Gemini Live API Dev
google-gemini/gemini-skills
A skill your agent uses when building real-time, bidirectional streaming applications with the Gemini Live API, or migrating legacy Live models (2.0/2.5/3.1) to Gemini 3.8 Live.
A skill your agent uses when building WebSocket features with Phoenix Channels — socket auth, join authorization, handlein/push/broadcast, Presence.
$ npx skills add j-morgan6/elixir-phoenix-guide --skill phoenix-channels-essentials -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install j-morgan6/elixir-phoenix-guide phoenix-channels-essentials --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/j-morgan6/elixir-phoenix-guide.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/phoenix-channels-essentials .claude/skills/phoenix-channels-essentials && rm -rf skills-srcUse ~/.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/
Install the "phoenix-channels-essentials" agent skill from https://github.com/j-morgan6/elixir-phoenix-guide/tree/main/skills/phoenix-channels-essentials into .claude/skills/phoenix-channels-essentials/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "phoenix-channels-essentials", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/j-morgan6/elixir-phoenix-guide/tree/main/skills/phoenix-channels-essentialsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add j-morgan6/elixir-phoenix-guide --skill phoenix-channels-essentials -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install j-morgan6/elixir-phoenix-guide phoenix-channels-essentials --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/j-morgan6/elixir-phoenix-guide.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/phoenix-channels-essentials .agents/skills/phoenix-channels-essentials && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "phoenix-channels-essentials" agent skill from https://github.com/j-morgan6/elixir-phoenix-guide/tree/main/skills/phoenix-channels-essentials into .agents/skills/phoenix-channels-essentials/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "phoenix-channels-essentials", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add j-morgan6/elixir-phoenix-guide --skill phoenix-channels-essentials -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install j-morgan6/elixir-phoenix-guide phoenix-channels-essentials --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/j-morgan6/elixir-phoenix-guide.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/phoenix-channels-essentials .cursor/skills/phoenix-channels-essentials && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "phoenix-channels-essentials" agent skill from https://github.com/j-morgan6/elixir-phoenix-guide/tree/main/skills/phoenix-channels-essentials into .cursor/skills/phoenix-channels-essentials/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "phoenix-channels-essentials", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/j-morgan6/elixir-phoenix-guide.git --path skills/phoenix-channels-essentials--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add j-morgan6/elixir-phoenix-guide --skill phoenix-channels-essentials -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install j-morgan6/elixir-phoenix-guide phoenix-channels-essentials --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/j-morgan6/elixir-phoenix-guide.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/phoenix-channels-essentials .gemini/skills/phoenix-channels-essentials && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "phoenix-channels-essentials" agent skill from https://github.com/j-morgan6/elixir-phoenix-guide/tree/main/skills/phoenix-channels-essentials into .gemini/skills/phoenix-channels-essentials/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "phoenix-channels-essentials", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install j-morgan6/elixir-phoenix-guide phoenix-channels-essentialsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add j-morgan6/elixir-phoenix-guide --skill phoenix-channels-essentials -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/j-morgan6/elixir-phoenix-guide.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/phoenix-channels-essentials .github/skills/phoenix-channels-essentials && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "phoenix-channels-essentials" agent skill from https://github.com/j-morgan6/elixir-phoenix-guide/tree/main/skills/phoenix-channels-essentials into .github/skills/phoenix-channels-essentials/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "phoenix-channels-essentials", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add j-morgan6/elixir-phoenix-guide --skill phoenix-channels-essentials -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install j-morgan6/elixir-phoenix-guide phoenix-channels-essentials --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/j-morgan6/elixir-phoenix-guide.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/phoenix-channels-essentials .opencode/skills/phoenix-channels-essentials && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "phoenix-channels-essentials" agent skill from https://github.com/j-morgan6/elixir-phoenix-guide/tree/main/skills/phoenix-channels-essentials into .opencode/skills/phoenix-channels-essentials/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "phoenix-channels-essentials", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
phoenix-channels-essentialsA skill your agent uses when building WebSocket features with Phoenix Channels — socket auth, join authorization, handlein/push/broadcast, Presence.
Phoenix Channels Essentials is an agent skill from j-morgan6/elixir-phoenix-guide. Use when building WebSocket features with Phoenix Channels — socket auth, join authorization, handlein/push/broadcast, Presence.
Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Backend & APIs, covering LLM observability and Realtime and WebSockets. The licence is MIT.
