rohaquinlop/dsh-setup
My DeepSeek Harness setup: desktop profile overlay and personal skills. No credentials.
stack: Shell
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 rohaquinlop/dsh-setup/skills ./rig-dsh-setup/skills 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 rohaquinlop/dsh-setup/skills/adopt-pr .claude/skills/adopt-pr $ npx degit rohaquinlop/dsh-setup/skills/branch-context .claude/skills/branch-context $ npx degit rohaquinlop/dsh-setup/skills/bro .claude/skills/bro $ npx degit rohaquinlop/dsh-setup/skills/complete-partial-pr .claude/skills/complete-partial-pr $ npx degit rohaquinlop/dsh-setup/skills/docs-parity-reviewer .claude/skills/docs-parity-reviewer $ npx degit rohaquinlop/dsh-setup/skills/file-followup-issue .claude/skills/file-followup-issue $ npx degit rohaquinlop/dsh-setup/skills/git-commit .claude/skills/git-commit $ npx degit rohaquinlop/dsh-setup/skills/i-have-adhd .claude/skills/i-have-adhd $ npx degit rohaquinlop/dsh-setup/skills/init .claude/skills/init $ npx degit rohaquinlop/dsh-setup/skills/inline-review .claude/skills/inline-review $ npx degit rohaquinlop/dsh-setup/skills/plan-clarifier .claude/skills/plan-clarifier $ npx degit rohaquinlop/dsh-setup/skills/poweruser-feature-audit .claude/skills/poweruser-feature-audit $ npx degit rohaquinlop/dsh-setup/skills/pre-push-review .claude/skills/pre-push-review $ npx degit rohaquinlop/dsh-setup/skills/pushing-commits-to-the-repo .claude/skills/pushing-commits-to-the-repo $ npx degit rohaquinlop/dsh-setup/skills/refresh-issue-brief .claude/skills/refresh-issue-brief $ npx degit rohaquinlop/dsh-setup/skills/release-notes .claude/skills/release-notes $ npx degit rohaquinlop/dsh-setup/skills/uv .claude/skills/uv
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 (17)
Similar rigs
rohaquinlop/claude-config
Sanitized Claude Code config: skills, agents, hooks, settings
Skill Collector 2.6k tok · · Q8
andryorelabs/emet
Spec to merge on one approval: parallel workers in isolated worktrees, a review per wave, CI green before merge.
Pragmatist 2.3k tok · · Q53
ahmedelgabri/dotfiles
~ 🍭 ~
Skill Collector 7.8k tok · · Q3
ayghri/i-have-adhd
A skill to stop your coding agent from burying the answer. ADHD-friendly output.
Minimalist 1.4k tok · · Q3