New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Jev Reviewer

by egma-ai in egma-ai/jev-code-reviewer

Analyze and refresh Jev-Reviewer results when creating, updating, pushing to, or inspecting a GitHub pull request.

MITAuto-check passedDevelopment

Install Jev Reviewer

skills CLI
$ npx skills add egma-ai/jev-code-reviewer --skill jev-reviewer -a claude-code

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

GitHub CLI
$ gh skill install egma-ai/jev-code-reviewer jev-reviewer --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/egma-ai/jev-code-reviewer.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skill/jev-reviewer .claude/skills/jev-reviewer && 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
jev-reviewer
GitHub stars
140
Token cost
~1.2k tokens
SKILL.md length
627 words
Files
3 (incl. references)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Analyze and refresh Jev-Reviewer results when creating, updating, pushing to, or inspecting a GitHub pull request.

  • Development work in your project
  • SKILL.md covers Creating or updating a pull…, Live analysis, Recorded demo and Browser bridge, plus 1 more section
  • Needs TYPESAFE_API_KEY and OPENAI_API_KEY

What it does

Jev Reviewer is an agent skill from egma-ai/jev-code-reviewer. Analyze and refresh Jev-Reviewer results when creating, updating, pushing to, or inspecting a GitHub pull request. Use after an agent changes a PR and for historical-PR demos; this skill invokes the local CLI and is not a guaranteed background hook.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `agents/openai.yaml` and `references/priority-policy.md`).

It sits in Development. It works with GitHub. The repository describes itself as: Review behavior, not just diffs. Jev prioritizes human attention; OpenAI explains the changes. Local CLI + agent skill + GitHub extension. The licence is MIT.

When your agent uses it

  • Development work in your project

Example prompts

  • “/jev-reviewer”

Requirements

  • A credential in TYPESAFE_API_KEY
  • A credential in OPENAI_API_KEY

What it can do on your machine

Read from SKILL.md and the folder at commit 5bc56f2. 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 (its code samples are bash).

    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 these keys or tokens, usually read from environment variables:

    • TYPESAFE_API_KEY
    • OPENAI_API_KEY

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

Context cost

Jev Reviewer loads about 1.2k tokens when it runs, and up to ~1.5k if it reads all its reference files. Until then it costs about 66 tokens; SKILL.md has 627 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~66
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.5k

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 egma-ai/jev-code-reviewer at commit 5bc56f2, republished under its MIT licence (© egma-ai). 627 words, ~1,161 tokens.

Download SKILL.mdSave it as .claude/skills/jev-reviewer/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
jev-reviewer
description
Analyze and refresh Jev-Reviewer results when creating, updating, pushing to, or inspecting a GitHub pull request. Use after an agent changes a PR and for historical-PR demos; this skill invokes the local CLI and is not a guaranteed background hook.

Jev Reviewer

Use the local jev-reviewer CLI to turn a pull request into prioritized, natural-language review cards for the locally installed browser extension.

Creating or updating a pull request

Complete the requested implementation, run the repository's normal verification, push the intended commits, and create or update the pull request first. Then, as the final post-PR step, run:

bash
jev-reviewer analyze --pr <github-pr-url> --repo <local-repository-path>

Use the full GitHub PR URL returned by the PR workflow and the repository's absolute local path. If the PR identity is unclear, resolve it with the repository's existing GitHub tooling instead of guessing.

This is a best-effort agent workflow, not an event listener. Do not claim the skill will run after the agent exits or when another actor pushes commits.

Do not create, push, or modify a PR solely to make analysis possible unless the user requested that action. If no PR exists or the latest commits are not pushed, state that analysis is deferred and provide the exact command to run later.

Live analysis

Live analysis requires locally configured TYPESAFE_API_KEY for Jev classification and OPENAI_API_KEY for natural-language explanations. Before analyzing, run this check. It prints where each key comes from and whether each provider accepts it, never a key value, so it is safe in an agent transcript:

bash
jev-reviewer doctor

Your shell may not load variables the user's login shell exports, so a key that is only in the user's environment can be invisible to you. If doctor reports a missing or environment-only key, ask the user to run this directly in their terminal; it stores keys it finds only in the environment:

bash
jev-reviewer setup

Never ask the user to paste a key into chat, add it to this skill, commit it, print it, or inspect its value. Skill installation and credential setup are separate.

analyze prints how many change units it will send to the providers (default 12, in path order, --max-units up to 100). Tell the user when a PR has more units than were analyzed: files with an unanalyzed change keep GitHub's code in the extension. Do not raise --max-units without the user's agreement, because it increases provider cost and time.

The CLI attempts local Graphify enrichment by default and falls back to source-only context when Graphify is unavailable. --no-graphify disables that attempt; --graphify is an optional explicit enable. Do not present Graphify installation as required.

Show full SKILL.md (243 more words)Show less

Recorded demo

To replay the bundled, precomputed demonstration without provider keys, run:

bash
jev-reviewer demo

Describe this accurately as a recorded report replay, not live model analysis. The bundled report contains real recorded Jev classifications and prepared explanation copy; see demo/README.md for provenance. Follow the command's output to open the standalone replay or matching PR page.

