Agent skill

Prmr Codereview

by HorizonRobotics in HorizonRobotics/RoboOrchardLab

Review a GitHub PR or GitLab MR when the task is a PR/MR review or comment flow.

Apache-2.0Auto-check passedDevelopment

Install Prmr Codereview

skills CLI
$ npx skills add HorizonRobotics/RoboOrchardLab --skill prmr-codereview -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install HorizonRobotics/RoboOrchardLab prmr-codereview --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/HorizonRobotics/RoboOrchardLab.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/codereview/prmr-codereview .claude/skills/prmr-codereview && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
prmr-codereview
GitHub stars
173
Token cost
~961 tokens
SKILL.md length
482 words
Files
2
Skills in repo
8
Repo updated
First seen
Licence
Apache-2.0

At a glance

Review a GitHub PR or GitLab MR when the task is a PR/MR review or comment flow.

  • Works in 7 steps: Check locally whether any stop condition… → Fetch the title, description, source and… → If comment publication was requested,… → …
  • PR/MR-specific transport
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Comment workflows

What it does

Prmr Codereview is an agent skill from HorizonRobotics/RoboOrchardLab. Review a GitHub PR or GitLab MR when the task is a PR/MR review or comment flow. Use this skill for PR/MR-specific transport, metadata, and comment workflows.

Its SKILL.md is about 960 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `REPORT_TEMPLATE.md`).

It sits in Development. It works with GitHub and GitLab. The licence is Apache-2.0.

When your agent uses it

  • PR/MR-specific transport
  • Comment workflows

Example prompts

  • “/prmr-codereview”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Check locally whether any stop condition applies
  2. Fetch the title, description, source and target branches, current head,
  3. If comment publication was requested, determine whether summary comments,
  4. Run ../changeset-codereview/SKILL.md against the full current PR/MR diff.
  5. Convert the validated findings into REPORT_TEMPLATE.md.
  6. Before posting issue comments, prepare and verify the complete comment set.
  7. Post validated issue comments using the platform-appropriate mechanism.

What it can do on your machine

Read from SKILL.md and the folder at commit 221ec0e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Prmr Codereview loads about 961 tokens when it runs. Until then it costs about 44 tokens; SKILL.md has 482 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~44
When it runs · the whole SKILL.md, loaded when a task matches
~961

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from HorizonRobotics/RoboOrchardLab at commit 221ec0e, republished under its Apache-2.0 licence (© HorizonRobotics). 482 words, ~961 tokens.

Download SKILL.mdSave it as .claude/skills/prmr-codereview/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
prmr-codereview
description
Review a GitHub PR or GitLab MR when the task is a PR/MR review or comment flow. Use this skill for PR/MR-specific transport, metadata, and comment workflows.

Provide a code review for the given pull request or merge request.

Use this skill after .agents/skills/codereview/SKILL.md routes the task here. Read ../references/triggering-and-signal.md and ../references/review-depth-and-delegation.md first. When composing the final report, also read ../references/report-composition.md.

Do not use this skill for commit, branch, staged, working-tree, patch, or generic local review. Use ../changeset-codereview/SKILL.md for those. If architecture review is explicitly requested or materially applicable, pass that dimension into the changeset workflow rather than launching a separate architecture agent here. Keep this skill as the main report owner and summarize paired logical review inputs in Related review inputs.

Follow ../references/review-depth-and-delegation.md. The main agent owns PR/MR triage, metadata, prior-comment inspection, and comment transport. The delegated changeset review owns the one-reviewer-per-round budget and review loop transitions.

To do this:

  1. Check locally whether any stop condition applies:

    • The PR/MR is closed.
    • It is a draft.
    • It is automated or trivial and clearly does not need code review.
    • The current authenticated reviewer already reviewed the same head and the user did not request re-review.

    If a condition applies, stop. If the head advanced or the user explicitly requested re-review, continue with a fresh pass on the current head.

  2. Fetch the title, description, source and target branches, current head, file list, and full current diff.

    • For re-review, also fetch the last reviewed head when available, the incremental diff, and prior findings or comment threads that need status verification.
  3. If comment publication was requested, determine whether summary comments, inline comments, or both are required.

