hashgraph-online/awesome-codex-plugins / plugins/beastlabai/multi-llm-plugin/skills/multi-llm
multi-llm
FlaggedOrchestrate plan reviews, task generation, implementation and code reviews across several LLM CLIs in parallel, or ask every model one free-text question about a plan. Use when the user says: review my plan, multi-llm, run a code review, generate tasks from a plan, implement this plan, ask the models about my plan.
hosts/uv-missing.txt
View on GitHub[UV_MISSING] uv is required and could not be found.
Every multi-llm command runs through `uv run --project <skill-dir>`, so nothing
can start until uv resolves. Install it, then re-run the same command:
1) Official installer - Linux / macOS
curl -LsSf https://astral.sh/uv/install.sh | sh
(installs to ~/.local/bin/uv)
2) Official installer - Windows
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
(installs uv.exe to %USERPROFILE%\.local\bin, i.e. ~/.local/bin/uv.exe
under Git Bash)
3) Package manager - whichever fits the platform
brew install uv | pipx install uv | pip install --user uv
winget install --id=astral-sh.uv -e | your distro's package
Already installed? It may not be on PATH yet. uv is looked for in $MULTI_LLM_UV,
then on PATH, then at:
~/.local/bin/uv[.exe], ~/.cargo/bin/uv[.exe], /opt/homebrew/bin/uv,
/usr/local/bin/uv, /opt/local/bin/uv
Add the install directory to PATH - or just restart the shell, since the
installers update the profile - and re-run.
There is no bare-`python` fallback, deliberately: this skill's dependencies are
pinned in uv.lock and resolved by uv from pyproject.toml, so a bare interpreter
would run against whatever happens to be importable - a ModuleNotFoundError at
best, a silently wrong dependency version mid-fan-out at worst. The documented
recovery is always "install uv, re-run".
Docs: https://docs.astral.sh/uv/getting-started/installation/
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirements | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |