OpenAI 'Hazelnut' Skills: composable, code-executable modules (rumored 2026)

GENERAL PUB_DATE: 2026.W01

Reports indicate OpenAI is testing 'Skills' (codename Hazelnut): reusable capability modules bundling instructions, context, examples, and executable code that ...

Reports indicate OpenAI is testing 'Skills' (codename Hazelnut): reusable capability modules bundling instructions, context, examples, and executable code that the model composes at runtime. Skills are described as portable across ChatGPT surfaces and the API, load on demand, and may allow converting existing GPTs into Skills. Launch is rumored for early 2026 and details may change.

[ WHY_IT_MATTERS ]

01.

This could standardize agent capabilities into versioned, testable units, reducing prompt sprawl and duplication.

02.

Reusable modules may simplify deploying the same capability across chat, APIs, and internal tools.

[ WHAT_TO_TEST ]

terminal
Prototype capability modularization today using Assistants/GPTs + code execution with explicit I/O schemas, fixtures, and logging.
terminal
Validate sandboxing, secrets, and data-access controls for code-running modules, and measure latency/cost effects of on-demand loading.

arrow_back

PREVIOUS_DATA_LOG

DeepSeek open models: worth a backend/RAG benchmark

Initialize_Return_to_Core

LINK_STATUS: 127.0.0.1 (SECURE)

NEXT_DATA_LOG

Tracking LLM mentions: 5 GEO tools to measure AI-driven discovery

arrow_forward