Implement evaluated findings: load code-style rules, apply the accepted fixes, then close out the change with full or quick QA. Use after $evaluate-findings has tagged findings and they need to be implemented, or when the user asks to "resolve findings", "apply evaluated findings", or "dispatch findings to implementation".
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Apply evaluated findings and close out the change.
At the start, use update_plan to track each step, restating any remaining steps of a parent workflow alongside them:
$code-style skill$apply-findings skill$code-style SkillRun the $code-style skill to load existence, reuse, mirror, and symmetry rules before editing.
$apply-findings SkillRun the $apply-findings skill on the evaluated findings.
If no changes were made, skip this step.
Use request_user_input to choose how to close out the change:
$finalize skill$quick-finalize skillThen call update_plan to mark this step completed and continue with the next step of the active workflow.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Apply findings by making the suggested code changes. Applies accepted verdicts, escalates ambiguous findings to the user, and offers to note genuine improvements for later. Use when the user asks to "apply findings", "apply fixes", "apply suggestions", "apply accepted findings", "fix the findings", or "apply the review results".
The English summary is being prepared. Showing the original description.
Audit the turbo skill lessons that /self-improve writes into this repo's .turbo/handoff/ from other projects, apply the ones the user approves, delete the consumed handoffs, commit and push, and update the installed Turbo skills. Use when the user asks to "read .turbo/handoff and let me know what you think", "read the handoff files and let me know what you think", "review the lesson handoffs", "apply the self-improve handoffs", or "process the turbo handoffs".
The English summary is being prepared. Showing the original description.
Assess project-wide structural technical debt: complexity hotspots, deprecated API usage, duplication clusters, architecture rot, and low-value tests. Ranks findings by impact and refactor effort into a report at .turbo/technical-debt.md. Use when the user asks to "assess technical debt", "find technical debt", "review technical debt", "what should we refactor", "find refactoring candidates", "where is the code rot", "what's our worst code", "find low-value tests", or "which tests can we delete". Analysis-only — does not modify code.
The English summary is being prepared. Showing the original description.
Shared changelog conventions and formatting rules referenced by /create-changelog and /update-changelog. Not typically invoked directly.
The English summary is being prepared. Showing the original description.
Shared changelog conventions and formatting rules referenced by $create-changelog and $update-changelog. Not typically invoked directly.
The English summary is being prepared. Showing the original description.
Run a non-interactive Claude Code print-mode call from Codex. Use when the user asks to "claude print", "ask claude", "run claude", "consult claude", or when a Codex Turbo skill needs Claude as an independent peer reviewer.
The English summary is being prepared. Showing the original description.