dnswd/skill
My personal collections of AI agent skills, tailored for OMP but Claude Code Marketplace compliant.
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 dnswd/skill/skills ./rig-skill/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 dnswd/skill/skills/Alvarmethod/skills/learn-profile .claude/skills/learn-profile $ npx degit dnswd/skill/skills/Alvarmethod/skills/learn-verify .claude/skills/learn-verify $ npx degit dnswd/skill/skills/Alvarmethod/skills/learn-visual .claude/skills/learn-visual $ npx degit dnswd/skill/skills/Alvarmethod/skills/probe .claude/skills/probe $ npx degit dnswd/skill/skills/Alvarmethod/skills/teach .claude/skills/teach $ npx degit dnswd/skill/skills/deepwiki .claude/skills/deepwiki $ npx degit dnswd/skill/skills/knowledge-management/skills/hindsight-churn .claude/skills/hindsight-churn $ npx degit dnswd/skill/skills/knowledge-management/skills/omp-notion/skills/setup-oauth .claude/skills/setup-oauth $ npx degit dnswd/skill/skills/knowledge-management/skills/omp-notion/skills/workspace-explorer .claude/skills/workspace-explorer $ npx degit dnswd/skill/skills/knowledge-management/skills/registrar .claude/skills/registrar $ npx degit dnswd/skill/skills/taste-skill/skills/brandkit .claude/skills/brandkit $ npx degit dnswd/skill/skills/taste-skill/skills/brutalist-skill .claude/skills/brutalist-skill $ npx degit dnswd/skill/skills/taste-skill/skills/gpt-tasteskill .claude/skills/gpt-tasteskill $ npx degit dnswd/skill/skills/taste-skill/skills/image-to-code-skill .claude/skills/image-to-code-skill $ npx degit dnswd/skill/skills/taste-skill/skills/imagegen-frontend-mobile .claude/skills/imagegen-frontend-mobile $ npx degit dnswd/skill/skills/taste-skill/skills/imagegen-frontend-web .claude/skills/imagegen-frontend-web $ npx degit dnswd/skill/skills/taste-skill/skills/minimalist-skill .claude/skills/minimalist-skill $ npx degit dnswd/skill/skills/taste-skill/skills/output-skill .claude/skills/output-skill $ npx degit dnswd/skill/skills/taste-skill/skills/redesign-skill .claude/skills/redesign-skill $ npx degit dnswd/skill/skills/taste-skill/skills/soft-skill .claude/skills/soft-skill $ npx degit dnswd/skill/skills/taste-skill/skills/stitch-skill .claude/skills/stitch-skill $ npx degit dnswd/skill/skills/taste-skill/skills/taste-skill-v1 .claude/skills/taste-skill-v1 $ npx degit dnswd/skill/skills/taste-skill/skills/taste-skill .claude/skills/taste-skill
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)
learn-profilelearn-verifylearn-visualprobeteachdeepwikihindsight-churnsetup-oauthworkspace-explorerregistrarbrandkitindustrial-brutalist-uigpt-tasteimage-to-codeimagegen-frontend-mobileimagegen-frontend-webminimalist-uifull-output-enforcementredesign-existing-projectshigh-end-visual-designstitch-design-tastedesign-taste-frontend-v1design-taste-frontend
Similar rigs
Leonxlnx/taste-skill
Taste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop
Skill Collector 1.2k tok · · Q0
anas1412/dotfiles
Material You rice for Arch (CachyOS) + KDE Plasma 6 on Wayland, managed with GNU Stow
Skill Collector 1.1k tok · · Q0
techmefr/forge-ops
Story-driven board that orchestrates Claude Code agent sessions and refuses to let a story advance without proof: every story carries a twin test story, every checkpoint needs an evidence file on disk, out-of-order steps are refused server-
Skill Collector 1.2k tok · · Q15
adlakhavansh/claude-setup
Claude Code config: CLAUDE.md, settings, skills, commands, hooks
Skill Collector 5.3k tok · · Q20