6 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit cdfddac. It shows what the files ask for, not the result of running them.
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.
No scripts in the folder and no shell commands in SKILL.md (its code samples are elixir).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Phoenix Channels Essentials loads about 2.3k tokens when it runs. Until then it costs about 39 tokens; SKILL.md has 357 words of instructions outside code blocks.
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.
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.
The full file from j-morgan6/elixir-phoenix-guide at commit cdfddac, republished under its MIT licence (© j-morgan6). 357 words, ~2,283 tokens.
.claude/skills/phoenix-channels-essentials/SKILL.md (or your agent's skills folder).For non-LiveView real-time features: mobile clients, SPAs, external APIs, inter-service communication.
connect/3 — channels bypass the Plug pipeline; tokens must be verified in the socketjoin/3 — verify the user can access the requested topic before allowing the connectionhandle_in for client-to-server, push for server-to-client, broadcast for server-to-all — never confuse the direction{:reply, :ok, socket} or {:reply, {:error, reason}, socket} from handle_in — don't silently drop messagesChannels bypass the Plug pipeline, so session-based auth doesn't work. Use token-based authentication.
# In a controller or LiveView — generate a token for the current user
defmodule MyAppWeb.UserAuth do
def generate_socket_token(conn) do
Phoenix.Token.sign(conn, "user socket", conn.assigns.current_scope.user.id)
end
end
# In your layout or root template
<script>
window.userToken = "<%= Phoenix.Token.sign(@conn, "user socket", @current_scope.user.id) %>"
</script>defmodule MyAppWeb.UserSocket do
use Phoenix.Socket
channel "room:*", MyAppWeb.RoomChannel
channel "notifications:*", MyAppWeb.NotificationChannel
@impl true
def connect(%{"token" => token}, socket, _connect_info) do
# Phoenix.Token.verify/4 defaults max_age to 86_400 (1 day); this example
# passes max_age: 1_209_600 to extend it to 2 weeks.
case Phoenix.Token.verify(socket, "user socket", token, max_age: 1_209_600) do
{:ok, user_id} ->
{:ok, assign(socket, :user_id, user_id)}
{:error, _reason} ->
:error
end
end
def connect(_params, _socket, _connect_info), do: :error
@impl true
def id(socket), do: "users_socket:#{socket.assigns.user_id}"
endBad:
# No authentication — anyone can connect
def connect(_params, socket, _connect_info) do
{:ok, socket}
endVerify in join/3 that the user is allowed to access the topic.
defmodule MyAppWeb.RoomChannel do
use MyAppWeb, :channel
@impl true
def join("room:" <> room_id, _payload, socket) do
user_id = socket.assigns.user_id
if Rooms.member?(room_id, user_id) do
{:ok, assign(socket, :room_id, room_id)}
else
{:error, %{reason: "unauthorized"}}
end
end
endBad:
# No authorization — any authenticated user can join any room
def join("room:" <> room_id, _payload, socket) do
{:ok, assign(socket, :room_id, room_id)}
endAlways reply so the client knows the result.
@impl true
def handle_in("new_msg", %{"body" => body}, socket) do
user_id = socket.assigns.user_id
room_id = socket.assigns.room_id
case Chat.create_message(room_id, user_id, body) do
{:ok, message} ->
broadcast!(socket, "new_msg", %{
id: message.id,
body: message.body,
user_id: message.user_id,
inserted_at: message.inserted_at
})
{:reply, :ok, socket}
{:error, changeset} ->
{:reply, {:error, %{errors: format_errors(changeset)}}, socket}
end
endBad:
# No reply — client doesn't know if message was received
def handle_in("new_msg", %{"body" => body}, socket) do
broadcast!(socket, "new_msg", %{body: body})
{:noreply, socket}
endSend a message to a specific client, not everyone.
# Push to this specific client only
push(socket, "typing", %{user_id: other_user_id})
# Broadcast to all clients on the topic (including sender)
broadcast!(socket, "new_msg", payload)
# Broadcast to all clients except the sender
broadcast_from!(socket, "user_joined", %{user_id: user_id})For messages from PubSub, timers, or other processes.
