Desktop Release Sync Landing
Eynzof/Hermes-CN-Desktop
Use only for stable/public Hermes Agent CN Desktop releases that should be visible to all users.
Audits, launches, checks and stops the Multi-AI Chat Tauri desktop app from a local source checkout, only when you explicitly ask.
Install Multi-AI Chat Launcher
$ npx skills add teddashh/multi-ai-chat-desktop --skill launch-multi-ai-chat -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install teddashh/multi-ai-chat-desktop launch-multi-ai-chat --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/teddashh/multi-ai-chat-desktop.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/launch-multi-ai-chat .claude/skills/launch-multi-ai-chat && 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 "launch-multi-ai-chat" agent skill from https://github.com/teddashh/multi-ai-chat-desktop/tree/main/.agents/skills/launch-multi-ai-chat into .claude/skills/launch-multi-ai-chat/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "launch-multi-ai-chat", 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/teddashh/multi-ai-chat-desktop/tree/main/.agents/skills/launch-multi-ai-chatType 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 teddashh/multi-ai-chat-desktop --skill launch-multi-ai-chat -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install teddashh/multi-ai-chat-desktop launch-multi-ai-chat --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/teddashh/multi-ai-chat-desktop.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/launch-multi-ai-chat .agents/skills/launch-multi-ai-chat && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "launch-multi-ai-chat" agent skill from https://github.com/teddashh/multi-ai-chat-desktop/tree/main/.agents/skills/launch-multi-ai-chat into .agents/skills/launch-multi-ai-chat/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "launch-multi-ai-chat", 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 teddashh/multi-ai-chat-desktop --skill launch-multi-ai-chat -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install teddashh/multi-ai-chat-desktop launch-multi-ai-chat --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/teddashh/multi-ai-chat-desktop.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/launch-multi-ai-chat .cursor/skills/launch-multi-ai-chat && 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 "launch-multi-ai-chat" agent skill from https://github.com/teddashh/multi-ai-chat-desktop/tree/main/.agents/skills/launch-multi-ai-chat into .cursor/skills/launch-multi-ai-chat/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "launch-multi-ai-chat", 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/teddashh/multi-ai-chat-desktop.git --path .agents/skills/launch-multi-ai-chat--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 teddashh/multi-ai-chat-desktop --skill launch-multi-ai-chat -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install teddashh/multi-ai-chat-desktop launch-multi-ai-chat --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/teddashh/multi-ai-chat-desktop.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/launch-multi-ai-chat .gemini/skills/launch-multi-ai-chat && 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 "launch-multi-ai-chat" agent skill from https://github.com/teddashh/multi-ai-chat-desktop/tree/main/.agents/skills/launch-multi-ai-chat into .gemini/skills/launch-multi-ai-chat/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "launch-multi-ai-chat", 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 teddashh/multi-ai-chat-desktop launch-multi-ai-chatInstalls 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 teddashh/multi-ai-chat-desktop --skill launch-multi-ai-chat -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/teddashh/multi-ai-chat-desktop.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/launch-multi-ai-chat .github/skills/launch-multi-ai-chat && 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 "launch-multi-ai-chat" agent skill from https://github.com/teddashh/multi-ai-chat-desktop/tree/main/.agents/skills/launch-multi-ai-chat into .github/skills/launch-multi-ai-chat/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "launch-multi-ai-chat", 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 teddashh/multi-ai-chat-desktop --skill launch-multi-ai-chat -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install teddashh/multi-ai-chat-desktop launch-multi-ai-chat --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/teddashh/multi-ai-chat-desktop.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/launch-multi-ai-chat .opencode/skills/launch-multi-ai-chat && 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 "launch-multi-ai-chat" agent skill from https://github.com/teddashh/multi-ai-chat-desktop/tree/main/.agents/skills/launch-multi-ai-chat into .opencode/skills/launch-multi-ai-chat/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "launch-multi-ai-chat", 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.
Facts
- Skill name
launch-multi-ai-chat- GitHub stars
- 151
- Token cost
- ~536 tokens
- SKILL.md length
- 260 words
- Files
- 2
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
Audits, launches, checks and stops the Multi-AI Chat Tauri desktop app from a local source checkout, only when you explicitly ask.
- Works in 7 steps: Confirm the shell is on the user's local… → Run node scripts/agent/audit.mjs --phase… → Run node scripts/agent/doctor.mjs --json. → …
- Starting the Multi-AI Chat desktop app from a local source checkout
- Calls node and pnpm
- Checking whether the running app has reached the ready state
What it does
This skill runs the source-development lane of the Multi-AI Chat desktop app, defined by agent-release.json, from a checked-out repository. It is not an installer, release build, container or remote GUI, and launching executes code from the repository plus its locked JavaScript and Rust build dependencies. It applies only when you explicitly ask to run the repo on your local graphical computer.
