Skip to content
Skills Library
AI & agents · Tool integration

codejury-setup

/codejury-setup

Set up CodeJury or diagnose its local prerequisites when the user asks to install it, choose coding agents, or check whether a review can run. Setup does not start a review.

Repository
codejury ↗
Licence
MIT
Last repository change
25.10.2026

Assessment and security

96/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content31 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
2
Deprecation

No signals detected. Repository changed on 25.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Set up CodeJury or diagnose its local prerequisites when the user asks to install it, choose coding agents, or check whether a review can run. Setup does not start a review.

Original author description

Set up CodeJury or diagnose its local prerequisites when the user asks to install it, choose coding agents, or check whether a review can run. Setup does not start a review.

How it works

SKILL.md has no level-two headings · 51 lines, 377 words

SKILL.md preview
---
name: codejury-setup
description: Set up CodeJury or diagnose its local prerequisites when the user asks to install it, choose coding agents, or check whether a review can run. Setup does not start a review.
---

# Set up CodeJury

CodeJury runs on the user's computer. It orchestrates separately installed agent
CLIs; this plugin supplies instructions, not agent accounts or subscriptions.
Follow the user's requested scope and existing authorization.
Reviews start from PR links; local files or folders alone are not supported
review targets for this plugin. Setup can check prerequisites before a PR is
selected, without starting a review.

1. Check `node --version`, `npm --version`, and `git --version`. Node must be at
   least 20.10. For GitHub PRs, also check `gh --version` and `gh auth status`.
   Identify missing prerequisites before attempting a review. Help install or
   authenticate them only within the user's requested setup scope.
2. Resolve `<plugin-root>` as two directories above this skill folder. Use this
   runner for plugin commands:

   ```sh
   node "<plugin-root>/scripts/jury.mjs" version
   node "<plugin-root>/scripts/jury.mjs" agents
   ```

   The launcher checks `npm root --global` for CodeJury and reuses that global
   installation. If missing, it runs `npm install --global @agentsdance/codejury@latest`.
   It reports the version and absolute CLI path. Installation errors stop setup;
   never use npx, a custom prefix, or a plugin-private CLI copy as a fallback.
   Existing versions are not upgraded automatically. For a requested version,
   install that version globally and check its help before using its options.
3. `jury agents` checks executable availability, not authentication or quota.
   Report these separately. Consult the CLI's built-in install hints for missing
   agents. Let the user complete provider sign-in; do not collect credentials
   into the plugin or copy credentials between providers.
4. Preserve existing role/model settings. Use per-run `--judge`, `--jury`, and
   `--model` flags for a particular review. Change global defaults with `jury
   agents judge`, `jury agents jury`, or `jury agents model` only when the user
   asks to save defaults.
5. Report the CLI version, available agents, remaining prerequisites, and a
   suitable PR-link command. If no PR URL is available, request it before a
   subsequent review rather than defaulting to local files. Do not start agents
   just to validate setup.

A CodeJury review can edit files, create commits, and push fixes. Pushing defaults
to `--push=true`. Honor requests to keep fixes local with `--push=false`.
Agent providers process the review's code and prompts and may charge for usage.
`--push=false` disables Jury's pushes; it does not make a review read-only or
sandbox an agent.

Official project documentation:
[setup](https://github.com/agentsdance/codejury#quick-start) and
[configuration](https://github.com/agentsdance/codejury/blob/master/docs/configuration.md).

Versions

The database has no other skills named codejury-setup.

Database snapshot: 13.11.2026 · package version 9c6a61809895 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100codejury
    Review a pull request with CodeJury using separate Claude judge and reviewer sessions. Use when asked to run the CodeJury review loop, re-review a PR after fixes, or manually triage CodeJury findings.
  • 86codejury-results
    List, inspect, or summarize saved CodeJury reviews and findings, or reopen their local console, without starting new reviewers. Use when the user asks what a prior jury found or wants its saved evidence.
  • 96setup-autoontology
    Set up and run AutoOntology locally in one go — check prerequisites, install, configure the chat provider (default the user's Claude login, no API key), build the quickstart sample set and show the web UI URL. Use when the user asks to install, set up, bootstrap, start or try AutoOntology.
  • 86setup
    Install and connect memry, the persistent memory for AI coding agents. Use when the user wants to set up memry, asks why memry tools are missing, or wants Claude Code to remember context between sessions.
  • 90setup-agent-md
    Use when a repository needs one canonical instruction file shared by coding agents, when AGENTS.md or CLAUDE.md is missing, or when their guidance has diverged.
  • 90setup-shadowclone
    Install and configure shadowclone for the user from start to finish. Use it when the user asks to "set up", install, configure, or start shadowclone with Claude Code, Codex, Cursor, Pi, Antigravity, OpenCode, or another agent.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.