CC4PMs Mastery Bonus — AI skill for Claude Code
3 Claude Code skills & commands: multi-model council, subagent delegation, and web research.
How to install CC4PMs Mastery Bonus
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open carlvellotti/CC4PMs-mastery-bonus and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What CC4PMs Mastery Bonus does
3 Claude Code skills & commands: multi-model council, subagent delegation, and web research.
Alternatives in AI
- Discover — Discovery phase - Multi-AI research and exploration 2.8k ★
- NotebookLM Research Agent — A fully autonomous AI research agent that ingests sources into Google NotebookLM, runs deep web research, synt 168 ★
- Ultimate MCP Server — Comprehensive MCP server exposing dozens of capabilities to AI agents: multi-provider LLM delegation, browser 146 ★
README
CC4PMs Mastery Bonus: Claude Code Skills & Commands
Three power-ups for Claude Code that make it dramatically more useful.
| Skill | What It Does | Type | Prerequisites |
|---|---|---|---|
/consult-the-council |
Ask GPT, Gemini, and Grok the same question — get 3 perspectives at once | Command | API keys for OpenAI, Google, xAI |
/spin-up |
Force Claude to delegate work to parallel subagents instead of doing everything in one thread | Command | None |
/web-research |
Upgraded web research with Tavily search + Firecrawl scraping | Skill | Tavily MCP server, Firecrawl CLI |
Quick Concepts: Skills vs Commands
Claude Code has two extension types:
- Commands (
.claude/commands/) — Slash commands you invoke manually (e.g.,/consult-the-council). They're prompt files that tell Claude what to do. - Skills (
.claude/skills/) — Automatic behaviors Claude activates when relevant. They include trigger conditions, allowed tools, and reference docs. You can also invoke them manually.
Both live in your project's `.claude/` directory.
Installation
1. `/consult-the-council` — Multi-Model Council
Ask Claude to consult GPT, Gemini, and Grok simultaneously and synthesize their answers. Great for hard decisions, architecture debates, or getting unstuck.
**Install:**
# Copy the command file
cp consult-the-council/consult-the-council.md YOUR_PROJECT/.claude/commands/
# Copy the Python script (put it wherever makes sense for your project)
cp consult-the-council/consult_council.py YOUR_PROJECT/scripts/
**Important:** Update the script path in `consult-the-council.md` (line 31) to match where you put `consult_council.py`.
**Prerequisites:**
# Install Python dependencies
pip3 install openai google-genai
# Set API keys (add to your .env or export them)
OPENAI_API_KEY=sk-... # https://platform.openai.com/api-keys
G
Related Skills
Dsh Legion
Multi-agent orchestration and LLM model routing for DeepSeek Harness (DSH): semantic AI agent profiles, exact
Council Refine
/council-refine — Multi-Model Plan Refinement with Opus 4.6 Synthesis
Export To Council
/export-to-council — Export Session to Multi-Model Council Analysis
Bpx Council
A portable multi-model council CLI — one advisor or a whole debating council, usable from any coding agent (Cl
Multi Agent LLM Council
Multi-LLM consensus & evaluation platform querying OpenAI, Gemini, Claude, DeepSeek & Mistral in parallel to c
AI Debate Club
A multi-agent debate engine. Two different LLMs argue any motion, research the web for themselves, and cite th
Related Agents
Councillor
Read-only council advisor. Examines the codebase and provides independent analysis. Spawned by the /council co
Council Munger
Council member. Use standalone for multi-model reasoning & economic analysis, or via /council for multi-perspe
Council Chairman
Chief arbiter of the LLM Council that synthesizes multi-model responses. MUST BE INVOKED after council members