apply-turbo-handoffs
Audit the turbo skill lessons that /self-improve writes into this repo's .turbo/handoff/ from other projects, apply the ones the…
@tobihagemannInstall SkillDevelopment
Skill
/review-pr
Review a pull request by fetching PR comments, running a comprehensive code review, evaluating findings, and dispatching to implementation. Use when the user asks to \"review PR\", \"review pull request\", \"review this PR\", \"check PR before merging\", or \"full PR review\".
Claude Code
$ npx -y skills add tobihagemann/turbo --skill review-pr --agent claude-code
Codex
$ npx skills add tobihagemann/turbo --skill review-pr -a codex -y
Cursor
$ npx skills add tobihagemann/turbo --skill review-pr -a cursor -y
Gemini CLI
$ npx skills add tobihagemann/turbo --skill review-pr -a gemini-cli -y
GitHub Copilot
$ npx skills add tobihagemann/turbo --skill review-pr -a github-copilot -y
OpenCode
$ npx skills add tobihagemann/turbo --skill review-pr -a opencode -y
Windsurf
$ npx skills add tobihagemann/turbo --skill review-pr -a windsurf -y
SKILL.md
review-pr.SKILL.mdname: review-pr
description: "Review a pull request: run a full code review of its diff, evaluate findings, and implement them. Use when the user asks to \"review PR\", \"review this PR\", or \"check PR before merging\"."
Review PR
Run a comprehensive code review of the PR's diff, evaluate findings, and dispatch accepted findings to implementation.
Task Tracking
At the start, use `TaskCreate` to create a task for each step:
1. Resolve base branch 2. Run `/review-code` skill 3. Run `/evaluate-findings` skill 4. Run `/implement-findings` skill
Step 1: Resolve Base Branch
Detect the PR's base branch and the issues it closes via `gh pr view --json baseRefName,closingIssuesReferences`, then run `git fetch origin <base-branch>` to bring the remote ref up to date.
Step 2: Run `/review-code` Skill
When the PR closes issues, fetch each by its URL with `gh issue view <url> --json title,body,comments`, issuing the calls together. Together, their text is the governing document.
Run the `/review-code` skill. The diff command is `git diff origin/<base-branch>...HEAD`. Take the base from `origin/`: a local branch of the same name can sit behind the remote, which puts the merge base before an already-merged pull request and pulls merged work into the review as if it were new. Supply the governing document when there is one.
Step 3: Run `/evaluate-findings` Skill
Run the `/evaluate-findings` skill on the results from Step 2.
Step 4: Run `/implement-findings` Skill
If zero actionable findings survive evaluation, report that the code looks clean and stop.
Otherwise, run the `/implement-findings` skill on the accepted findings from Step 3.
Read more
name: review-pr description: "Review a pull request: run a full code review of its diff, evaluate findings, and implement them. Use when the user asks to \"review PR\", \"review this PR\", or \"check PR before merging\"."
Review PR
Run a comprehensive code review of the PR's diff, evaluate findings, and dispatch accepted findings to implementation.
Task Tracking
At the start, use `TaskCreate` to create a task for each step:
1. Resolve base branch 2. Run `/review-code` skill 3. Run `/evaluate-findings` skill 4. Run `/implement-findings` skill
Step 1: Resolve Base Branch
Detect the PR's base branch and the issues it closes via `gh pr view --json baseRefName,closingIssuesReferences`, then run `git fetch origin <base-branch>` to bring the remote ref up to date.
Step 2: Run `/review-code` Skill
When the PR closes issues, fetch each by its URL with `gh issue view <url> --json title,body,comments`, issuing the calls together. Together, their text is the governing document.
Run the `/review-code` skill. The diff command is `git diff origin/<base-branch>...HEAD`. Take the base from `origin/`: a local branch of the same name can sit behind the remote, which puts the merge base before an already-merged pull request and pulls merged work into the review as if it were new. Supply the governing document when there is one.
Step 3: Run `/evaluate-findings` Skill
Run the `/evaluate-findings` skill on the results from Step 2.
Step 4: Run `/implement-findings` Skill
If zero actionable findings survive evaluation, report that the code looks clean and stop.
Otherwise, run the `/implement-findings` skill on the accepted findings from Step 3.
Ships withturbo
Reusable workflows for planning, building, reviewing, and shipping with Claude Code and Codex.
41775 skills
Stars on GitHub
Momentum
- stars in total
- 417
Other skills on turbo.
@tobihagemannInstall Skillapply-findings
Apply findings by making the suggested code changes. Applies accepted verdicts, escalates ambiguous findings to the user, and…
@tobihagemannInstall Skillassess-technical-debt
Assess project-wide structural technical debt: complexity hotspots, deprecated API usage, duplication clusters, architecture rot,…
@tobihagemannInstall Skillchangelog-rules
Shared changelog conventions and formatting rules referenced by /create-changelog and /update-changelog. Not typically invoked…
@tobihagemannInstall Skillcode-style
Enforce existence, reuse, mirror, and symmetry principles to keep new code minimal and consistent with surrounding code. Use when…
@tobihagemannInstall Skillcodex-exec
Run autonomous task execution using the codex CLI. Use when the user asks to \"codex exec\", \"run codex exec\", \"execute a task…
@tobihagemannInstall SkillMore skills from other plugins.
Auto-invoked
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
@obraInstall Skillask-matt
Ask which skill or flow fits your situation. A router over the skills in this repo.
@mattpocockInstall SkillAuto-invoked
Questions about review-pr.
- Which coding agents can use review-pr?
- review-pr installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.