Gmcli
CheckedGmcli allows you to interact with the game master interface programmatically, streamlining automation and complex command execution for enhanced gameplay control.
Install on your platform
Showing Claude Code. One command installs this skill into any of the agents below.
- 1
Run this in your project
terminal$ npx skills add badlogic/pi-skills --skill gmcli -a claude-code Uses the open-source
skillsCLI and needs Node.js. Add-gto install it for your user instead of this project.
What we know about this skill
Publisher
badlogic
Taken from the source listing. We haven't verified who controls this account.
Install target
Live repository
Not pinned. Installing fetches whatever the repository holds at the time you run the command.
Automated safety checks
This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.
Declares what it does: passed
SKILL.md parses and declares a name and a description.
SKILL.md exists, its frontmatter parses, and it declares a name and a description.
No undeclared network calls: passed
Makes no network calls.
Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.
No obfuscated payloads: passed
No encoded or obfuscated payloads.
No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.
No credential access: passed
Reads no keys, tokens, keychains or credential files.
Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.
No pipe-to-shell installers: passed
No pipe-to-shell or download-and-run installers.
No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.
Pinned to a commit: passed
Scanned badlogic/pi-skills at 90bb51cae3.
The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.
- Commit
- 90bb51cae3
- Manifest
- gmcli/SKILL.md
- Scanned
- 1 file, 55 lines
About this skill
What it does
Gmcli provides a command-line interface for interacting with Gmail. It allows an AI agent to programmatically perform actions like searching emails, reading threads, sending messages, and managing labels and drafts. The skill requires initial setup involving Google Cloud Console configuration and OAuth credentials.
When to use it
- Automating email searches based on specific criteria (e.g., finding all emails from a particular sender containing certain keywords).
- Retrieving complete email threads for review or analysis.
- Sending automated emails with customized subject lines and bodies.
- Listing available Gmail labels to understand the organization of your inbox.
- Managing drafts, such as listing them or potentially automating draft creation (though this isn't explicitly detailed).
Key capabilities
- Email searching using Gmail query syntax.
- Reading entire email threads by thread ID.
- Sending emails with specified recipients, subject lines, and bodies.
- Listing available labels within a Gmail account.
- Listing drafts stored in Gmail.
- OAuth authentication via JSON credentials file.
Example prompts
- "Search my inbox for emails from '[email protected]' containing the word 'urgent'."
- "Read the email thread with ID '1234567890abcdef.'"
- "Send an email to '[email protected]' with the subject 'Meeting Reminder' and body 'Don't forget our meeting tomorrow!'"
Tips & gotchas
- Initial Setup Required: Gmcli requires a Google Cloud project, enabled Gmail API, OAuth credentials (JSON file), and account setup before it can be used.
- OAuth Authentication: The skill uses OAuth for authentication; the
--manualflag is available if browser-based authentication isn't possible. - Data Storage: Credentials and tokens are stored locally in
~/.gmcli/credentials.jsonand~/.gmcli/accounts.json.