Agent skill

LinkedIn MCP Issue Investigator

by stickerdaniel in stickerdaniel/linkedin-mcp-server

Investigates a reported LinkedIn-MCP issue by matching the reporter's tool call to the exact source file and tests, without applying a fix.

Apache-2.0Auto-check passedDevelopment

Install LinkedIn MCP Issue Investigator

skills CLI
$ npx skills add stickerdaniel/linkedin-mcp-server --skill 2-repro-issue -a claude-code

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

GitHub CLI
$ gh skill install stickerdaniel/linkedin-mcp-server 2-repro-issue --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/stickerdaniel/linkedin-mcp-server.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/2-repro-issue .claude/skills/2-repro-issue && 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
2-repro-issue
GitHub stars
3.8k
Token cost
~2k tokens
SKILL.md length
542 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
Apache-2.0

At a glance

Investigates a reported LinkedIn-MCP issue by matching the reporter's tool call to the exact source file and tests, without applying a fix.

  • Works in 4 steps: Read the issue → Packet and source → Optional live check → …
  • Investigating a reported bug in the LinkedIn MCP server
  • SKILL.md covers 1. Read the issue, 2. Packet and source, 3. Optional live check and 4. Report, plus 1 more section
  • Calls git, uv and curl

What it does

This skill is scoped to investigation only - reproducing and evaluating a reported bug, not fixing it, since a separate skill handles verifying a fix. Given an issue number or URL, it pulls the GitHub thread and extracts the tool called, its arguments, the observed result, the runtime, the LinkedIn variant, and any related issues, keeping observations, source findings, hypotheses and work not yet done clearly separate.

It maps the reported tool to code through a fixed chain: the MCP entrypoint for that surface, a generated ownership table that points to the real implementation file rather than treating a shared extractor file as authoritative, the section definitions file, and the matching owner-level test file. Every finding gets labeled as supported by reporter evidence, confirmed in source, needing more evidence, or not supported by the evidence supplied.

It treats a successful call from the maintainer's own account as no refutation of a failure on the reporter's account, and explicitly withholds authorization for any reporter command with real side effects - sending a message, a connection request, a forced login, or a repeated call - even when the issue grants publishing permission generally.

When your agent uses it

  • Investigating a reported bug in the LinkedIn MCP server
  • Checking whether a GitHub issue's claim holds up against the source
  • Mapping a reported tool failure to the exact implementation file

Example prompts

  • “Investigate issue #214 and tell me if the source supports it.”
  • “Try to reproduce the bug reported in #198 locally.”
  • “Verify the bug in #230 without running any side-effecting calls.”

Requirements

  • gh CLI access to the repository's issues

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Read the issue
  2. Packet and source
  3. Optional live check
  4. Report

What it can do on your machine

Read from SKILL.md and the folder at commit b71682f. 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

    Shell commands in SKILL.md call:

    • git
    • uv
    • curl
    • gh
    • jq

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, uv, curl and gh, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

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

Context cost

LinkedIn MCP Issue Investigator loads about 2k tokens when it runs. Until then it costs about 21 tokens; SKILL.md has 542 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~21
When it runs · the whole SKILL.md, loaded when a task matches
~2k

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 stickerdaniel/linkedin-mcp-server at commit b71682f, republished under its Apache-2.0 licence (© stickerdaniel). 542 words, ~1,961 tokens.

Download SKILL.mdSave it as .claude/skills/2-repro-issue/SKILL.md (or your agent's skills folder).
name
2-repro-issue
description
Reproduce #N, investigate #N, try #N locally, or verify the bug in #N.
argument-hint
<issue-number-or-url>

Investigate a LinkedIn-MCP issue

Evaluate the reporter packet and the matching source. A live LinkedIn call is optional. Do not check out a PR or attempt a fix. That is /3-verify-pr-fix.

