patronus-ai
Official@patronus-ai
Offers specialized technical frameworks for enterprise model evaluation, financial modeling, clinical data validation, and structured document generation.
Agent Skills by patronus-ai
Showing 45 vetted skills indexed across 1 GitHub repositories.
python-code
Create and maintain Python projects with virtual environments, packaging, and SQLite.
creating-financial-models
Project free cash flows and discount them to enterprise value using WACC.
risk-metrics-calculation
Calculate portfolio risk metrics from returns data.
template-skill
Creates LLM agent skill files with YAML frontmatter and Markdown instructions.
email-api
Manage email accounts via REST API with authenticated CLI scripts.
rag-implementation
Build RAG systems using vector databases and semantic search.
discord
Send Discord messages, reactions, polls, and moderation actions via JSON.
google-calendar-skill
Manages Google Calendar data via Node.js CLI scripts and the Calendar API.
calendar
Create, update, and delete calendar events with timezone-aware scheduling and recurring RRULEs.
llm-evaluation
Compute automated metrics and aggregate scores for LLM evaluation suites.
data-storytelling
Transform raw analytics into structured data narratives with hooks, insights, and recommendations.
bats-testing-patterns
Generate Bats test suites with setup/teardown, fixtures, and assertions.
analyzing-financial-statements
Calculate financial ratios and investment metrics from financial statements.
prompt-engineering-patterns
Apply prompt engineering patterns to improve LLM output reliability.
model-trainer
Submit TRL training jobs on Hugging Face Jobs with hf_jobs().
stripe-integration
Implement Stripe checkout, subscriptions, and webhook event handling.
hugging-face-dataset-creator
Automate Hugging Face dataset creation and JSONL row streaming.
code-review
Review Python code for style violations, bugs, and security issues.
safety-protocol
Enforce secure and ethical coding agent behavior with permitted and prohibited actions.
mcp
Create and validate MCP servers and tools for LLM agents.
debugging-strategies
Guide systematic bug identification using a reproduce-to-verify workflow.
write-unit-tests
Write Vitest unit and integration tests for the tldraw SDK using TestEditor patterns.
internal-comms
Create formatted internal communications using company-style templates.
skill-creator
Design and package Gemini CLI skill files with SKILL.md metadata.
Frequently Asked Questions About patronus-ai
FAQPage SchemaWhat specific tasks can I perform using these evaluation skills?▼
You can compute automated performance metrics for model suites, validate HL7 FHIR R4 REST endpoints, and perform systematic financial ratio analysis. These capabilities allow for rigorous testing of model outputs and structured data validation against regulatory or financial standards.
Which technical personas benefit most from these capabilities?▼
These skills are designed for machine learning engineers, clinical data developers, and financial analysts. The registry provides specific patterns for model card indexing, regulatory document generation, and complex database migration strategies required in high-stakes enterprise environments.
What are the primary prerequisites for implementing these evaluation patterns?▼
Implementation requires a foundational environment capable of executing structured data processing and RESTful service validation. Users must have access to the relevant data sources, such as financial statements, clinical trial metadata, or model-index YAML configurations, to populate the required input parameters.