testing, scraping, and AI agent interactions. The difference between a flaky script and a reliable system comes down to understanding selectors, waiting strategies, and anti-detection patterns.

iradoweck Skill

Expert guide for creating custom Odoo modules. Covers __manifest__.py, model inheritance, ORM patterns, and module structure best practices.

lev-os Bundle

Use when creating AI-optimized repository snapshots paired with sophisticated prompts for LLM consumption. Combines repomix configuration selection with prompt engineering to generate complete "prompt packets" for code analysis, documentation, debugging, or architectural planning.

iradoweck Skill

Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks

iradoweck Skill

Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration.

iradoweck 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.

lev-os Skill

Drafts execution-ready lead-based paint disclosure documents compliant with 42 U.S.C. § 4852d and 24 CFR Part 35 for sales or leases of pre-1978 residential properties. Covers seller/landlord hazard disclosures, buyer/tenant acknowledgments, inspection waivers, agent certifications, and attachment schedules. Use when drafting lead paint disclosures, pre-1978 property transactions, residential lease hazard disclosures, or EPA Section 1018 compliance documents.

iradoweck Skill

Production-ready patterns for building LLM applications, inspired by [Dify](https://github.com/langgenius/dify) and industry best practices.

iradoweck Skill

Automate Airtable tasks via Rube MCP (Composio): records, bases, tables, fields, views. Always search tools first for current schemas.

iradoweck Skill

Automate Stripe tasks via Rube MCP (Composio): customers, charges, subscriptions, invoices, products, refunds. Always search tools first for current schemas.

iradoweck Skill

Operate GitHub issues, pull requests, branches, checks, workflows, and permissions through Rube MCP. Use when GitHub work must be queried or changed programmatically with repository-policy safeguards.

iradoweck Skill

Automate HubSpot CRM operations (contacts, companies, deals, tickets, properties) via Rube MCP using Composio integration.

iradoweck Skill

Create Pydantic models following the multi-model pattern for clean API contracts.

lev-os Skill

Structures OIG-model compliance program elements with effectiveness measurement and reporting. Use when building compliance programs, implementing OIG guidance, or measuring program effectiveness.

iradoweck 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

iradoweck 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.

iradoweck 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

Model decay processes by the time required for half of a quantity to degrade, enabling exponential decay predictions

lev-os Skill

Evaluates AI/ML applications in financial services with model governance, bias assessment, and regulatory considerations. Use when analyzing AI in finance, evaluating ML models, or assessing AI governance.

lev-os Skill

Applies ASC 606 five-step model with contract analysis, performance obligation identification, and allocation documentation. Use when analyzing revenue contracts, applying ASC 606, or documenting revenue recognition.

lev-os Skill

Drafts motions to dismiss criminal indictments in federal and state courts. Covers defective indictments, statute of limitations, speedy trial, double jeopardy, prosecutorial misconduct, and jurisdictional defects. Use when the agent needs to challenge the legal sufficiency of criminal charges or draft a pre-trial dismissal motion.

lev-os Skill

Drafts U.S. foreign-corporation qualification filings (Certificate of Authority) for a target state. Use when registering a corporation to transact business outside its home jurisdiction, appointing a registered agent, checking qualification triggers, or assembling a filing-ready package. Trigger terms: certificate of authority, foreign corporation, register to do business, registered agent appointment.

iradoweck Skill

Lightweight Google Docs integration with standalone OAuth authentication. No MCP server required.

iradoweck Skill

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

iradoweck Skill

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

iradoweck Skill

Lightweight Google Calendar integration with standalone OAuth authentication. No MCP server required.

iradoweck Skill

Guide to selecting and optimizing embedding models for vector search applications.

iradoweck Skill

Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom model evaluations with vLLM/lighteval. Works with the model-index metadata format.

lev-os Bundle

Rebuild CHANGELOG.md files and release histories from git, tags, releases, and issue trackers. Use when writing changelogs, version timelines, or agent-facing project history summaries.

lev-os Skill

Guides the agent through TRID tolerance compliance under 12 CFR § 1026.19(e)(3), comparing Closing Disclosure fees to Loan Estimate fees across zero, 10% cumulative, and unlimited tolerance categories. Use when reviewing a CD for tolerance variances, determining whether a revised LE is permitted, calculating cure amounts, or resolving post-closing tolerance violations.

lev-os Bundle

Cross-validate decisions using multiple AI models (Codex, Gemini, Grok). Use when "get a second opinion", evaluating approaches, or high-stakes decisions.

lev-os Skill

Builds strategic and tactical asset allocation models with risk-return optimization and constraint management. Use when constructing portfolios, optimizing asset allocation, or building model portfolios.

lev-os Skill

Assesses startup viability through business model canvas analysis, unit economics validation, and market timing evaluation. Use when evaluating startup pitches, analyzing business model sustainability, or assessing product-market fit.

lev-os Skill

Drafts jurisdiction-specific Advance Health Care Directive packages with agent appointment, living will instructions, HIPAA authorization bridge, organ donation preferences, and execution compliance checklists. Trigger when the user mentions advance directive, healthcare proxy, living will, health care agent, HIPAA authorization, medical power of attorney, end-of-life planning, capacity trigger planning, state-specific directive forms, witness/notary requirements for healthcare documents, or cross-state directive portability.

lev-os Skill

Customer satisfaction framework that categorizes product features into five types based on their relationship to user delight and investment