1. Read the issue

bash
NUM=$(echo "$ARGUMENTS" | sed -E 's|.*/||; s|#||g' | grep -oE '^[0-9]+' | head -1)
[ -z "$NUM" ] && { echo "Invalid input: '$ARGUMENTS'. Pass an issue number or URL." >&2; exit 1; }
REPO=stickerdaniel/linkedin-mcp-server

gh issue view $NUM --repo $REPO --comments

From the thread extract the tool, arguments, observed result, runtime, LinkedIn variant, and related issues. Distinguish observations, source findings, hypotheses, and work not run.

Map the tool to code:

  1. linkedin_mcp_server/tools/<surface>.py. MCP entrypoint and arg validation
  2. docs/linkedin-architecture.md. Generated ownership table; follow it to linkedin_mcp_server/linkedin/<owner>.py rather than treating linkedin/extractor.py as the implementation
  3. linkedin_mcp_server/linkedin/fields.py. PERSON_SECTIONS / COMPANY_SECTIONS (each entry = one navigation)
  4. The owner-local test, usually tests/linkedin/test_<owner>.py; use tests/test_fields.py, tests/test_identifiers.py, and tests/test_link_metadata.py for those owners, and tests/linkedin/test_facade_*.py only for facade contracts

2. Packet and source

Inspect the relevant source at the current SHA. Do not invent a LinkedIn result or an unimplemented tool call.

This step is complete when the report names the issue, the code SHA, the inspected evidence, the facts established, the unverified runtime claims, and the next decision.

Use one of:

  • supported by reporter evidence
  • confirmed in source
  • needs more evidence (list the specific missing fields)
  • not supported by the supplied evidence

A successful call on the maintainer's different account never refutes a failure on the reporter's account. Target content language is not the authenticated account's UI language. Captures and URL or attribute evidence may establish the needed variation without another live call.

Review reporter commands before execution. Publishing permission does not authorize send_message, a connection request, a forced login, or repeated calls with account side effects. Record sent, recipient_selected, and retry_safe as observed fields, not as replay authorization.

If the next decision needs a live observation, name the exact unresolved question and ask before login, session changes, or LinkedIn writes. If the human declines, keep the packet-and-source verdict.

Show full SKILL.md (246 more words)Show less

3. Optional live check

Only after an explicit yes for this run. Use uv run, never uvx, so the server reflects the workspace. Record the actual tool, arguments, runtime, account variant, code SHA, and timestamp before the call. Keep the reporter's installed-launcher context distinct from a workspace check.

bash
git status --porcelain | head -5
git log -1 --oneline

If the workspace is dirty, ask before continuing. If a login is required, ask; do not run --login as a default.

bash
PORT=8765
while lsof -nP -iTCP:$PORT -sTCP:LISTEN >/dev/null 2>&1; do PORT=$((PORT+1)); done
echo $PORT > /tmp/repro-$NUM.port

uv run -m linkedin_mcp_server --transport streamable-http --port $PORT --log-level INFO > /tmp/repro-$NUM.log 2>&1 &
SERVER_PID=$!
echo $SERVER_PID > /tmp/repro-$NUM.pid

for i in $(seq 1 30); do
  lsof -nP -iTCP:$PORT -sTCP:LISTEN >/dev/null 2>&1 && break
  kill -0 $SERVER_PID 2>/dev/null || { echo "Server died during startup. Tail of /tmp/repro-$NUM.log:" >&2; tail -20 /tmp/repro-$NUM.log >&2; exit 1; }
  sleep 1
done
lsof -nP -iTCP:$PORT -sTCP:LISTEN >/dev/null 2>&1 || { echo "Server never bound port $PORT after 30s" >&2; tail -20 /tmp/repro-$NUM.log >&2; exit 1; }
bash
PORT=$(cat /tmp/repro-$NUM.port)
curl -s -D /tmp/repro-$NUM-headers -X POST http://127.0.0.1:$PORT/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"repro-issue","version":"1.0"}}}' \
  > /tmp/repro-$NUM-init.json

