Incremental Implementation is the execution discipline for any change that touches more than one file. The agent implements the smallest complete piece, runs the tests, verifies the result, commits it and only then moves to the next slice.
The skill describes vertical, contract-first and risk-first slicing, and sets rules for simplicity, scope discipline, one change at a time, a compilable build after every step, feature flags, safe defaults and rollback-friendly increments.
What You Get
- The implement, test, verify and commit cycle
- Slicing strategies with examples
- Rules from simplicity to rollback-friendly changes
- A per-increment checklist and a prompt pattern for directing an agent
Common Use Cases
- Implementing a feature from a task breakdown
- Making a multi-file change
- Merging unfinished work behind a feature flag
- Refactoring in small steps
What Makes It Unique
The skill pairs slicing strategies with explicit scope control and a rule against re-running a verification command when the code has not changed. It also gives a short prompt that tells an agent what is in and out of scope for each increment.
Under The Hood
The skill is a single SKILL.md of instructions. It runs no scripts of its own. The agent runs the repository’s own test, build, type check and lint commands and makes git commits after each slice, and it points to the git-workflow-and-versioning skill and a definition-of-done reference.