ooloth/dotfiles
My macOS development environment, including the agent skills and workflows I use for software engineering.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code
$ npx degit ooloth/dotfiles/.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 ooloth/dotfiles/.claude/skills/add-tool .claude/skills/add-tool $ npx degit ooloth/dotfiles/.claude/skills/next .claude/skills/next $ npx degit ooloth/dotfiles/.claude/skills/uphold-project-invariants .claude/skills/uphold-project-invariants $ npx degit <redacted> .claude/skills/commit $ npx degit <redacted>-pr .claude/skills/create-pr $ npx degit <redacted> .claude/skills/design $ npx degit <redacted> .claude/skills/discuss $ npx degit <redacted> .claude/skills/handoff $ npx degit <redacted>-unattended .claude/skills/implement-unattended $ npx degit ooloth/dotfiles/tools/agents/config/skills/plan-unattended .claude/skills/plan-unattended $ npx degit <redacted>-it-works .claude/skills/prove-it-works $ npx degit <redacted>-code .claude/skills/review-code $ npx degit <redacted>-completion .claude/skills/review-completion $ npx degit <redacted>-converge .claude/skills/review-converge $ npx degit <redacted>-pr-comments-converge .claude/skills/review-pr-comments-converge $ npx degit <redacted>-prs .claude/skills/review-prs $ npx degit ooloth/dotfiles/tools/agents/config/skills/scan-gaps .claude/skills/scan-gaps $ npx degit ooloth/dotfiles/tools/agents/config/skills/scan-harness .claude/skills/scan-harness $ npx degit ooloth/dotfiles/tools/agents/config/skills/scan-ideas .claude/skills/scan-ideas $ npx degit ooloth/dotfiles/tools/agents/config/skills/scan-impact .claude/skills/scan-impact $ npx degit ooloth/dotfiles/tools/agents/config/skills/scan-standards .claude/skills/scan-standards $ npx degit <redacted>-standards .claude/skills/uphold-standards $ npx degit ooloth/dotfiles/tools/agents/config/skills/use-argo .claude/skills/use-argo $ npx degit ooloth/dotfiles/tools/agents/config/skills/use-codefresh .claude/skills/use-codefresh $ npx degit ooloth/dotfiles/tools/agents/config/skills/use-gh .claude/skills/use-gh $ npx degit ooloth/dotfiles/tools/agents/config/skills/use-linear .claude/skills/use-linear $ npx degit ooloth/dotfiles/tools/agents/config/skills/use-next-devtools .claude/skills/use-next-devtools $ npx degit ooloth/dotfiles/tools/agents/config/skills/use-notion .claude/skills/use-notion $ npx degit ooloth/dotfiles/tools/agents/config/skills/use-trekker .claude/skills/use-trekker $ npx degit <redacted>-pr-description .claude/skills/write-pr-description $ npx degit <redacted>-ticket-description .claude/skills/write-ticket-description $ npx degit ooloth/dotfiles/tools/claude/config/@archive/skills/draft-til-style-blog-post .claude/skills/draft-til-style-blog-post $ npx degit ooloth/dotfiles/tools/claude/config/@archive/skills/fetch-github-prs-to-review .claude/skills/fetch-github-prs-to-review $ npx degit ooloth/dotfiles/tools/claude/config/@archive/skills/scanning-git-for-tils .claude/skills/scanning-git-for-tils $ npx degit ooloth/dotfiles/tools/claude/config/@archive/skills/scanning-notion-for-tils .claude/skills/scanning-notion-for-tils $ npx degit ooloth/dotfiles/tools/claude/config/@archive/skills/use-beads .claude/skills/use-beads $ npx degit ooloth/dotfiles/tools/claude/config/@archive/skills/validate .claude/skills/validate
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 (37)
add-toolnextuphold-project-invariantscommitcreate-prdesigndiscusshandoffimplement-unattendedplan-unattendedprove-it-worksreview-codereview-completionreview-convergereview-pr-comments-convergereview-prsscan-gapsscan-harnessscan-ideasscan-impactscan-standardsuphold-standardsuse-argouse-codefreshuse-ghuse-linearuse-next-devtoolsuse-notionuse-trekkerwrite-pr-descriptionwrite-ticket-descriptiondrafting-tilfetch-github-prs-to-reviewscanning-git-for-tilsscanning-notion-for-tilsuse-beadsvalidate
Similar rigs
PacificStudio/openase
Ticket-Driven Automated Software Engineering. OpenASE is an all-in-one platform that turns tickets into working code — AI agents automatically pick up tickets, execute workflows on your machines, and deliver results with full traceability.
Skill Collector 2.3k tok ·
vichannnnn/ccstart
Quick setup for projects or repositories using Claude Code with built-in agents, ticket system, and planning tools.
Pragmatist 3.0k tok ·
ikanago/dotfiles
Dotfiles deployed by Ansible 🚀
Pragmatist 291 tok ·
AI-BrandFactory/claude-code-starter-pack
Working templates for Claude Code primitives: slash commands, skills, hooks, subagents, MCP configs, Agent SDK starters. Current to Opus 4.7, April 2026.
Fort Knox 584 tok ·