The sequence is: confirm the shell is on that computer, run the before audit and the doctor check, stop and report if prerequisites are missing, then launch with a 600000 ms timeout, run the after audit even if launch fails, and claim readiness only when the state is ready, not merely accepted or building. Status, with the last 80 log lines, and stop commands are available, and an unverified process is never stopped.
Strict limits apply. It never installs or removes toolchains, global packages, PATH entries, shell profiles or security settings, never runs pnpm tauri build or creates installers, never uploads logs, and never reads provider credentials, cookies, storage or profiles. Host changes need separate explicit approval outside the skill.
When your agent uses it
- Starting the Multi-AI Chat desktop app from a local source checkout
- Checking whether the running app has reached the ready state
- Stopping the app safely after a test session
Example prompts
- “Launch the Multi-AI Chat app from this checkout on my local machine.”
- “Check the status of the Multi-AI Chat app and show the recent log lines.”
- “Stop the running Multi-AI Chat app, but only if the process is verified.”
Requirements
- A local graphical computer, not a remote or headless shell
- A checkout of the multi-ai-chat-desktop repository with Node, pnpm and Rust toolchains installed
Workflow steps
7 steps, taken from the first numbered list in SKILL.md.
- Confirm the shell is on the user's local graphical computer. Do not claim a remote or headless shell can display the window.
- Run node scripts/agent/audit.mjs --phase before --write --json.
- Run node scripts/agent/doctor.mjs --json.
- If prerequisites are missing, report the exact checks and stop. This skill never installs or removes host toolchains, global packages…
- Run node scripts/agent/launch.mjs --wait --timeout-ms 600000 --json.
- Run node scripts/agent/audit.mjs --phase after --write --json, including after a launch failure or timeout.
- Claim readiness only when launch or node scripts/agent/status.mjs --json --lines 80 reports state: "ready". “accepted” or “building” does…
What it can do on your machine
Read from SKILL.md and the folder at commit 74d16ba. 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:
nodepnpm
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use pnpm, 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
Multi-AI Chat Launcher loads about 536 tokens when it runs. Until then it costs about 53 tokens; SKILL.md has 260 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.
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 teddashh/multi-ai-chat-desktop at commit 74d16ba, republished under its MIT licence (© teddashh). 260 words, ~536 tokens.
Download SKILL.mdSave it as
.claude/skills/launch-multi-ai-chat/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- launch-multi-ai-chat
- description
- Audit, launch, verify, inspect, or stop the local Multi-AI Chat Tauri source app. Use only when the user explicitly asks to run this checked-out repository on their local graphical computer.
Operate the source-development lane defined by agent-release.json. It is not an installer, release build, container, or remote GUI.
Source launch executes code from the checked-out repository, locked JavaScript dependencies, and Rust build dependencies. Keep all lifecycle records local and never read provider credentials, cookies, storage, or profiles.
For an explicit launch request:
- Confirm the shell is on the user's local graphical computer. Do not claim a remote or headless shell can display the window.
- Run
node scripts/agent/audit.mjs --phase before --write --json. - Run
node scripts/agent/doctor.mjs --json. - If prerequisites are missing, report the exact checks and stop. This skill never installs or removes host toolchains, global packages, PATH entries, shell profiles, or security settings. A separate host-change request requires separate explicit approval outside this skill, with exact commands and side effects disclosed first.
- Run
node scripts/agent/launch.mjs --wait --timeout-ms 600000 --json. - Run
node scripts/agent/audit.mjs --phase after --write --json, including after a launch failure or timeout. - Claim readiness only when launch or
node scripts/agent/status.mjs --json --lines 80reportsstate: "ready". “accepted” or “building” does not mean the window is ready.
For status, run node scripts/agent/status.mjs --json --lines 80. For an explicit stop request, run node scripts/agent/stop.mjs --json. Never stop an unverified process. Use --clear-invalid-state only after the user explicitly asks to recover inspected corrupt state; it removes no process.
Never run pnpm tauri build, generate installers, download release assets for this lane, upload logs or audits, weaken OS security, delete provider profiles, or automatically roll back/uninstall host software. Shared pnpm/Cargo caches and normal app data are user-managed.
© teddashh, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in .agents/skills/launch-multi-ai-chat of teddashh/multi-ai-chat-desktop.