  4. Run ../changeset-codereview/SKILL.md against the full current PR/MR diff. Pass the title, description, prior-findings ledger, last reviewed head, and any architecture-review requirement as context. Do not launch another PR/MR-specific review agent; use the current round's changeset reviewer across all applicable review dimensions.

  5. Convert the validated findings into REPORT_TEMPLATE.md.

    • Summarize paired logical review inputs without copying their findings into the main findings sections.
    • Include a required architecture summary when architecture review applied.

    If --comment was not provided, stop here. If it was provided and no issues were found, post the summary comment and stop.

  6. Before posting issue comments, prepare and verify the complete comment set.

    • For re-review, separate fixed prior findings, unresolved prior findings, and newly introduced validated issues.
    • Run one convergence check against the current full diff.
  7. Post validated issue comments using the platform-appropriate mechanism.

    • For GitHub, use the GitHub inline comment tool with confirmed: true.
    • For GitLab, use available GitLab review or note tooling. If inline comments are unavailable, post only the top-level summary and state that inline comments were skipped due to tool limitations.
    • Use committable suggestions only for small fixes that the suggestion resolves completely.
    • Reuse existing discussions for previously reported findings when possible; open new comments only for new findings.
Show full SKILL.md (27 more words)Show less

Notes:

  • Use gh for GitHub and glab for GitLab. Do not use web fetch.
  • Keep PR/MR transport and publication logic here; keep generic diff review in changeset-codereview.

© HorizonRobotics, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .agents/skills/codereview/prmr-codereview of HorizonRobotics/RoboOrchardLab.

  • SKILL.md
  • REPORT_TEMPLATE.md

Open the folder on GitHubat commit 221ec0e

Compare with similar skills

Prmr Codereview next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Prmr Codereview compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Prmr Codereview this skillHorizonRobotics/RoboOrchardLab173—~961Automated safety check: PassApache-2.0
Greplooponyx-dot-app/onyx32k4 repos~3.3kAutomated safety check: PassMIT
Check PRonyx-dot-app/onyx32k2 repos~2.3kAutomated safety check: PassMIT
Visual Reviewai-dynamo/dynamo8.2k—~4.5kAutomated safety check: PassApache-2.0
Debate ReviewamElnagdy/review-skills1322 repos~986Automated safety check: PassMIT
degit Project ScaffoldingRich-Harris/degit7.9k—~534Automated safety check: PassMIT

Similar skills

  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    DevelopmentAuto-check passed
  • Check PR

    onyx-dot-app/onyx

    Checks a GitHub, GitLab, or Perforce (p4) pull request (or merge request, or shelved changelist) for unresolved review comments, failing status checks, and incomplete PR descriptions.

    32k GitHub starsUsed in 2 repos~2.3k tokens
    DevelopmentAuto-check passed
  • Visual Review

    ai-dynamo/dynamo

    Create self-contained interactive HTML code-review dashboards from GitHub or GitLab pull requests, checked-out branch diffs, or supplied unified diffs, with correctness and safe-to-merge scores…

    8.2k GitHub stars~4.5k tokensUpdated today
    DevelopmentAuto-check passed
  • Debate Review

    amElnagdy/review-skills

    Two-model debate review of a GitHub PR, GitLab MR, Azure DevOps PR, or local working tree, posted as inline comments or printed.

    132 GitHub starsUsed in 2 repos~986 tokens
    DevelopmentAuto-check passed
  • degit Project Scaffolding

    Rich-Harris/degit

    Downloads a repository snapshot or template with degit into an empty folder, from GitHub, GitLab, Bitbucket, Sourcehut or a Gist, optionally at a branch, tag or commit.

    7.9k GitHub stars~534 tokensUpdated 25 days ago
    DevelopmentAuto-check passed
  • Greploop Apps

    michaelshimeles/skills

    Loops on a large pull request, merge request or Perforce changelist, fixing Greptile findings until it scores 5/5 with no unresolved comments.

