agentrigs
+ submit rig
~ / rigs / google-gemini / gemini-skills

google-gemini/gemini-skills

Skills for the Gemini API, SDK and model/agent interactions

↗ GitHub ★ 4,239 apache-2.0 updated 16d ago collection Claude Code Claude plugin
share on X
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
CONTEXT TAX · EVERY TURN
~261 tokens
Featherweight · median rig: 2.2k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit google-gemini/gemini-skills/skills ./rig-gemini-skills/skills

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ npx degit google-gemini/gemini-skills/skills/gemini-api-dev .claude/skills/gemini-api-dev
$ npx degit google-gemini/gemini-skills/skills/gemini-live-api-dev .claude/skills/gemini-live-api-dev
$ npx degit google-gemini/gemini-skills/skills/gemini-omni-flash-api .claude/skills/gemini-omni-flash-api

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,413 rigs:

{
  "permissions": {
    "deny": [
      "Read(~/.ssh/**)",
      "Read(**/.env)",
      "Bash(rm -rf *)",
      "Read(./.env)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /*)",
      "Read(~/.aws/**)",
      "Bash(rm -rf:*)",
      "Read(.env)",
      "Bash(git push --force*)",
      "Read(**/*.key)",
      "Read(./.env.*)",
      "Read(**/.env.*)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(wget *)",
      "Bash(npm publish:*)",
      "Bash(gh pr merge *)",
      "Bash(chown *)",
      "Bash(docker *)"
    ]
  }
}

Skills (3)

gemini-api-devgemini-live-api-devgemini-omni-flash-api

Similar rigs

sagaargroups/OpenWarehouse
The Universal Open-Source Warehouse for AI Agents, Skills, MCP Servers & Plugins
★ 0 project Claude Code 30 mcp 150 skills 1d ago
MCP Hoarder 94.7k tok ·
tmolavi/mcp-agent-skills-hub
Molavi Agent Skills: Curated AI agent skills and MCP configs for Antigravity, Cursor, Codex & Claude — by Taghi Molavi
★ 0 collection Claude CodeCodex 150 skills 3mo ago
Skill Collector 6.9k tok ·
multica-ai/andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
★ 217k collection Claude CodeCursor 1 skills 6mo ago
Minimalist 723 tok ·
shareAI-lab/learn-claude-code
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
★ 78.0k project Claude Code 4 skills 11d ago
Minimalist 156 tok ·
copied ✓