Move repeatable coding-agent instructions from words into code.
The public documentation is the best place to start. This directory contains the versioned technical source that stays with each Yield revision.
You may already be repeating a workflow in a prompt:
Run the checks. Review the diff. Stop if anything critical remains. Ask me before publishing. If the session ends, start again without losing our place.
Yield lets you keep the useful words and put the repeatable flow in normal code. The coding agent still investigates, reviews, edits, and explains. Your program decides which operation comes next, what evidence must exist, and when the run is finished.
When one step needs judgment, call the coding agent with AgentTask, receive
structured data, then continue in normal code.
A skill workflow is a portable, executable process that combines agent skills with deterministic code, state, and verification. The canonical workflow is the source you edit. Generated adapters let coding agents discover and start it.
- Create your first workflow — install the runtime, write a workflow and fixture, test it, and register it.
- Understand skill workflows — the canonical workflow, generated adapter, and execution boundary.
- Read the public guide — the complete guide for the current release.
- Register it with your coding agents — keep one workflow and generate the small discovery adapters each agent needs.
- Learn the primitives — commands, model work, human input, gates, and honest outcomes.
- Follow a complete tutorial — review, approval, environment repair, bounded debugging, and migration.
- Browse the examples — working skill workflows in Go, TypeScript, Python, and Rust.
- Convert an existing prose skill — use the
workflow builder to convert an existing
SKILL.md.
| Put in code | Leave with the model |
|---|---|
| order and branching | investigation and judgment |
| retry limits | reading unfamiliar code |
| commands that must really run | proposing changes |
| approval points | writing explanations |
| evidence required to finish | interpreting evidence |
This is not a new agent loop or a hosted agent runtime. A thin SKILL.md starts
the program, the program emits one typed operation, and the coding agent
performs that operation through its normal interface. Yield records the
response and resumes from the next unanswered operation.