Setup and workflow
Provide a PR with read-only GitHub access, or paste its diff and context. The native Bot implementation may differ from this template.
- Fix the base/head and requirements so the review target is stable.
- Verify triggers and run suggested tests before a maintainer decides on merging.
Input and output example
Illustrative example · not an execution result
Input
Demo diff: pagination changes offset >= count to offset > count. With count 10 and offset 10, is another request issued?
Output
Risk: if offset is the next batch start, equality means no items remain, but the new condition may allow another request. Check the caller contract and add an equality-boundary test. This is an illustration, not an executed repository test.
Limits and failure cases
- A partial diff cannot establish correctness or security of the whole application.
- Tests that were not run are not reported as passing.
What was verified
- Source check · Verified · 2026-09-05
- Compared with bots/pr-reviewer.md in BotDirectory commit 84dc42af7661. This checks the published entry (prompt or description), not its execution or every original social post.
- Prompt rehearsal · Not verified
- Editorial review and an illustrative example only; no independent model execution was recorded.
- Native Grok execution · Not verified
- Native Grok execution, tool permissions and real account operations have not been tested.
- Bot link access · Not verified
- The source includes a Bot link. HTTP access alone does not establish its identity or functional availability; opening it may require an account.
Source and editorial adaptation
Adapted from PR Reviewer in botdirectory.ai (listed contributor: mustafaergisi), distributed under MIT. Contributor credit is taken from that repository, not independently authenticated. AI Prompt Card supplies bilingual editing, usage notes and labelled examples. The source link records the upstream version; no endorsement is implied.
Source license and attributionCopyable instruction template
Instructions curated or adapted by this site, not a claim to reproduce the native Bot’s internal system prompt. Check setup, tools and limitations before use.
0 opens · 0 copies
Editorial assessment
Use it to prepare a risk list before human review, not to delegate the approval button. Unlike a repository-wide hardening audit, it is bounded by a specified base/head diff. The native source provides a description only; this is an editorially adapted instruction template, not its hidden system prompt.
This directory is an independent, fan-made catalog. It is not affiliated with, endorsed by, or sponsored by xAI or Grok. Grok and related names are trademarks of their respective owners. Live-bot links point to official x.ai pages.
