broomva/skills
Broomva agent-skills monorepo — 48 Tier-2 skills compatible with Claude Code, Codex, Cursor, Gemini CLI, Goose, Copilot. Layout follows anthropics/skills (agentskills.io spec). Install: npx skills add broomva/skills --skill <name>.
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code
$ npx degit broomva/skills/skills/research/deep-dive-research-orchestrator/.claude ./rig-skills # inspect, then merge into .claude/ 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 broomva/skills/skills/video/content-engine/skills/content-engine-autopilot .claude/skills/content-engine-autopilot $ npx degit broomva/skills/skills/video/content-engine/skills/content-engine-cinema .claude/skills/content-engine-cinema $ npx degit broomva/skills/skills/video/content-engine/skills/content-engine-dna .claude/skills/content-engine-dna $ npx degit broomva/skills/skills/video/content-engine/skills/content-engine-loop .claude/skills/content-engine-loop
$ curl -fsSL --create-dirs -o .claude/agents/competitive-analyst.md https://raw.githubusercontent.com/broomva/skills/main/skills/research/deep-dive-research-orchestrator/.claude/agents/competitive-analyst.md $ curl -fsSL --create-dirs -o .claude/agents/financial-researcher.md https://raw.githubusercontent.com/broomva/skills/main/skills/research/deep-dive-research-orchestrator/.claude/agents/financial-researcher.md $ curl -fsSL --create-dirs -o .claude/agents/governance-auditor.md https://raw.githubusercontent.com/broomva/skills/main/skills/research/deep-dive-research-orchestrator/.claude/agents/governance-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/market-product-analyst.md https://raw.githubusercontent.com/broomva/skills/main/skills/research/deep-dive-research-orchestrator/.claude/agents/market-product-analyst.md $ curl -fsSL --create-dirs -o .claude/agents/research-orchestrator.md https://raw.githubusercontent.com/broomva/skills/main/skills/research/deep-dive-research-orchestrator/.claude/agents/research-orchestrator.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"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(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Skills (4)
Subagents (5)
| competitive-analyst model: sonnet | Provides data-backed competitive intelligence using the competitor-intel skill's mandatory web research framework. Researches real signals across 6 categories to deliver verified business metrics, act |
| financial-researcher model: sonnet | Conducts enterprise-grade financial research using the financial-deep-research skill's 8-phase pipeline with multi-source synthesis, regulatory compliance, and verified market analysis. Use for financ |
| governance-auditor model: haiku | Applies governance policies, audit trails, and quality controls to research outputs. Use when research requires compliance verification, policy enforcement, or audit documentation. |
| market-product-analyst model: sonnet | Complete ASO and market analysis specialist using the app-store-optimization skill toolkit. Researches app performance, optimizes metadata, analyzes competitors, manages reviews, and tracks ASO health |
| research-orchestrator model: opus | Orchestrates comprehensive multi-dimensional research by coordinating financial-researcher, competitive-analyst, and market-product-analyst agents in parallel, then synthesizing their findings into pr |
Similar rigs
kelegele/oh-my-pm
Oh-My-PM - Product Manager AI Agent Workflow System via Claude Code Skills
Orchestrator 5.7k tok ·
mcp-tool-shop-org/role-os
Role OS — a repo-native operating layer that staffs coding-agent work through 61 role contracts, packs, missions, recipe cards, and a critic jury. Claude Code adapter ships; the contracts are markdown any harness can consume.
Orchestrator 364 tok ·
aneja5/forge-skills
An assembly line for AI software development. 35 skills, 11 agent personas, 29 commands. From raw idea to shipped code.
Orchestrator 7.7k tok ·
carlopezzuto/agents
Claude Code configuration with 42 specialized agents, 33 skills, 28 commands, and a hook system for development best practices
Orchestrator 6.3k tok ·