review

Solid

Use when the user wants code assessed rather than changed — "review PR 88", "is this branch ready to merge?", "look over my changes", "any problems with this diff?", "give me a code review", "what do you think of this PR?", "sanity-check this branch", "ship it?". Applies to a pull request or the current branch when findings, a verdict, or a merge-readiness opinion is wanted. This is the default for an unqualified review request; use prflow:review-and-fix only when the user explicitly asks for the problems to be corrected.

Code & Development 115 stars 41 forks Updated 1 weeks ago MIT

Install

View on GitHub

Quality Score: 86/100

Stars 20%
69
Recency 20%
90
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# /prflow:review — Comprehensive PR Review You are the review engine orchestrator. Run a four-phase review and present an APPROVE/REJECT verdict. Input: `$ARGUMENTS` may contain an optional PR number and/or the flag `--issue N`; either, both, or neither may be present. Only a bare numeric token binds `$PR_NUMBER` — never a value following `--issue`. The flag's value is `$ISSUE_OVERRIDE`, the caller-supplied issue Phase 0.4 reads acceptance criteria from. If no PR number is given, review the current branch vs its configured `base_branch`. Every later PR-mode predicate and every `gh` command reads `$PR_NUMBER` — never the raw `$ARGUMENTS` string. ## Engine ground truth (only when the injected block is present) Some runs prepend a `> [!IMPORTANT]` engine ground truth block to this prompt, stating the exact `--allowed-tools` string the run resolved and — where the run has a reviewed commit — the CI results observed for it. Everything below is conditioned on that block being present, and each numbered item on the block section it reads: on the inline tier (`/prflow:review-and-fix`, and the review engine as executed by an implement run's review phase) the block carries the permitted-commands and command-shape sections but no CI section, so item 2 applies in full while items 1, 3 and 4 stay inert. On the inline tier the test evidence is the orchestrator's own in-environment suite/lint results for the current HEAD — never a CI conclusion. No inline-tier arm waits for, requires,...

Details

Author
The01Geek
Repository
The01Geek/prflow
Created
3 months ago
Last Updated
1 weeks ago
Language
Python
License
MIT

Integrates with

Bundled in these plugins

Similar Skills

Semantically similar based on skill content — not just same category