sami-abdul/claude-content-pipeline
Content Intelligence System for Claude Code. Skills, agents, and rules that mine real codebases to produce grounded social media content. Adapted from production agent infrastructure (claude-pre-dev-setup + agentic-org).
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 sami-abdul/claude-content-pipeline/.claude ./rig-claude-content-pipeline # 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 sami-abdul/claude-content-pipeline/.claude/skills/10-10-post .claude/skills/10-10-post $ npx degit sami-abdul/claude-content-pipeline/.claude/skills/code-mining .claude/skills/code-mining $ npx degit sami-abdul/claude-content-pipeline/.claude/skills/content-pipeline .claude/skills/content-pipeline $ npx degit sami-abdul/claude-content-pipeline/.claude/skills/copywriting .claude/skills/copywriting $ npx degit sami-abdul/claude-content-pipeline/.claude/skills/humanizer .claude/skills/humanizer $ npx degit sami-abdul/claude-content-pipeline/.claude/skills/proposal-pipeline .claude/skills/proposal-pipeline
$ curl -fsSL --create-dirs -o .claude/agents/anti-ai-reviewer.md https://raw.githubusercontent.com/sami-abdul/claude-content-pipeline/main/.claude/agents/anti-ai-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/draft-reviewer.md https://raw.githubusercontent.com/sami-abdul/claude-content-pipeline/main/.claude/agents/draft-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/insight-architect.md https://raw.githubusercontent.com/sami-abdul/claude-content-pipeline/main/.claude/agents/insight-architect.md $ curl -fsSL --create-dirs -o .claude/agents/post-verifier.md https://raw.githubusercontent.com/sami-abdul/claude-content-pipeline/main/.claude/agents/post-verifier.md $ curl -fsSL --create-dirs -o .claude/agents/proposal-reviewer.md https://raw.githubusercontent.com/sami-abdul/claude-content-pipeline/main/.claude/agents/proposal-reviewer.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 (6)
Subagents (5)
| anti-ai-reviewer model: sonnet | | |
| draft-reviewer model: sonnet | | |
| insight-architect model: opus | | |
| post-verifier model: sonnet | | |
| proposal-reviewer model: sonnet | | |
Similar rigs
Aboudjem/humanizer-skill
Free, open-source AI writing humanizer and detector. 55 patterns, 5 voices, a 0-100 AI-tell score, and nothing leaves your machine.
Minimalist 1.7k tok ·
GrassHeadd/dotfiles
Personal dotfiles: fish, ghostty, nvim, tmux, aerospace, Claude Code + Codex configs
Pragmatist 5.0k tok ·
robonuggets/agentic-ai-starter-kit
Beginner-friendly setup for Claude Code and other agentic AI tools. Personalised CLAUDE.md, safety rails, 2 starter skills.
Minimalist 96 tok ·
Land-o-Clusters/sleight
Let Claude Code drive Mac apps in the background through the computer-use engine bundled with the ChatGPT desktop app.
Minimalist 405 tok ·