- SKILL.md
- agents/openai.yaml
Open the folder on GitHubat commit 74d16ba
Compare with similar skills
Multi-AI Chat Launcher 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 |
|---|---|---|---|---|---|---|
| Multi-AI Chat Launcher this skillteddashh/multi-ai-chat-desktop | 151 | — | ~536 | Automated safety check: Pass | MIT | |
| Desktop Release Sync LandingEynzof/Hermes-CN-Desktop | 1.7k | — | ~1.3k | Automated safety check: Pass | Custom licence | |
| Veloxdb Scalable Performanceveloxbase/veloxdb | 646 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Pnpm Engineteambit/bit | 18k | — | ~1.9k | Automated safety check: Pass | Custom licence | |
| Testing Changespnpm/pnpm | 37k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Happy Monorepo Dev Guideslopus/happy | 24k | — | ~1.8k | Automated safety check: Pass | MIT |
Similar skills
Veloxdb Scalable Performance
veloxbase/veloxdb
Guides scalability and performance work for VeloxDB's Tauri + Rust PostgreSQL backend and React + TanStack frontend.
Pnpm Engine
teambit/bit
Work on the pnpm Rust engine (@pnpm/napi, the pacquet crates) that bit install runs through.
Testing Changes
pnpm/pnpm
Run the tests that cover a change in the pnpm repository, in the Rust workspace (pnpm/, pnpr/) or the TypeScript CLI (pnpm11/), and recognize the cases where a scoped run passes without testing…
Happy Monorepo Dev Guide
slopus/happy
Local development guide for the Happy pnpm monorepo: install, build, test and run the CLI, server, Expo app and Tauri desktop packages.
Cut Release
delexw/claude-code-trace
Cuts a new versioned release of claude-code-trace end-to-end without asking any questions.
Related
Categories
Questions about Multi-AI Chat Launcher
What does Multi-AI Chat Launcher do?
Audits, launches, checks and stops the Multi-AI Chat Tauri desktop app from a local source checkout, only when you explicitly ask. json, from a checked-out repository. It is not an installer, release build, container or remote GUI, and launching executes code from the repository plus its locked JavaScript and Rust build dependencies.
When should I use Multi-AI Chat Launcher?
Multi-AI Chat Launcher fits situations like: starting the Multi-AI Chat desktop app from a local source checkout; checking whether the running app has reached the ready state; stopping the app safely after a test session.
How do I install Multi-AI Chat Launcher in Claude Code?
Run `npx skills add teddashh/multi-ai-chat-desktop --skill launch-multi-ai-chat -a claude-code`. Or copy the skill folder (.agents/skills/launch-multi-ai-chat in teddashh/multi-ai-chat-desktop) into .claude/skills/launch-multi-ai-chat in your project. Claude Code loads it when a task matches its description.
How do I install Multi-AI Chat Launcher in Codex?
Run `npx skills add teddashh/multi-ai-chat-desktop --skill launch-multi-ai-chat -a codex`. Or copy the skill folder (.agents/skills/launch-multi-ai-chat in teddashh/multi-ai-chat-desktop) into .agents/skills/launch-multi-ai-chat in your project. Codex loads it when a task matches its description.
Can I use Multi-AI Chat Launcher 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 teddashh/multi-ai-chat-desktop --skill launch-multi-ai-chat -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/launch-multi-ai-chat, .gemini/skills/launch-multi-ai-chat, .github/skills/launch-multi-ai-chat and .opencode/skills/launch-multi-ai-chat in your project.
What does Multi-AI Chat Launcher need to run?
Going by SKILL.md and its folder, Multi-AI Chat Launcher needs the command-line tools its instructions call (node and pnpm). Our summary lists: A local graphical computer, not a remote or headless shell; A checkout of the multi-ai-chat-desktop repository with Node, pnpm and Rust toolchains installed.
Does Multi-AI Chat Launcher access the network?
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.
Is Multi-AI Chat Launcher 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 Multi-AI Chat Launcher use?
Multi-AI Chat Launcher is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Multi-AI Chat Launcher use?
About 536 tokens (SKILL.md is roughly 2.1k 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 Multi-AI Chat Launcher?
Skills that share tags, products or a category with Multi-AI Chat Launcher: Desktop Release Sync Landing (Eynzof/Hermes-CN-Desktop, 1.7k stars), Veloxdb Scalable Performance (veloxbase/veloxdb, 646 stars), Pnpm Engine (teambit/bit, 18k stars) and Testing Changes (pnpm/pnpm, 37k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Multi-AI Chat Launcher?
teddashh (a GitHub user) maintains it in teddashh/multi-ai-chat-desktop, which has 151 GitHub stars. The repository was last updated on October 7, 2026.
Source: teddashh/multi-ai-chat-desktop on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.