SESSION_ID=$(grep -i 'Mcp-Session-Id' /tmp/repro-$NUM-headers | awk '{print $2}' | tr -d '\r')
[ -z "$SESSION_ID" ] && { echo "MCP initialize returned no Mcp-Session-Id. Tail of /tmp/repro-$NUM.log:" >&2; tail -20 /tmp/repro-$NUM.log >&2; kill $SERVER_PID 2>/dev/null; exit 1; }
grep -q '"error"' /tmp/repro-$NUM-init.json && { echo "Initialize returned a protocol error. Execution limit." >&2; cat /tmp/repro-$NUM-init.json >&2; kill $SERVER_PID 2>/dev/null; exit 1; }

curl -s -X POST http://127.0.0.1:$PORT/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -H "Mcp-Session-Id: $SESSION_ID" \
  -d '{"jsonrpc":"2.0","id":2,"method":"notifications/initialized","params":{}}' \
  > /tmp/repro-$NUM-initialized.json
grep -q '"error"' /tmp/repro-$NUM-initialized.json && { echo "notifications/initialized returned a protocol error. Execution limit." >&2; cat /tmp/repro-$NUM-initialized.json >&2; kill $SERVER_PID 2>/dev/null; exit 1; }

Capture and inspect both response bodies before tools/call. A protocol or validation error is an execution limit. Do not retry around it.

bash
SHA=$(git rev-parse HEAD)
TOOL="<TOOL>"
ARGS_JSON='{<ARGS>}'

jq -n --arg t "$TOOL" --argjson a "$ARGS_JSON" --arg sha "$SHA" \
  '{tool: $t, arguments: $a, sha: $sha}' \
  > /tmp/repro-issue-$NUM-meta.json

curl -s -X POST http://127.0.0.1:$PORT/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -H "Mcp-Session-Id: $SESSION_ID" \
  -d "{\"jsonrpc\":\"2.0\",\"id\":3,\"method\":\"tools/call\",\"params\":{\"name\":\"$TOOL\",\"arguments\":$ARGS_JSON}}" \
  | tee /tmp/repro-issue-$NUM-main.json | head -200

If the issue does not pin a concrete target, do not invent one to complete the live check. Ask, or stop with the packet-and-source verdict.

Preserve /tmp/repro-issue-$NUM-main.json and /tmp/repro-issue-$NUM-meta.json only for a genuine captured run. A run from a non-main commit must identify that SHA in the meta file. Do not claim an on-main baseline because of the filename.

bash
kill $SERVER_PID 2>/dev/null
wait $SERVER_PID 2>/dev/null
rm -f /tmp/repro-$NUM-headers /tmp/repro-$NUM.log /tmp/repro-$NUM.port /tmp/repro-$NUM.pid /tmp/repro-$NUM-init.json /tmp/repro-$NUM-initialized.json

Live verdicts, when a run happened:

  • reproduced in the stated environment
  • reproduced a different mode
  • not reproduced in the maintainer environment (does not refute the reporter)
  • execution limit (startup, protocol, login, rate limit)

4. Report

**#<N>**. <one-line issue summary>
**SHA:** <short-sha>
**Inspected:** <packet fields and source files>
**Facts established:** <list>
**Unverified:** <runtime claims not checked>
**Verdict:** <supported by reporter evidence | confirmed in source | reproduced in the stated environment | needs more evidence | not supported by the supplied evidence>
**Evidence:** <2 to 4 lines>
**Likely code path:** <file:line>. <one-line why>
**Baseline:** <path and SHA, or none>
**Next:** <missing fields | /3-verify-pr-fix N | fix sketch | no live check needed>

Non-negotiables

  • Packet and source first. Live LinkedIn only after yes, and only for a named unresolved question.
  • uv run, not uvx, for a workspace live check. Use the reporter's launcher only to test that installation.
  • One live run per invocation.
  • Do not edit code, commit, or check out a PR.
  • Do not create fake success or failure files to unlock /3-verify-pr-fix.

