Agent Plugins Marketplace
← All plugins

tabib

v0.3.0

Nexika tabib: finds out why CI failed, with evidence. Reads the failed run (GitHub Actions or GitLab CI), pulls out the failing tests and errors, sorts the failure (code, one Python or OS only, flaky, infrastructure, dependencies), compares with the last green run, reproduces the failing tests in a throwaway git worktree, and reports the cause with its evidence. Diagnoses only: it never edits code, pushes or re-runs CI. English and Arabic.

Claude Code1 Skill

By Loai ElattarLicense: MIT0 GitHub starsUpdated last week

Directory evidence

Runtimes
Claude Code
Parsed components
1 skill or MCP entry
Source updated
Oct 10, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install tabib for Claude Code

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install tabib@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/nexika/nexika

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/tabib/.

Plugin files

plugins/tabib/
├── .claude-plugin/plugin.json
└── skills/diagnose/SKILL.md

Included Skills1

diagnoseskills/diagnose/SKILL.md

Find out why CI failed, with evidence - the failing tests and errors from the log, the kind of failure (code, one Python or OS only, flaky, infrastructure, dependencies), the commits since the last green run, the failing tests run again in a throwaway worktree, and the cause backed by the code. Diagnoses only, never fixes or re-runs. Use when the user says "why did CI fail", "diagnose", "the pipeline is red", "tabib", "ليش فشل CI", "لماذا فشل الفحص", or presses "Why?" in mizan's band.

Plugin manifests1

plugins/tabib/.claude-plugin/plugin.json
{
  "name": "tabib",
  "description": "Nexika tabib: finds out why CI failed, with evidence. Reads the failed run (GitHub Actions or GitLab CI), pulls out the failing tests and errors, sorts the failure (code, one Python or OS only, flaky, infrastructure, dependencies), compares with the last green run, reproduces the failing tests in a throwaway git worktree, and reports the cause with its evidence. Diagnoses only: it never edits code, pushes or re-runs CI. English and Arabic.",
  "version": "0.3.0",
  "author": {
    "name": "Loai Elattar"
  },
  "license": "MIT",
  "keywords": [
    "nexika",
    "ci",
    "debugging",
    "github-actions",
    "gitlab-ci",
    "flaky-tests",
    "arabic"
  ]
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[tabib on Agent Plugins Marketplace](https://pluginsmp.com/plugins/tabib)