Start a fresh conversation. Replace the highlighted placeholders.
Use implement to implement the work in [PRD or issue set] in this project, using TDD at agreed seams where practical; run regular typechecks and focused tests, then the full suite, review the result, and commit it to the current branch. Verify environment-specific commands and dependencies before making changes.
Required inputs
[PRD or issue set]
User-approved starter prompt based on a pinned source version; check current skill requirements before running. Task evidence ↗
SKILL.md
name: implementdescription: Implement a piece of work based on a PRD or set of issues.risk: criticalsource: https://github.com/mattpocock/skills/tree/main/skills/engineering/implementsource_repo: mattpocock/skillssource_type: communitydate_added: 2026-07-01license: MITlicense_source: https://github.com/mattpocock/skills/blob/main/LICENSE
When to Use
Use this skill when you need to implement a piece of work based on a PRD or set of issues.
Implement the work described by the user in the PRD or issues.
Use the project's actual test workflow at pre-agreed seams; /tdd is an upstream command, not a promised available host tool. Preserve the attached plan and existing todos.
Run typechecking regularly, single test files regularly, and the full test suite once at the end.
Review the net diff and actual verification evidence. Use /review only when available; otherwise perform the review directly.
Commit only the authorized scope on a topic branch following repository policy; inspect staged files and preserve unrelated work. Do not commit to a protected default branch or publish merely because implementation was requested.
Example
User request:
Implement a piece of work based on a PRD or set of issues.
Limitations
Use this skill only when the task clearly matches its upstream source and local project context.
Verify commands, generated code, dependencies, credentials, and external service behavior before applying changes.
Do not treat examples as a substitute for environment-specific tests, security review, or user approval for destructive or costly actions.