OPENAI 'HAZELNUT' SKILLS: COMPOSABLE, CODE-EXECUTABLE MODULES (RUMORED 2026)
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.
This could standardize agent capabilities into versioned, testable units, reducing prompt sprawl and duplication.
Reusable modules may simplify deploying the same capability across chat, APIs, and internal tools.
-
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.
Legacy codebase integration strategies...
- 01.
Inventory existing GPTs/agents and Python tools and map them to candidate skills with dependency pinning and version migration plans.
- 02.
Add tracing, metrics, and replay around tool calls now to compare behavior pre/post migration and enable safe rollback.
Fresh architecture paradigms...
- 01.
Design small, stateless, idempotent skills with clear interfaces and test fixtures, stored in a registry for reuse.
- 02.
Set up CI to lint/test/bench skills and a router that composes them with explicit permissions, timeouts, and budgets.