    1.3k GitHub starsUsed in 1 repo~3.6k tokens
    DevelopmentAuto-check passed

More from HorizonRobotics/RoboOrchardLab

All 8 skills in this repo
  • Feature Dev

    HorizonRobotics/RoboOrchardLab

    Guided feature development with codebase understanding and architecture focus.

    173 GitHub stars~797 tokensUpdated 14 days ago
    Auto-check passed
  • Codereview Family

    HorizonRobotics/RoboOrchardLab

    Structured code review family for explicit heavy review requests and architecture-sensitive review/evaluation requests.

    173 GitHub stars~724 tokensUpdated 14 days ago
    Auto-check passed
  • Architecture Review

    HorizonRobotics/RoboOrchardLab

    Review local code, diffs, modules, directories, or design changes for consequential architecture issues when the user explicitly asks for architecture review, when an upstream review routes…

    173 GitHub stars~1k tokensUpdated 14 days ago
    Auto-check passed
  • Code Architect

    HorizonRobotics/RoboOrchardLab

    Designs feature architectures by analyzing existing codebase patterns and conventions, then providing comprehensive implementation blueprints with specific files to create or modify, component…

    173 GitHub stars~750 tokensUpdated 14 days ago
    Auto-check passed
  • Code Explorer

    HorizonRobotics/RoboOrchardLab

    Deeply analyzes existing codebase features by tracing execution paths, mapping architecture layers, understanding patterns and abstractions, and documenting dependencies to inform new development.

    173 GitHub stars~721 tokensUpdated 14 days ago
    Auto-check passed
  • Code Reviewer

    HorizonRobotics/RoboOrchardLab

    Reviews code for bugs, logic errors, security vulnerabilities, code quality issues, and adherence to project conventions, using confidence-based filtering to report only high-priority issues that…

    173 GitHub stars~1.2k tokensUpdated 14 days ago
    Auto-check passed

Works with

Categories

Questions about Prmr Codereview

What does Prmr Codereview do?

Review a GitHub PR or GitLab MR when the task is a PR/MR review or comment flow. Prmr Codereview is an agent skill from HorizonRobotics/RoboOrchardLab. Review a GitHub PR or GitLab MR when the task is a PR/MR review or comment flow.

When should I use Prmr Codereview?

Prmr Codereview fits situations like: PR/MR-specific transport; comment workflows.

How do I install Prmr Codereview in Claude Code?

Run `npx skills add HorizonRobotics/RoboOrchardLab --skill prmr-codereview -a claude-code`. Or copy the skill folder (.agents/skills/codereview/prmr-codereview in HorizonRobotics/RoboOrchardLab) into .claude/skills/prmr-codereview in your project. Claude Code loads it when a task matches its description.

How do I install Prmr Codereview in Codex?

Run `npx skills add HorizonRobotics/RoboOrchardLab --skill prmr-codereview -a codex`. Or copy the skill folder (.agents/skills/codereview/prmr-codereview in HorizonRobotics/RoboOrchardLab) into .agents/skills/prmr-codereview in your project. Codex loads it when a task matches its description.

Can I use Prmr Codereview in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add HorizonRobotics/RoboOrchardLab --skill prmr-codereview -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/prmr-codereview, .gemini/skills/prmr-codereview, .github/skills/prmr-codereview and .opencode/skills/prmr-codereview in your project.

What does Prmr Codereview need to run?

SKILL.md names no scripts, command-line tools or credentials: Prmr Codereview is instructions for the agent only.

Does Prmr Codereview access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Prmr Codereview safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Prmr Codereview use?

Prmr Codereview is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Prmr Codereview use?

About 961 tokens (SKILL.md is roughly 3.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Prmr Codereview?

Skills that share tags, products or a category with Prmr Codereview: Greploop (onyx-dot-app/onyx, 32k stars), Check PR (onyx-dot-app/onyx, 32k stars), Visual Review (ai-dynamo/dynamo, 8.2k stars) and Debate Review (amElnagdy/review-skills, 132 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Prmr Codereview?

HorizonRobotics (a GitHub organization) maintains it in HorizonRobotics/RoboOrchardLab, which has 173 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on September 24, 2026.

Source: HorizonRobotics/RoboOrchardLab on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.