Implement takes the work described in a spec or tickets and builds it. If you pass a ticket reference it fetches the ticket from the issue tracker and states its title first, and it asks when the reference is ambiguous.
It calls the tdd skill where possible at pre-agreed seams, runs typechecking and single test files regularly and the full suite once at the end, calls code-review, and commits.
What You Get
- The ticket title stated back to you before work starts
- Code built test-first through the tdd skill
- Typechecks, single-file test runs and one full test run at the end
- A code-review pass over the result
- A commit on the current branch
Common Use Cases
- Working through local ticket files blockers-first, one fresh session each
- Building a small change in the same context window where it was grilled
- Picking up an agent-ready issue produced by triage
What Makes It Unique
It is deliberately short and delegates: test-first building to tdd and review to code-review. It handles one ticket in one context window and pairs with implement-spec for running a whole spec at once. The test cadence is explicit: typecheck and single test files often, the full suite once.
Under The Hood
SKILL.md is a short Markdown instruction with no scripts. The model fetches a ticket from your configured issue tracker, runs typecheck and test commands, invokes the tdd and code-review skills through the Skill tool, edits files in your working tree and commits to the current branch. Automatic model invocation is disabled, so it runs only when you call it.