szaghi/dotfiles
my dotfiles...me!
ARCHETYPE
YOLO Cowboy
Permissions? Never heard of 'em. Ships at the speed of `--dangerously-skip-permissions`.
Copy this rig
# review before running: this installs third-party code
$ npx degit szaghi/dotfiles/claude/.claude ./rig-dotfiles # 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 szaghi/dotfiles/claude/.claude/skills/ai-research-verification .claude/skills/ai-research-verification $ npx degit szaghi/dotfiles/claude/.claude/skills/blog .claude/skills/blog $ npx degit szaghi/dotfiles/claude/.claude/skills/cpp-hpc .claude/skills/cpp-hpc $ npx degit szaghi/dotfiles/claude/.claude/skills/cuda-programming .claude/skills/cuda-programming $ npx degit szaghi/dotfiles/claude/.claude/skills/darktable-operator .claude/skills/darktable-operator $ npx degit szaghi/dotfiles/claude/.claude/skills/darktable-raw .claude/skills/darktable-raw $ npx degit szaghi/dotfiles/claude/.claude/skills/fobis .claude/skills/fobis $ npx degit szaghi/dotfiles/claude/.claude/skills/fortran-2023-standard .claude/skills/fortran-2023-standard $ npx degit szaghi/dotfiles/claude/.claude/skills/gpu-multithreading .claude/skills/gpu-multithreading $ npx degit szaghi/dotfiles/claude/.claude/skills/hpc-cluster-tooling .claude/skills/hpc-cluster-tooling $ npx degit szaghi/dotfiles/claude/.claude/skills/hpc-index .claude/skills/hpc-index $ npx degit szaghi/dotfiles/claude/.claude/skills/hpc-numerics .claude/skills/hpc-numerics $ npx degit szaghi/dotfiles/claude/.claude/skills/iso-c-9899-2024 .claude/skills/iso-c-9899-2024 $ npx degit szaghi/dotfiles/claude/.claude/skills/iso-cpp-2023 .claude/skills/iso-cpp-2023 $ npx degit szaghi/dotfiles/claude/.claude/skills/markdown-mermaid-writing .claude/skills/markdown-mermaid-writing $ npx degit szaghi/dotfiles/claude/.claude/skills/markitdown .claude/skills/markitdown $ npx degit szaghi/dotfiles/claude/.claude/skills/mpi-5.0 .claude/skills/mpi-5.0 $ npx degit szaghi/dotfiles/claude/.claude/skills/openacc-3.4 .claude/skills/openacc-3.4 $ npx degit szaghi/dotfiles/claude/.claude/skills/openmp-6.0 .claude/skills/openmp-6.0 $ npx degit szaghi/dotfiles/claude/.claude/skills/python-hpc .claude/skills/python-hpc $ npx degit szaghi/dotfiles/claude/.claude/skills/remotion-infographics .claude/skills/remotion-infographics $ npx degit szaghi/dotfiles/claude/.claude/skills/research-lookup .claude/skills/research-lookup $ npx degit szaghi/dotfiles/claude/.claude/skills/scientific-writing .claude/skills/scientific-writing
$ curl -fsSL --create-dirs -o .claude/agents/blog-code-checker.md https://raw.githubusercontent.com/szaghi/dotfiles/master/claude/.claude/agents/blog-code-checker.md $ curl -fsSL --create-dirs -o .claude/agents/blog-prose-reviewer.md https://raw.githubusercontent.com/szaghi/dotfiles/master/claude/.claude/agents/blog-prose-reviewer.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 (23)
ai-research-verificationblogcpp-hpccuda-programmingdarktable-operatordarktable-rawfobisfortran-2023-standardgpu-multithreadinghpc-cluster-toolinghpc-indexhpc-numericsiso-c-9899-2024iso-cpp-2023markdown-mermaid-writingmarkitdownmpi-5.0openacc-3.4openmp-6.0python-hpcremotion-infographicsresearch-lookupscientific-writing
Subagents (2)
| blog-code-checker | > |
| blog-prose-reviewer | > |
Hooks (4)
| event | matcher | runs |
|---|---|---|
| SessionStart | * | bash ~/.claude/hooks/load-context-by-cwd.sh |
| UserPromptSubmit | * | bash ~/.claude/hooks/context-memory-guard.sh |
| PostToolUse | * | bash ~/.claude/hooks/context-memory-guard.sh |
| Stop | * | bash ~/.claude/hooks/context-memory-guard.sh |
Slash commands (2)
/capture-findings/semantic-commit
Plugins (5)
frontend-design@claude-plugins-officialskill-creator@claude-plugins-officialcli-anything@cli-anythingdocument-skills@anthropic-agent-skillsecc@ecc
Permissions
deny (0)
—
ask (0)
—
allow (4)
Read(~/fortran/**)
Edit(~/fortran/**)
Read(~/python/**)
Edit(~/python/**)
Similar rigs
K-Dense-AI/claude-scientific-writer
A general purpose scientific writer
Skill Collector 8.2k tok · · Q3
jahyunlee00299/sci-toolkit
Lab-shared Claude Code skillset for scientific work — literature, manuscripts, figures, data analysis, with verification gates
Skill Collector 9.1k tok · · Q8
ARAVINDAN20/Claude-Research-Paper-OS
Drop-in .claude/ config that turns Claude Code into an autonomous academic paper production system. 6 agents, 47+ skills, 5-phase pipeline from literature search to submission-ready manuscript.
Orchestrator 6.3k tok · · Q0
cloudQuant/backtrader
Optimized Python fork of Backtrader for strategy backtesting and live trading, with vectorized and event-driven modes, multi-timeframe data, technical indicators, and portfolio analytics.
Pragmatist 5.8k tok · · Q3