jerseycheese/agent-skills
Agent skills for Claude Code, Codex, and Gemini CLI — shared workflows for testing, code review, issue triage, and dev loop automation.
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 jerseycheese/agent-skills/skills ./rig-agent-skills/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 jerseycheese/agent-skills/skills/abstraction-finder .claude/skills/abstraction-finder $ npx degit jerseycheese/agent-skills/skills/analyze-issue .claude/skills/analyze-issue $ npx degit jerseycheese/agent-skills/skills/backlog-routing .claude/skills/backlog-routing $ npx degit jerseycheese/agent-skills/skills/band-aid-finder .claude/skills/band-aid-finder $ npx degit jerseycheese/agent-skills/skills/browser-debugger-cli .claude/skills/browser-debugger-cli $ npx degit jerseycheese/agent-skills/skills/ci-fix-with-memory .claude/skills/ci-fix-with-memory $ npx degit jerseycheese/agent-skills/skills/code-health-audit .claude/skills/code-health-audit $ npx degit jerseycheese/agent-skills/skills/comment-reaper .claude/skills/comment-reaper $ npx degit jerseycheese/agent-skills/skills/cyoa .claude/skills/cyoa $ npx degit jerseycheese/agent-skills/skills/dead-code-cleanup .claude/skills/dead-code-cleanup $ npx degit jerseycheese/agent-skills/skills/doc-rot .claude/skills/doc-rot $ npx degit jerseycheese/agent-skills/skills/drupal-mental-model .claude/skills/drupal-mental-model $ npx degit jerseycheese/agent-skills/skills/ds-guard .claude/skills/ds-guard $ npx degit jerseycheese/agent-skills/skills/evidence-check .claude/skills/evidence-check $ npx degit jerseycheese/agent-skills/skills/github-screenshot .claude/skills/github-screenshot $ npx degit jerseycheese/agent-skills/skills/issue-maintenance .claude/skills/issue-maintenance $ npx degit jerseycheese/agent-skills/skills/kiss .claude/skills/kiss $ npx degit jerseycheese/agent-skills/skills/plain-language-audit .claude/skills/plain-language-audit $ npx degit jerseycheese/agent-skills/skills/post-merge .claude/skills/post-merge $ npx degit jerseycheese/agent-skills/skills/pr-review-fix-pipeline .claude/skills/pr-review-fix-pipeline $ npx degit jerseycheese/agent-skills/skills/prioritize-issues .claude/skills/prioritize-issues $ npx degit jerseycheese/agent-skills/skills/project-bootstrap .claude/skills/project-bootstrap $ npx degit jerseycheese/agent-skills/skills/project-pulse .claude/skills/project-pulse $ npx degit jerseycheese/agent-skills/skills/route .claude/skills/route $ npx degit jerseycheese/agent-skills/skills/ship-issue .claude/skills/ship-issue $ npx degit jerseycheese/agent-skills/skills/skill-parity .claude/skills/skill-parity $ npx degit jerseycheese/agent-skills/skills/tdd-implement .claude/skills/tdd-implement $ npx degit jerseycheese/agent-skills/skills/test-fix .claude/skills/test-fix $ npx degit jerseycheese/agent-skills/skills/test-reaper .claude/skills/test-reaper $ npx degit jerseycheese/agent-skills/skills/test-workflow .claude/skills/test-workflow $ npx degit jerseycheese/agent-skills/skills/update-routing .claude/skills/update-routing $ npx degit jerseycheese/agent-skills/skills/visual-crawl .claude/skills/visual-crawl $ npx degit jerseycheese/agent-skills/skills/visual-qa-pipeline .claude/skills/visual-qa-pipeline $ npx degit jerseycheese/agent-skills/skills/worktree-enhanced .claude/skills/worktree-enhanced $ npx degit jerseycheese/agent-skills/skills/wrap-it-up .claude/skills/wrap-it-up
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 (35)
abstraction-finderanalyze-issuebacklog-routingband-aid-finderbrowser-debugger-clici-fix-with-memorycode-health-auditcomment-reapercyoadead-code-cleanupdoc-rotdrupal-mental-modelds-guardevidence-checkgithub-screenshotissue-maintenancekissplain-language-auditpost-mergepr-review-fix-pipelineprioritize-issuesproject-bootstrapproject-pulserouteship-issueskill-paritytdd-implementtest-fixtest-reapertest-workflowupdate-routingvisual-crawlvisual-qa-pipelineworktree-enhancedwrap-it-up
Similar rigs
Eydenn/loomy
Your AI development team, orchestrated: Claude Code and Codex on your projects, each request routed to the right model for the least cost, cross reviews, official skills, shared memory and live tracking.
Pragmatist 4.4k tok · · Q8
jlucktay/dotfiles
My dotfiles, managed with https://github.com/twpayne/chezmoi
Minimalist 1.8k tok · · Q5
anton-dergunov/agentic-org-planner
Org-mode planning system for Emacs with an LLM agent working on the plan: it adds, files and edits tasks in your own files, every change reviewed as a diff.
Minimalist 447 tok · · Q0
rfidel214/project-template
Cross-tool AI agent workflow bootstrap template (Claude Code, OpenCode, KiloCode, Codex CLI)
Pragmatist 9.7k tok · · Q5