agentleFS
WadeWarrenWadeWarren/gws-claude-plugin/skills/gws-chat/SKILL.md

gws-chat

Skill38 starsChanged 8 months agoApache-2.0View on GitHub

Google Chat: Manage Chat spaces and messages.

We split this skill into the rules it gives an agent

2 rules. 1 is common, 0 are distinctive, and 1 is very specific to this project.

  • 1

    Common

    Most of the 3 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Common:

    Before calling any API method, inspect it:

    line 62
  2. Very specific:

    Use gws schema output to build your --params and --json flags.

    line 72

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

chat (v1)

PREREQUISITE: Read ../gws-shared/SKILL.md for auth, global flags, and security rules. If missing, run gws generate-skills to create it.

gws chat <resource> <method> [flags]

Helper Commands

CommandDescription
+sendSend a message to a space

API Resources

customEmojis

media

  • download — Downloads media. Download is supported on the URI /v1/media/{+name}?alt=media.
  • upload — Uploads an attachment. For an example, see Upload media as a file attachment.

spaces

  • completeImport — Completes the import process for the specified space and makes it visible to users.
  • create — Creates a space. Can be used to create a named space, or a group chat in Import mode. For an example, see Create a space.
  • delete — Deletes a named space. Always performs a cascading delete, which means that the space's child resources—like messages posted in the space and memberships in the space—are also deleted. For an example, see Delete a space.
  • findDirectMessage — Returns the existing direct message with the specified user. If no direct message space is found, returns a 404 NOT_FOUND error. For an example, see Find a direct message. With app authentication, returns the direct message space between the specified user and the calling Chat app.
  • get — Returns details about a space. For an example, see Get details about a space.
  • list — Lists spaces the caller is a member of. Group chats and DMs aren't listed until the first message is sent. For an example, see List spaces.
  • patch — Updates a space. For an example, see Update a space. If you're updating the displayName field and receive the error message ALREADY_EXISTS, try a different display name.. An existing space within the Google Workspace organization might already use this display name.
  • search — Returns a list of spaces in a Google Workspace organization based on an administrator's search. In the request, set use_admin_access to true. For an example, see Search for and manage spaces.
  • setup — Creates a space and adds specified users to it. The calling user is automatically added to the space, and shouldn't be specified as a membership in the request. For an example, see Set up a space with initial members. To specify the human members to add, add memberships with the appropriate membership.member.name. To add a human user, use users/{user}, where {user} can be the email address for the user.
  • members — Operations on the 'members' resource
  • messages — Operations on the 'messages' resource
  • spaceEvents — Operations on the 'spaceEvents' resource

users

  • spaces — Operations on the 'spaces' resource

Discovering Commands

Before calling any API method, inspect it:

# Browse resources and methods
gws chat --help

# Inspect a method's required params, types, and defaults
gws schema chat.<resource>.<method>

Use gws schema output to build your --params and --json flags.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.