@impl true
def handle_info({:new_notification, notification}, socket) do
push(socket, "notification", %{
title: notification.title,
body: notification.body
})
{:noreply, socket}
end# Resource-specific — one room
"room:42"
# User-scoped — all notifications for a user
"notifications:user_123"
# Collection-wide — all public updates
"updates:all"
# Subtopic — specific channel within a room
"room:42:typing"Pattern match in join to extract IDs:
def join("room:" <> room_id, _payload, socket) do
# room_id is a string — parse if needed
room_id = String.to_integer(room_id)
# ...
endUse Phoenix.Presence for tracking who is online. It handles distributed nodes automatically.
# lib/my_app_web/channels/presence.ex
defmodule MyAppWeb.Presence do
use Phoenix.Presence,
otp_app: :my_app,
pubsub_server: MyApp.PubSub
enddefmodule MyAppWeb.RoomChannel do
use MyAppWeb, :channel
alias MyAppWeb.Presence
@impl true
def join("room:" <> room_id, _payload, socket) do
send(self(), :after_join)
{:ok, assign(socket, :room_id, room_id)}
end
@impl true
def handle_info(:after_join, socket) do
# Track this user's presence
{:ok, _} = Presence.track(socket, socket.assigns.user_id, %{
online_at: inspect(System.system_time(:second)),
typing: false
})
# Send current presence state to the joining client
push(socket, "presence_state", Presence.list(socket))
{:noreply, socket}
end
end@impl true
def handle_in("typing", %{"typing" => typing}, socket) do
Presence.update(socket, socket.assigns.user_id, fn meta ->
Map.put(meta, :typing, typing)
end)
{:reply, :ok, socket}
end| Feature | Channels | LiveView | PubSub |
|---|---|---|---|
| Client | Any (mobile, SPA, IoT) | Browser only | Server-side only |
| Protocol | WebSocket + custom | WebSocket + HTML | Erlang messages |
| Rendering | Client renders | Server renders | No rendering |
| Use when | Non-browser clients, custom protocols | Browser UI with real-time | Inter-process communication |
Choose Channels when:
Choose LiveView when:
Choose PubSub when:
defmodule MyAppWeb.RoomChannelTest do
use MyAppWeb.ChannelCase
setup do
user = user_fixture()
room = room_fixture(members: [user])
token = Phoenix.Token.sign(MyAppWeb.Endpoint, "user socket", user.id)
{:ok, socket} = connect(MyAppWeb.UserSocket, %{"token" => token})
{:ok, _, socket} = subscribe_and_join(socket, "room:#{room.id}", %{})
%{socket: socket, user: user, room: room}
end
test "new_msg broadcasts to room", %{socket: socket} do
ref = push(socket, "new_msg", %{"body" => "hello"})
assert_reply ref, :ok
assert_broadcast "new_msg", %{body: "hello"}
end
test "new_msg with invalid data returns error", %{socket: socket} do
ref = push(socket, "new_msg", %{"body" => ""})
assert_reply ref, :error, %{errors: _}
end
test "unauthorized user cannot join room", %{socket: socket, room: room} do
other_user = user_fixture()
token = Phoenix.Token.sign(MyAppWeb.Endpoint, "user socket", other_user.id)
{:ok, socket} = connect(MyAppWeb.UserSocket, %{"token" => token})
assert {:error, %{reason: "unauthorized"}} =
subscribe_and_join(socket, "room:#{room.id}", %{})
end
test "presence is tracked on join", %{socket: socket, user: user} do
user_id = to_string(user.id)
assert %{^user_id => %{metas: [%{online_at: _}]}} =
MyAppWeb.Presence.list(socket)
end
endSee phoenix-pubsub-patterns skill for server-side PubSub patterns.
See phoenix-liveview-essentials skill for LiveView real-time patterns.
See testing-essentials skill for comprehensive testing patterns.
© j-morgan6, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in skills/phoenix-channels-essentials of j-morgan6/elixir-phoenix-guide.
Open the folder on GitHubat commit cdfddac
Phoenix Channels Essentials 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Phoenix Channels Essentials this skillj-morgan6/elixir-phoenix-guide | 167 | — | ~2.3k | Automated safety check: Pass | MIT | |
| Gemini Live API Devgoogle-gemini/gemini-skills | 4.3k | — | ~4.6k | Automated safety check: Pass | Apache-2.0 | |
| Databuddydatabuddy-analytics/Databuddy | 1.2k | — | ~2.1k | Automated safety check: Pass | AGPL-3.0 | |
| Phoenix GraphqlArize-ai/phoenix | 12k | — | ~2.2k | Automated safety check: Pass | Custom licence | |
| Building AI Agent On CloudflareCommandCodeAI/agent-skills | 133 | — | ~2.3k | Automated safety check: Pass | MIT | |
| Iflytek Image Understandingiflytek/iFly-Skills | 209 | — | ~949 | Automated safety check: Pass | Apache-2.0 |
google-gemini/gemini-skills
A skill your agent uses when building real-time, bidirectional streaming applications with the Gemini Live API, or migrating legacy Live models (2.0/2.5/3.1) to Gemini 3.8 Live.
databuddy-analytics/Databuddy
Integrate Databuddy analytics using the SDK, REST API, or MCP.