Browser bridge

For a previously analyzed PR, start or confirm the local bridge:

bash
jev-reviewer serve --port 4731

The human can run jev-reviewer token | pbcopy to copy the local browser-extension pairing token. Never run that command in an agent transcript: the token is for the human to paste into the extension's Connection section, whose Save button confirms the pairing. The extension works on GitHub's classic Files changed page (/pull/<n>/files); on the new /changes page it shows a notice instead of the logic view.

Results and policy

  • Treat the cards as supplemental review guidance, not proof that a PR is safe.
  • Report analysis failures and stale results clearly. Never silently reuse results from a different commit.
  • Preserve existing tests, approval rules, and human-review requirements.
  • Use P0 as the highest priority. Read references/priority-policy.md only when interpreting or changing priority policy.
  • Configure priorities in config/policy.json, a repository .jev-reviewer.json, or a file passed with --policy; do not edit this skill to change review policy.
  • Do not start a persistent server unless the user is preparing to use the browser extension or explicitly asks for it.

If jev-reviewer is unavailable, report the missing prerequisite instead of inventing an installation command.

© egma-ai, MIT. 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 2 other files (references) in skill/jev-reviewer of egma-ai/jev-code-reviewer.

  • SKILL.md
  • agents/openai.yaml
  • references/priority-policy.md

Open the folder on GitHubat commit 5bc56f2

Compare with similar skills

Jev Reviewer 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.

Jev Reviewer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Jev Reviewer this skillegma-ai/jev-code-reviewer140—~1.2kAutomated safety check: PassMIT
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated 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
Setup Matt Pocock Skillsbestofjs/bestofjs3.1k20 repos~1.7kAutomated safety check: PassMIT
Contributor-First PR MergeHKUDS/OpenHarness16k1 repos~847Automated safety check: PassMIT

Similar skills

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed

  • 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

  • Setup Matt Pocock Skills

    bestofjs/bestofjs

    Configure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout.

    3.1k GitHub starsUsed in 20 repos~1.7k tokens
    DevelopmentAuto-check passed

  • Contributor-First PR Merge

    HKUDS/OpenHarness

    Merges external GitHub pull requests while keeping the original author credited, and fixes conflicts after the merge instead of rewriting the contribution.

    16k GitHub starsUsed in 1 repo~847 tokens
    DevelopmentAuto-check passed

  • Create Pull Request

    cline/cline

    Opens a GitHub pull request from your current branch with the gh CLI, after reviewing the commits and diff and gathering the details the PR needs.

    70k GitHub starsUsed in 1 repo~1.6k tokens
    DevelopmentAuto-check passed

Works with

Categories

Questions about Jev Reviewer

What does Jev Reviewer do?

Analyze and refresh Jev-Reviewer results when creating, updating, pushing to, or inspecting a GitHub pull request. Jev Reviewer is an agent skill from egma-ai/jev-code-reviewer. Analyze and refresh Jev-Reviewer results when creating, updating, pushing to, or inspecting a GitHub pull request.

When should I use Jev Reviewer?

Jev Reviewer fits situations like: development work in your project.

How do I install Jev Reviewer in Claude Code?

Run `npx skills add egma-ai/jev-code-reviewer --skill jev-reviewer -a claude-code`. Or copy the skill folder (skill/jev-reviewer in egma-ai/jev-code-reviewer) into .claude/skills/jev-reviewer in your project. Claude Code loads it when a task matches its description.

How do I install Jev Reviewer in Codex?

Run `npx skills add egma-ai/jev-code-reviewer --skill jev-reviewer -a codex`. Or copy the skill folder (skill/jev-reviewer in egma-ai/jev-code-reviewer) into .agents/skills/jev-reviewer in your project. Codex loads it when a task matches its description.

Can I use Jev Reviewer 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 egma-ai/jev-code-reviewer --skill jev-reviewer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/jev-reviewer, .gemini/skills/jev-reviewer, .github/skills/jev-reviewer and .opencode/skills/jev-reviewer in your project.

What does Jev Reviewer need to run?

Going by SKILL.md and its folder, Jev Reviewer needs credentials named TYPESAFE_API_KEY and OPENAI_API_KEY. Our summary lists: A credential in TYPESAFE_API_KEY; A credential in OPENAI_API_KEY.

Does Jev Reviewer 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 Jev Reviewer 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 Jev Reviewer use?

Jev Reviewer is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Jev Reviewer use?

About 1.2k tokens (SKILL.md is roughly 4.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 342 tokens, read only when the agent opens those files.

What are the alternatives to Jev Reviewer?

Skills that share tags, products or a category with Jev Reviewer: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Greploop (onyx-dot-app/onyx, 32k stars), Check PR (onyx-dot-app/onyx, 32k stars) and Setup Matt Pocock Skills (bestofjs/bestofjs, 3.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Jev Reviewer?

egma-ai (a GitHub organization) maintains it in egma-ai/jev-code-reviewer, which has 140 GitHub stars. The repository was last updated on October 5, 2026.

Source: egma-ai/jev-code-reviewer on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.