skills.rest
kaistenberg
kaistenbergCOMMUNITY
Explore all skills by this author →
Website𝕏@kaistenbergGitHub

2-repro-issue

Reproduce LinkedIn-MCP GitHub issues locally against a real authenticated LinkedIn session.

Updated Aug 6, 2026
Search Tags:#debugging#linkedin#triage#mcp server#bug reproduction#streamable-http#github issue
One-click install
npx skills add https://github.com/kaistenberg/MCP-Linkedin --skill 2-repro-issue-kaistenberg
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: 2-repro-issue
Source: https://github.com/kaistenberg/MCP-Linkedin/tree/main/.agents/skills/2-repro-issue
Command: npx skills add https://github.com/kaistenberg/MCP-Linkedin --skill 2-repro-issue-kaistenberg

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Confirming whether a reported bug in the linkedin-mcp-server project actually exists requires manually setting up the server, authenticating, and replaying the failing tool call. This Skill automates that investigation, producing concrete evidence that confirms or refutes an issue on the current branch. ## Core Features & Use Cases - Issue Parsing and Code Mapping: Reads a GitHub issue via gh, extracts the affected MCP tool, exact arguments, and expected behavior, then maps them to the relevant scraper code path. - Live MCP Server Reproduction: Starts the streamable-http MCP server from the current workspace with uv run, initializes an MCP session over curl, and replays the exact failing tool call against the real LinkedIn profile at ~/.linkedin-mcp/profile/. - Verdict and Baseline Capture: Classifies the result as Reproduced, Reproduced different mode, Not reproduced, or Inconclusive, and saves the response plus request metadata to /tmp for the follow-up /3-verify-pr-fix workflow. - Use Case: A maintainer sees issue #442 claiming get_person_profile returns empty sections. Run this Skill with the issue number to replay the call against real LinkedIn and get a verdict with evidence and the likely code path. ## Quick Start Ask the assistant 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. It reads the issue with the gh CLI, starts the MCP server from your workspace with uv run on a free port, initializes a streamable-http session, and replays the exact failing tool call to capture the failure evidence.

How to test LinkedIn MCP tools against a real account?▼

The Skill uses the authenticated browser profile stored at ~/.linkedin-mcp/profile/ and never mocks data. If the profile is missing or stale, it runs uv run -m linkedin_mcp_server --login once before replaying the tool call.

Does this Skill fix the bug or check out the PR?▼

No. It only reproduces and reports the issue with a verdict and evidence. Verifying a candidate fix is handled separately by the /3-verify-pr-fix skill, which reuses the saved baseline files in /tmp.

Why does the MCP initialized 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, so it should not be retried.

What happens if my git workspace has uncommitted changes?▼

The Skill checks git status before running and asks for confirmation if the workspace is dirty. Local changes can hide or fake the bug, so reproduction requires a clean state to be trustworthy.

Related Skills

Explore More Software Engineering Skills→
QuixiAIQuixiAI
609

github-issues

Search, read, create, and comment on GitHub issues via the GitHub MCP server.

Official
Intermediate
tr4m0ryptr4m0ryp

3-verify-pr-fix

Compare tool call outputs before and after a pull request fix.

Community
Advanced
aist-ai-sastaist-ai-sast

mcp-regression-fix

Diagnose MCP regression failures and implement durable fixes across test suites.

Official
Advanced
SethyPagnaSethyPagna

rest-graphql-debug

Diagnose REST and GraphQL API failures by isolating connectivity, TLS, authentication, and parsing errors.

Community
Advanced