Arize-ai/phoenix
Write efficient GraphQL queries against the Phoenix API. An agent skill from Arize-ai/phoenix.
CommandCodeAI/agent-skills
Builds AI agents on Cloudflare using the Agents SDK with state management, real-time WebSockets, scheduled tasks, tool integration, and chat capabilities.
iflytek/iFly-Skills
A skill your agent uses when user asks to analyze an image, describe image contents, or answer questions about a picture.
microsoft/skills
Azure AI Voice Live SDK for JavaScript/TypeScript. An agent skill from microsoft/skills.
j-morgan6/elixir-phoenix-guide
A skill your agent uses when refactoring for duplication, complexity, or dead code — includes the plugin's on-demand analysis scripts.
j-morgan6/elixir-phoenix-guide
A skill your agent uses when preparing releases or deployment config — runtime.exs vs compile-time config, release migrations, PHXHOST/PHXSERVER, assets, health checks.
j-morgan6/elixir-phoenix-guide
A skill your agent uses when a resource needs multiple changesets (registration vs update), conditional validation, field transforms, or uniqueness validation — changeset composition.
j-morgan6/elixir-phoenix-guide
A skill your agent uses when defining schemas, writing queries, or creating migrations — schema design, Repo usage, indexes, query composition.
j-morgan6/elixir-phoenix-guide
A skill your agent uses when a form or operation manages parent and child records together — castassoc/castembed, onreplace, Ecto.Multi across tables, FK cascade design.
j-morgan6/elixir-phoenix-guide
A skill your agent uses when writing or refactoring core Elixir — pattern matching, case/cond/with, pipes, {:ok, }/{:error, } contracts.
Categories
A skill your agent uses when building WebSocket features with Phoenix Channels — socket auth, join authorization, handlein/push/broadcast, Presence. Phoenix Channels Essentials is an agent skill from j-morgan6/elixir-phoenix-guide. Use when building WebSocket features with Phoenix Channels — socket auth, join authorization, handlein/push/broadcast, Presence.
Phoenix Channels Essentials fits situations like: building WebSocket features with Phoenix Channels — socket auth; join authorization; handlein/push/broadcast.
Run `npx skills add j-morgan6/elixir-phoenix-guide --skill phoenix-channels-essentials -a claude-code`. Or copy the skill folder (skills/phoenix-channels-essentials in j-morgan6/elixir-phoenix-guide) into .claude/skills/phoenix-channels-essentials in your project. Claude Code loads it when a task matches its description.
Run `npx skills add j-morgan6/elixir-phoenix-guide --skill phoenix-channels-essentials -a codex`. Or copy the skill folder (skills/phoenix-channels-essentials in j-morgan6/elixir-phoenix-guide) into .agents/skills/phoenix-channels-essentials in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add j-morgan6/elixir-phoenix-guide --skill phoenix-channels-essentials -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/phoenix-channels-essentials, .gemini/skills/phoenix-channels-essentials, .github/skills/phoenix-channels-essentials and .opencode/skills/phoenix-channels-essentials in your project.
SKILL.md names no scripts, command-line tools or credentials: Phoenix Channels Essentials is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
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.
Phoenix Channels Essentials is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.3k tokens (SKILL.md is roughly 9.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Phoenix Channels Essentials: Gemini Live API Dev (google-gemini/gemini-skills, 4.3k stars), Databuddy (databuddy-analytics/Databuddy, 1.2k stars), Phoenix Graphql (Arize-ai/phoenix, 12k stars) and Building AI Agent On Cloudflare (CommandCodeAI/agent-skills, 133 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
j-morgan6 (a GitHub user) maintains it in j-morgan6/elixir-phoenix-guide, which has 167 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on July 6, 2026.
Source: j-morgan6/elixir-phoenix-guide on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.