© stickerdaniel, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/2-repro-issue of stickerdaniel/linkedin-mcp-server.

Open the folder on GitHubat commit b71682f

Compare with similar skills

LinkedIn MCP Issue Investigator 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.

LinkedIn MCP Issue Investigator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
LinkedIn MCP Issue Investigator this skillstickerdaniel/linkedin-mcp-server3.8k—~2kAutomated safety check: PassApache-2.0
React Router Bug Fix Workflowremix-run/react-router57k—~1.3kAutomated safety check: PassMIT
Extension Puppeteer Debuggingmengxi-ream/read-frog10k—~2kAutomated safety check: NotesGPL-3.0
Triagebot Action Bug Triagewithastro/astro63k—~639Automated safety check: PassCustom licence
OpenROAD Issue TriageThe-OpenROAD-Project/OpenROAD3.2k—~842Automated safety check: PassBSD-3-Clause
Playground Website DebuggingWordPress/wordpress-playground2k—~1.9kAutomated safety check: PassGPL-2.0

Similar skills

  • React Router Bug Fix Workflow

    remix-run/react-router

    Fixes a React Router bug reported in a GitHub issue end to end: fetching the issue, validating the reproduction, writing a failing test and implementing the fix on a new branch.

    57k GitHub stars~1.3k tokensUpdated 2 days ago
    DevelopmentAuto-check passed
  • Extension Puppeteer Debugging

    mengxi-ream/read-frog

    Debug the built Read Frog extension in real Chrome. An agent skill from mengxi-ream/read-frog.

    10k GitHub stars~2k tokensUpdated yesterday
    DevelopmentAuto-check: notes
  • Official

    Takes a bug report for the triagebot-action GitHub Action through reproduction, root-cause diagnosis, an intended-behavior check and a fix attempt.

    63k GitHub stars~639 tokensUpdated yesterday
    DevelopmentAuto-check passed
  • OpenROAD Issue Triage

    The-OpenROAD-Project/OpenROAD

    Reproduces an OpenROAD GitHub bug from an attached tarball and shrinks the failing design with whittle.py so maintainers get a minimal test case.

    3.2k GitHub stars~842 tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Playground Website Debugging

    WordPress/wordpress-playground

    Debug the WordPress Playground website by running the dev server from source and interacting with it via Playwright MCP.

    2k GitHub stars~1.9k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Issue Tracer

    ZaxbyHub/opencode-swarm

    Drives a bug report from validation and root-cause tracing through a critic-reviewed plan, an approved minimal fix and a PR-ready closure, never merging without recorded human approval.

    490 GitHub stars~4.4k tokensUpdated yesterday
    DevelopmentAuto-check passed

More from stickerdaniel/linkedin-mcp-server

  • Issue and PR Triage

    stickerdaniel/linkedin-mcp-server

    Turns the open issues and pull requests of the linkedin-mcp-server repository into a read-only priority list for maintainers.

    3.8k GitHub stars~1.9k tokensUpdated yesterday
    Auto-check passed
  • Verify Candidate PR Fix

    stickerdaniel/linkedin-mcp-server

    Reviews a candidate pull request's diff and tests against its linked issue, with an optional live comparison against a previously captured baseline, without editing, merging or pushing.

    3.8k GitHub stars~2k tokensUpdated yesterday
    Auto-check passed
  • BTCA Local Repo Search

    stickerdaniel/linkedin-mcp-server

    Searches git repositories cloned locally under a sandbox folder to answer questions with cited links and complete code snippets.

    3.8k GitHub stars~660 tokensUpdated yesterday
    Auto-check passed
  • PR Review Triage

    stickerdaniel/linkedin-mcp-server

    Collects every review comment on a pull request, checks each against the real code, fixes the valid ones, pushes, and replies on and resolves each thread.

