Invoke a reviewer agent to validate a build step and produce approval or feedback.
npx skills add https://github.com/lenlla/one_shot_build --skill review-step-lenlla
Please help me install this Agent Skill. Skill: review-step Source: https://github.com/lenlla/one_shot_build/tree/main/skills/review-step Command: npx skills add https://github.com/lenlla/one_shot_build --skill review-step-lenlla
Manually invoke a reviewer agent to validate the work produced for a specific epic and step when the normal build-step review flow is not appropriate or when an automated review must be re-run.
Run the review-step skill to invoke the reviewer agent for the current epic and step, collect the git diff and test results, and produce an approval or requested-changes response.
High-intent search queries and answers about installing and using this skill.
To manually run a code review, invoke the reviewer agent to validate the current build step's work, compute the git diff, and produce an approval or requested changes response.
Yes, you can re-run an automated code review outside the normal pipeline by dispatching the reviewer agent for a specific epic and step to validate work and update the execution state.
To dispatch a reviewer subagent you need repository git history access, the execution state file, test results, and a Task tool capable of updating execution state with approval or feedback.
The reviewer agent validates code changes by computing the git diff since the last approved step or TDD baseline to scope the review and provide the step specification for formal validation.
Manually trigger a code review when the normal build-step review flow is not appropriate, or when you need to re-run automated reviews for a specific epic and step after iterating outside the pipeline.
After a manual code review completes, the reviewer output is processed to mark approval or surface requested changes, and the execution state file is updated accordingly to reflect the verdict.
unclehowellReview code changes against quality and security checklists before merging.
TschonsenAudit milestone deliverables against plan expectations using git history and tests.
catlog22Orchestrate multi-agent software development workflows across specification, planning, implementation, testing, and review.
randoneeringDispatch a reviewer subagent to gather context for structured code-review requests.
