Check Collaborators logo

Check Collaborators

Community
yunshenwuchuxun
check-collaborators

Verify that Gemini CLI and Claude Code CLI are installed, authenticated, and API-reachable before starting collaboration workflows.

Overview

Publisheryunshenwuchuxun
Repositorylatex-paper-skills
Skill namecheck-collaborators
Stars
270
Forks
23
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by yunshenwuchuxun on GitHub. Read the source before you install it.

Installation

Install the Check Collaborators AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/yunshenwuchuxun/latex-paper-skills/tree/main/.codex/skills/check-collaborators
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/yunshenwuchuxun/latex-paper-skills.git /tmp/latex-paper-skills
mkdir -p .claude/skills
cp -r /tmp/latex-paper-skills/.codex/skills/check-collaborators .claude/skills/check-collaborators
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Check Collaborators in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Check Collaborators on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Check Collaborators is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Collaborator CLI Health Check

When to use

  • Before starting any collaboration workflow that depends on Gemini or Claude Code.
  • When diagnosing CLI connectivity or authentication issues.
  • After installing or reconfiguring either CLI.

When not to use

  • Both CLIs are already confirmed working in the current session.
  • The task does not involve cross-agent collaboration.

Inputs

  • Current OS environment (auto-detected).

Outputs

  • Summary table: Collaborator x CLI / Version / Auth / API / Status.
  • Actionable remediation advice for any failed step.

Workflow

Run the Gemini and Claude detection chains in parallel where possible. For each collaborator, execute steps sequentially and short-circuit on the first failure — skip subsequent steps and mark the failure reason.

Step 0: Detect OS

Determine the platform to choose the correct binary-lookup command:

  • Windows (win32): use where
  • Unix/macOS: use which

Detect via uname -s 2>/dev/null (returns nothing or errors on Windows) or check $OSTYPE.


Gemini Detection Chain

1. CLI Exists
bash
# Unix
which gemini
# Windows
where gemini

Pass: command exits 0 and outputs a path. Fail: command not found — suggest: npm install -g @anthropic-ai/gemini-cli or see https://github.com/google-gemini/gemini-cli

2. Version
bash
timeout 15 bash -c 'GEMINI_CLI_NO_RELAUNCH=true gemini --version'

On Windows (no timeout command), run directly:

bash
GEMINI_CLI_NO_RELAUNCH=true gemini --version

GEMINI_CLI_NO_RELAUNCH=true is required to prevent the CLI from hanging.

Pass: output contains a version string (e.g., 0.32.1). Fail: timeout or no version output.

3. Auth

Check for any of the following (any one is sufficient):

  1. Environment variable GEMINI_API_KEY is set and non-empty.
  2. Environment variable GOOGLE_API_KEY is set and non-empty.
  3. File ~/.gemini/oauth_creds.json exists.
bash
[[ -n "$GEMINI_API_KEY" ]] || [[ -n "$GOOGLE_API_KEY" ]]
test -f "$HOME/.gemini/oauth_creds.json"

Pass: any one condition is true. Fail: none found — suggest: export GEMINI_API_KEY=<key> or run gemini interactively to complete OAuth.

4. API Connectivity
bash
timeout 30 gemini --prompt "Reply with exactly: HEALTH_OK"

Pass: stdout contains HEALTH_OK. Fail: timeout or no HEALTH_OK in output — suggest checking network, API key validity, or quota.

Note: Gemini CLI may emit warnings (e.g., skill conflict notices) in its output. These are benign and do not affect the health check. The pass/fail criterion is solely whether HEALTH_OK appears in stdout.


Claude Code Detection Chain

1. CLI Exists
bash
# Unix
which claude
# Windows
where claude

Pass: command exits 0 and outputs a path. Fail: command not found — suggest: npm install -g @anthropic-ai/claude-code or see https://docs.anthropic.com/en/docs/claude-code

2. Version
bash
timeout 15 claude --version

Pass: output contains a version string (e.g., 2.1.74). Fail: timeout or no version output.

3. Auth
bash
claude auth status

Pass: output contains Logged in or JSON field loggedIn: true. Fail: not logged in — suggest: run claude interactively and use /login.

4. API Connectivity
bash
timeout 30 claude --print "Reply with exactly: HEALTH_OK" --output-format text --no-session-persistence --max-budget-usd 0.50

Pass: stdout contains HEALTH_OK. Fail: timeout or no HEALTH_OK — suggest checking API key, network, or account quota.

Note: --max-budget-usd must be at least 0.50. Lower values (e.g., 0.01, 0.05) cause immediate Exceeded budget errors because model inference has a minimum cost floor.


Output Format

Present a summary table after all checks:

| Collaborator | CLI | Version | Auth | API | Status    |
|--------------|-----|---------|------|-----|-----------|
| Gemini       | ✓/✗ | x.y.z   | ✓/✗  | ✓/✗ | Available / Failed |
| Claude Code  | ✓/✗ | x.y.z   | ✓/✗  | ✓/✗ | Available / Failed |
  • Use ✓ for passed steps, ✗ for failed steps, — for skipped steps (due to short-circuit).
  • Status is Available only if all 4 steps pass; otherwise Failed.
  • Version column shows the detected version string, or — if not reached.

For any failed step, append actionable remediation advice below the table:

### Issues Found

**Gemini — Auth failed**
No API key or OAuth credentials detected.
→ Set `GEMINI_API_KEY` environment variable, or run `gemini` to complete OAuth login.

**Claude Code — CLI not found**
Claude Code CLI is not installed.
→ Install: `npm install -g @anthropic-ai/claude-code`
→ Docs: https://docs.anthropic.com/en/docs/claude-code

If both collaborators pass all checks:

Both collaborators are available and ready for collaboration workflows.

Verification

  • Run this skill and confirm the summary table appears with correct status for each collaborator.

Safety and guardrails

  • Read-only checks only; no configuration files are modified.
  • API connectivity tests consume minimal tokens (~$0.01 per check).
  • Steps 2-4 spawn external CLI processes; run them outside sandbox (escalated permissions) to avoid hangs or EPERM errors.
  • On Windows, timeout may not be available; run commands directly and watch for hangs.
  • Gemini --version must use GEMINI_CLI_NO_RELAUNCH=true to prevent the CLI from relaunching itself.

Frequently asked questions

What does the Check Collaborators AI skill do?

Verify that Gemini CLI and Claude Code CLI are installed, authenticated, and API-reachable before starting collaboration workflows.

Why use Check Collaborators on TypingMind?

Because you install it once and use it with any model. Check Collaborators is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Check Collaborators in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/yunshenwuchuxun/latex-paper-skills/tree/main/.codex/skills/check-collaborators. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Check Collaborators?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Check Collaborators?

As many as you like. As long as a model supports skills, you can use Check Collaborators with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Check Collaborators AI skill free?

Yes. It is published on GitHub by yunshenwuchuxun under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