2-repro-issue

Reproduce LinkedIn MCP server issues locally against a real authenticated session.

Updated Aug 29, 2026
One-click install
npx skills add https://github.com/larscolombia/lubot-hunter-mcp-2026 --skill 2-repro-issue-larscolombia
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: 2-repro-issue
Source: https://github.com/larscolombia/lubot-hunter-mcp-2026/tree/main/.agents/skills/2-repro-issue
Command: npx skills add https://github.com/larscolombia/lubot-hunter-mcp-2026 --skill 2-repro-issue-larscolombia

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Confirming whether a reported GitHub issue for the linkedin-mcp-server is a real bug requires manually running the failing MCP tool against live LinkedIn, which is slow and error-prone. This Skill automates that reproduction workflow and produces concrete evidence tied to the exact code path. ## Core Features & Use Cases - Issue-to-Tool Mapping: Parses a GitHub issue (number or URL) to identify the affected MCP tool, triggering arguments, and expected versus actual behavior. - Live Reproduction: Starts the local MCP streamable-http server with uv run against the real authenticated profile at ~/.linkedin-mcp/profile/ and calls the failing tool via JSON-RPC. - Verdict and Baseline Capture: Classifies the result as Reproduced, Reproduced different mode, Not reproduced, or Inconclusive, and saves the response plus request metadata for the follow-up /3-verify-pr-fix skill. - Use Case: A maintainer sees issue #442 claiming get_person_profile returns empty sections. They invoke this Skill with "442" and receive a verdict with the exact tool output, the failing scraper file, and a saved baseline for verifying a fix later. ## Quick Start Ask the AI to reproduce issue 442 from stickerdaniel/linkedin-mcp-server locally and report whether the bug is confirmed on the current branch.

Frequently Asked Questions about 2-repro-issue

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I reproduce a GitHub issue for an MCP server locally?▼

Pass the issue number or URL to this Skill, which reads the issue via the gh CLI, starts the local MCP server with uv run on a free port, and calls the failing tool over JSON-RPC. It then reports a verdict with the actual tool output as evidence.

What tool verifies bug reports for linkedin-mcp-server?▼

This Skill handles bug verification by mapping the issue to the affected MCP tool, running it against the real LinkedIn session at ~/.linkedin-mcp/profile/, and classifying the result as reproduced, different mode, not reproduced, or inconclusive.

Does this Skill use mocked LinkedIn data for testing?▼

No, it explicitly forbids mocks and fixtures. Every reproduction runs against the real authenticated LinkedIn profile stored at ~/.linkedin-mcp/profile/, so results reflect actual live behavior.

Can this Skill fix the bug or check out a PR?▼

No, it only reproduces and reports. It never edits code, commits, or checks out a PR; verifying a candidate fix is delegated to the separate /3-verify-pr-fix skill, which reuses the saved baseline files.

Why does the MCP initialize notification return an invalid parameters error?▼

The notifications/initialized POST often returns a -32602 error with a pydantic validation dump in the server log. This is harmless; the session remains valid and tools/call works on the same Mcp-Session-Id.