AhmedAl-Ashwal/claude-code-global-config
Global Claude Code configuration: one CLAUDE.md with unified phases for every project, a /report session-summary command, and the design-md skill. English and Arabic README.
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code $ npx degit AhmedAl-Ashwal/claude-code-global-config/commands ./rig-claude-code-global-config/commands $ npx degit AhmedAl-Ashwal/claude-code-global-config/skills ./rig-claude-code-global-config/skills $ npx degit AhmedAl-Ashwal/claude-code-global-config/hooks ./rig-claude-code-global-config/hooks
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 AhmedAl-Ashwal/claude-code-global-config/skills/data-analysis .claude/skills/data-analysis $ npx degit AhmedAl-Ashwal/claude-code-global-config/skills/design-md .claude/skills/design-md $ npx degit AhmedAl-Ashwal/claude-code-global-config/skills/erpnext-frappe .claude/skills/erpnext-frappe $ npx degit AhmedAl-Ashwal/claude-code-global-config/skills/report-writing .claude/skills/report-writing $ npx degit AhmedAl-Ashwal/claude-code-global-config/skills/video-production .claude/skills/video-production
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 (5)
Slash commands (1)
/report
Similar rigs
DougTrajano/pydantic-ai-skills
This package implements Agent Skills (https://agentskills.io) support with progressive disclosure for Pydantic AI. Supports filesystem and programmatic skills.
Pragmatist 2.3k tok ·
shellui/skills
Official Agent Skills for Shellui - config, CLI, SDK, and conventions for AI coding agents.
Pragmatist 57 tok ·
vstorm-co/pydantic-deepagents
Open-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it. Tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints, unlimited context - on Pydantic AI, any model.
Skill Collector 5.0k tok ·
JimLiu/baocut
BaoCut: an AI video agent with an editable timeline. Transcribe, subtitle, translate, dub, cut and animate.
Skill Collector 3.2k tok ·