Show Code Review Results

VerifiedCaution

Displays code review results for a specific commit or job ID. Use it to check the verdict, findings, and questions from a previous review without triggering a new analysis. It also shows recent review jobs and the prompt sent to the reviewer.

Sby Skills Guide Bot
DevelopmentBeginner
6/2/2026
Claude CodeCursorWindsurfCopilotCodex
#code-review#show-results#roborev#review-status

Recommended for

Automated summary

Displays existing code review results for a commit or job without re-running the analysis.

Strengths

  • Quickly retrieve verdict and findings from a previously run review
  • Avoids re-running expensive analysis when results already exist
  • Supports multiple access modes: commit SHA, job ID, or default HEAD

Limitations

  • Requires that a review was already submitted via roborev-review
  • Results are static and reflect only the original review run
  • Cannot provide real-time updates or partial re-execution
When to use it

Use this skill to inspect the outcome of a code review without triggering a new analysis.

When not to use it

Avoid using it when you need to review new changes or if the job ID is unknown or expired.

Security analysis

Caution
Quality score80/100

The skill uses Bash to run 'roborev show' commands, passing user input directly to the shell. Without sanitization, an attacker could inject shell metacharacters (e.g., '; rm -rf /'). While intended for legitimate code review display, the lack of input validation poses a moderate risk.

Findings
  • •Potential command injection via unsanitized arguments. The skill constructs bash commands directly with user-provided arguments ($ARGUMENTS) without escaping or validation, which could allow execution of arbitrary commands if a malicious argument is supplied.
How this analysis is made

Examples

Show recent reviews
Show me the recent code reviews.
Show review for commit abc123
Show the review results for commit abc123.
Show review by job ID
Show the review for job ID 9.

name: roborev-show description: Show existing code review results for a commit or job. Use to check review status without re-running. argument-hint: "[commit-sha|job-id]" allowed-tools: Bash

Roborev Show Skill

Display the results of an existing code review.

Usage

| Argument | Command | Description | |----------|---------|-------------| | (none) | roborev show | Show review for HEAD | | status | roborev status | List recent jobs with IDs | | <sha> | roborev show <sha> | Show review for specific commit | | <job-id> | roborev show --job <id> | Show review by job ID | | prompt <id> | roborev show --prompt <id> | Show the prompt sent to the reviewer |

Finding Job IDs

If the user doesn't know the job ID, run roborev status first to show recent jobs:

Recent Jobs:
  ID  SHA                Repo                 Agent  Status  Time
  9   dirty              buzzsprout-headless  codex  done    1m13s
  8   dirty              buzzsprout-headless  codex  done    2m5s

Then use the ID with roborev show --job <id>.

Instructions

  1. If user asks to see "recent reviews" or doesn't provide an ID, run roborev status first

  2. Parse the argument: $ARGUMENTS

  3. Run the appropriate command:

    • If empty: roborev show
    • If starts with "prompt ": roborev show --prompt <rest>
    • If numeric and user wants job ID: roborev show --job $ARGUMENTS
    • Otherwise: roborev show $ARGUMENTS
  4. Present the review results, highlighting:

    • Verdict (pass/fail)
    • Findings by severity
    • Questions/assumptions

Related Skills

  • /roborev-review - Run a new review
  • /roborev-address - Fix findings from a review
  • /roborev-refine - Automated fix loop

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/show-code-review-results-mm5t8arq/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/show-code-review-results-mm5t8arq' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/show-code-review-results-mm5t8arq/download' --output '.skill-downloads/show-code-review-results-mm5t8arq/SKILL.md.part' && mv '.skill-downloads/show-code-review-results-mm5t8arq/SKILL.md.part' '.skill-downloads/show-code-review-results-mm5t8arq/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

Tools declared by the author (check availability in your agent): Bash

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/show-code-review-results-mm5t8arq/SKILL.md' && test -s '.skill-downloads/show-code-review-results-mm5t8arq/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/roborev-show' && cp -R '.skill-downloads/show-code-review-results-mm5t8arq' '.claude/skills/roborev-show'

Cursor
test -f '.skill-downloads/show-code-review-results-mm5t8arq/SKILL.md' && test -s '.skill-downloads/show-code-review-results-mm5t8arq/SKILL.md' && mkdir -p '.cursor/skills' && test ! -e '.cursor/skills/roborev-show' && cp -R '.skill-downloads/show-code-review-results-mm5t8arq' '.cursor/skills/roborev-show'

Codex
test -f '.skill-downloads/show-code-review-results-mm5t8arq/SKILL.md' && test -s '.skill-downloads/show-code-review-results-mm5t8arq/SKILL.md' && mkdir -p '.agents/skills' && test ! -e '.agents/skills/roborev-show' && cp -R '.skill-downloads/show-code-review-results-mm5t8arq' '.agents/skills/roborev-show'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/show-code-review-results-mm5t8arq'

openskills read 'show-code-review-results-mm5t8arq'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/show-code-review-results-mm5t8arq/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills