AI Safety and Alignment Group
Official@aisa-group · Germany
AI Safety and Alignment Group at the ELLIS Institute Tübingen and Max Planck Institute for Intelligent Systems
Agent Skills by AI Safety and Alignment Group
Showing 45 vetted skills indexed across 2 GitHub repositories.
aisa-grouppython-code
Scaffold Python projects with virtual environments, src layouts, and testing practices.
aisa-groupcreating-financial-models
Automate DCF valuation modeling with sensitivity analysis and scenario planning.
aisa-grouprisk-metrics-calculation
Compute portfolio VaR, CVaR, drawdowns, and risk-adjusted metrics.
aisa-grouptemplate-skill
Create standardized Skill Unit skeletons with SKILL.md frontmatter and directory structure.
aisa-groupemail-api
Automate email operations via CLI scripts against an Email API server.
aisa-grouprag-implementation
Build retrieval-augmented generation systems with embeddings, vector stores, and reranking.
aisa-groupdiscord
Automate Discord channel, message, and role management tasks via Clawdbot.
aisa-groupgoogle-calendar-skill
Manage Google Calendar events via Node.js scripts with JSON output.
aisa-groupcalendar
Create, update, and manage calendar events with timezone-aware scheduling and ICS import/export.
aisa-groupllm-evaluation
Compute automated metrics and statistical tests for LLM evaluation.
aisa-groupdata-storytelling
Transform raw metrics into narrative frameworks with recommendations for stakeholder presentations.
aisa-groupbats-testing-patterns
Provide Bats testing patterns for setup, teardown, fixtures, mocks, and assertions.
aisa-groupanalyzing-financial-statements
Compute financial ratios from CSV, JSON, or Excel statements.
aisa-groupprompt-engineering-patterns
Optimize and structure prompts for consistent LLM outputs.
aisa-groupmodel-trainer
Train and fine-tune language models on Hugging Face Jobs using TRL.
aisa-groupstripe-integration
Integrate PCI-compliant Stripe payment processing with hosted checkouts, subscriptions, and webhooks.
aisa-grouphugging-face-dataset-creator
Automate Hugging Face dataset creation, configuration, and content updates.
aisa-groupcode-review
Run style checks on Python code and return structured JSON feedback.
aisa-groupsafety-protocol
Enforce coding-safety guidelines across file operations, code execution, and communications.
aisa-groupmcp
Create MCP servers with structured tools, validation, and error handling.
aisa-groupdebugging-strategies
Apply systematic debugging strategies to identify and resolve codebase bugs.
aisa-groupwrite-unit-tests
Write and maintain Vitest unit and integration tests for the tldraw SDK.
aisa-groupinternal-comms
Automate drafting of standardized internal communications from template guidelines.
aisa-groupskill-creator
Create and package reusable Gemini CLI skills with validated SKILL.md structure.
Frequently Asked Questions About AI Safety and Alignment Group
FAQPage SchemaWhat specific financial tasks can be performed using these skills?▼
You can execute DCF valuation models, perform sensitivity analysis, and compute portfolio risk metrics including VaR, CVaR, and drawdowns. Additionally, the system supports financial ratio analysis from CSV, JSON, or Excel statements.
Which technical personas are these skills designed for?▼
These skills are designed for financial analysts, healthcare data engineers, and enterprise developers who require structured, repeatable processes for document generation, clinical data validation, and complex financial modeling.
What are the prerequisites for implementing the FHIR developer skills?▼
Implementation requires familiarity with FHIR R4 standards and Pydantic v2 for data modeling. The skills provide the necessary structure to build and validate REST endpoints against clinical data requirements.