juyoungml/nemo-k-cards
Research Korean events, create English Instagram carousels, and publish with human approval. Claude Code + NVIDIA OpenShell.
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 juyoungml/nemo-k-cards/agent/.claude ./rig-nemo-k-cards # 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 juyoungml/nemo-k-cards/agent/.claude/skills/event-sources .claude/skills/event-sources $ curl -fsSL --create-dirs -o .claude/agents/copywriter.md https://raw.githubusercontent.com/juyoungml/nemo-k-cards/main/agent/.claude/agents/copywriter.md $ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/juyoungml/nemo-k-cards/main/agent/.claude/agents/planner.md $ curl -fsSL --create-dirs -o .claude/agents/researcher.md https://raw.githubusercontent.com/juyoungml/nemo-k-cards/main/agent/.claude/agents/researcher.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/juyoungml/nemo-k-cards/main/agent/.claude/agents/reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/safeguard.md https://raw.githubusercontent.com/juyoungml/nemo-k-cards/main/agent/.claude/agents/safeguard.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (1)
Subagents (5)
| copywriter | Turns verified EventBriefs (and optional brainstorm constraints) into a 6–8 slide CardDeck JSON. |
| planner | Brainstorm-mode co-planner. Updates the Brainstorm board (facts, 3 angles, outline) from a chat turn. Outputs BrainstormUpdate JSON. |
| researcher | Finds and structures current events in Korea for foreigners. Outputs EventBrief[] JSON. |
| reviewer | Final gate before human review — checks facts, sensitivity, PII, tone and the rendered slide images. Outputs ReviewVerdict JSON. |
| safeguard | Hard safety gate before publishing. Decides allow/block for harmful content in a card deck and explains why. Outputs SafeguardModelOutput JSON. |
Similar rigs
Fili999/ai-hub
One hub for your AI coding agents, skills and workflows: write them once, install them into Claude Code, Codex, Antigravity CLI and local models. Free, open source, runs on your computer.
Minimalist 903 tok · · Q8
iuliandita/agents
Global prompts and subagent roles for coding agents, deployed to every harness you use.
Orchestrator 1.5k tok · · Q3
fjerbi/claude-code-arsenal
A tested Claude Code operating system for efficient, reliable, and focused software engineering. Includes global instructions, workflows, rules, and tools designed to minimize wasted tokens, prevent hallucinations and unnecessary loops, enf
YOLO Cowboy 4.0k tok · · Q51
jaqubowsky/fleet
Runs Claude Code and pi agents in parallel on your Mac, one Docker sandbox per issue. A host agent hands out the work, watches every sandbox and brings back tested, reviewed pull requests.
Minimalist 566 tok · · Q0