    3.8k GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed
  • GitHub Issue Packet Intake

    stickerdaniel/linkedin-mcp-server

    Turns a bug report or feature idea into a properly sourced GitHub issue or comment, only after searching for a matching issue first.

    3.8k GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed
  • LinkedIn MCP Usage Rules

    stickerdaniel/linkedin-mcp-server

    Rules for using the bundled LinkedIn MCP server for profile, company, job, post, feed and inbox work, with explicit authorization required for messages and connection requests.

    3.8k GitHub stars~651 tokensUpdated yesterday
    Auto-check passed

Questions about LinkedIn MCP Issue Investigator

What does LinkedIn MCP Issue Investigator do?

Investigates a reported LinkedIn-MCP issue by matching the reporter's tool call to the exact source file and tests, without applying a fix. This skill is scoped to investigation only - reproducing and evaluating a reported bug, not fixing it, since a separate skill handles verifying a fix. Given an issue number or URL, it pulls the GitHub thread and extracts the tool called, its arguments, the observed result, the runtime, the LinkedIn variant, and any related issues, keeping observations, source findings, hypotheses and work not yet done clearly separate.

When should I use LinkedIn MCP Issue Investigator?

LinkedIn MCP Issue Investigator fits situations like: investigating a reported bug in the LinkedIn MCP server; checking whether a GitHub issue's claim holds up against the source; mapping a reported tool failure to the exact implementation file.

How do I install LinkedIn MCP Issue Investigator in Claude Code?

Run `npx skills add stickerdaniel/linkedin-mcp-server --skill 2-repro-issue -a claude-code`. Or copy the skill folder (.agents/skills/2-repro-issue in stickerdaniel/linkedin-mcp-server) into .claude/skills/2-repro-issue in your project. Claude Code loads it when a task matches its description.

How do I install LinkedIn MCP Issue Investigator in Codex?

Run `npx skills add stickerdaniel/linkedin-mcp-server --skill 2-repro-issue -a codex`. Or copy the skill folder (.agents/skills/2-repro-issue in stickerdaniel/linkedin-mcp-server) into .agents/skills/2-repro-issue in your project. Codex loads it when a task matches its description.

Can I use LinkedIn MCP Issue Investigator 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 stickerdaniel/linkedin-mcp-server --skill 2-repro-issue -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/2-repro-issue, .gemini/skills/2-repro-issue, .github/skills/2-repro-issue and .opencode/skills/2-repro-issue in your project.

What does LinkedIn MCP Issue Investigator need to run?

Going by SKILL.md and its folder, LinkedIn MCP Issue Investigator needs the command-line tools its instructions call (git, uv, curl, gh and jq). Our summary lists: gh CLI access to the repository's issues.

Does LinkedIn MCP Issue Investigator access the network?

SKILL.md contains no URLs. Its commands use git, uv, curl and gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is LinkedIn MCP Issue Investigator 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 LinkedIn MCP Issue Investigator use?

LinkedIn MCP Issue Investigator is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does LinkedIn MCP Issue Investigator use?

About 2k tokens (SKILL.md is roughly 7.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to LinkedIn MCP Issue Investigator?

Skills that share tags, products or a category with LinkedIn MCP Issue Investigator: React Router Bug Fix Workflow (remix-run/react-router, 57k stars), Extension Puppeteer Debugging (mengxi-ream/read-frog, 10k stars), Triagebot Action Bug Triage (withastro/astro, 63k stars) and OpenROAD Issue Triage (The-OpenROAD-Project/OpenROAD, 3.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains LinkedIn MCP Issue Investigator?

stickerdaniel (a GitHub user) maintains it in stickerdaniel/linkedin-mcp-server, which has 3,782 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 7, 2026.

Source: stickerdaniel/linkedin-mcp-server on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.