← All skills
llm-manager
85 / 100 · Low risk
Fine to try. Some of what it can do is expected: a coding skill usually runs build and test commands.
By diegosouzapw/awesome-omni-skill (GitHub) · coding · 66 stars · scanned at commit a6b3c30
Claude acts as manager/architect while delegating all coding to external LLM CLIs (Gemini, Codex, Qwen). Claude never writes code - only plans, delegates, and verifies. Use when user says "manage", "architect mode", "delegate to", or wants Claude to drive another LLM.
Works with any agent that supports SKILL.md skills.
What this skill can do
Runs commands on your computer
The author does not mention this. Expected for a coding skill.
Found in 21 places.
Show 17 more
- skills/data-ai/llm-manager/SKILL.md, line 185
qwen "TASK: [specific instruction] - skills/data-ai/llm-manager/SKILL.md, line 208
gemini "FIX: [specific issue found] - skills/data-ai/llm-manager/SKILL.md, line 225
gemini "Implement [feature] in [file]. - skills/data-ai/llm-manager/SKILL.md, line 235
codex exec "Implement [feature] in [file]. - skills/data-ai/llm-manager/SKILL.md, line 245
qwen "Implement [feature] in [file]. - skills/data-ai/llm-manager/SKILL.md, line 257
gemini "Fix bug in [file] at line [N]. - skills/data-ai/llm-manager/SKILL.md, line 266
codex exec "Fix bug in [file] at line [N]. - skills/data-ai/llm-manager/SKILL.md, line 275
qwen "Fix bug in [file] at line [N]. - skills/data-ai/llm-manager/SKILL.md, line 286
gemini "Create tests for [file/function]. - skills/data-ai/llm-manager/SKILL.md, line 295
codex exec "Create tests for [file/function]. - skills/data-ai/llm-manager/SKILL.md, line 304
qwen "Create tests for [file/function]. - skills/data-ai/llm-manager/SKILL.md, line 346
gemini "FIX: You are over-engineering this. - skills/data-ai/llm-manager/SKILL.md, line 376
gemini "FIX: Cut the attitude. Just do the work. - skills/data-ai/llm-manager/SKILL.md, line 384
gemini "FIX: You're taking shortcuts. - skills/data-ai/llm-manager/SKILL.md, line 465
llm-task.sh --brainstorm "Should we use microservices or monolith for this e-commerce app? Consider scale, team size, deployment complexity." - skills/data-ai/llm-manager/SKILL.md, line 484
~/.claude/skills/llm-manager/scripts/llm-task.sh "task description" - skills/data-ai/llm-manager/SKILL.md, line 510
~/.claude/skills/llm-manager/scripts/llm-daemon.sh start
and 1 more places
Changes files outside its own folder
This is disclosed by the author in the skill's SKILL.md or README.
Found in 1 place.
Sends data to these websites: raw.githubusercontent.com
The author does not mention this.
Found in 1 place.
Other copies in this repository
diegosouzapw/awesome-omni-skill has 1 more folder with a skill named llm-manager. This page shows the lowest-scoring copy.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'llm-manager' ] || [ -L ~/.agents/skills/'llm-manager' ]; then echo 'A skill folder named llm-manager already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/diegosouzapw/awesome-omni-skill' "$d" && git -C "$d" checkout --quiet 'a6b3c3005cedf056a48b084671c6282426d6e9fc' -- 'skills/data-ai/llm-manager' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/data-ai/llm-manager' ~/.agents/skills/'llm-manager' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'llm-manager' ~/.claude/skills/'llm-manager' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
The badge for diegosouzapw/awesome-omni-skill shows the score of its lowest-scoring skill.

[](https://zalavijaysinh.github.io/skilltrust/repos/diegosouzapw/awesome-omni-skill/)
Score history
| Date | Version | Score |
|---|
| 2026-11-07 | a6b3c30 | 85 |