eai-org/agent-toolkit
Minimalistic, project-agnostic skills and rules for AI coding agents
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 eai-org/agent-toolkit/skills ./rig-agent-toolkit/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 eai-org/agent-toolkit/skills/agentify-project .claude/skills/agentify-project $ npx degit eai-org/agent-toolkit/skills/attach-to-ticket .claude/skills/attach-to-ticket $ npx degit eai-org/agent-toolkit/skills/check-ticket-implementation .claude/skills/check-ticket-implementation $ npx degit eai-org/agent-toolkit/skills/compact-docs-writer .claude/skills/compact-docs-writer $ npx degit eai-org/agent-toolkit/skills/compact-skill-creator .claude/skills/compact-skill-creator $ npx degit eai-org/agent-toolkit/skills/context-checkup .claude/skills/context-checkup $ npx degit eai-org/agent-toolkit/skills/create-implementation-plan .claude/skills/create-implementation-plan $ npx degit eai-org/agent-toolkit/skills/create-manual-test-instructions .claude/skills/create-manual-test-instructions $ npx degit eai-org/agent-toolkit/skills/execute-plan-tasks .claude/skills/execute-plan-tasks $ npx degit eai-org/agent-toolkit/skills/explain-in-simple-language .claude/skills/explain-in-simple-language $ npx degit eai-org/agent-toolkit/skills/fetch-pr-review .claude/skills/fetch-pr-review $ npx degit eai-org/agent-toolkit/skills/fetch-ticket .claude/skills/fetch-ticket $ npx degit eai-org/agent-toolkit/skills/fresh-eyes-review .claude/skills/fresh-eyes-review $ npx degit eai-org/agent-toolkit/skills/grill-me .claude/skills/grill-me $ npx degit eai-org/agent-toolkit/skills/handover .claude/skills/handover $ npx degit eai-org/agent-toolkit/skills/harden-artifact .claude/skills/harden-artifact $ npx degit eai-org/agent-toolkit/skills/maintainer-review .claude/skills/maintainer-review $ npx degit eai-org/agent-toolkit/skills/memory-doctor .claude/skills/memory-doctor $ npx degit eai-org/agent-toolkit/skills/prepare-prompt .claude/skills/prepare-prompt $ npx degit eai-org/agent-toolkit/skills/refine-pr-review .claude/skills/refine-pr-review $ npx degit eai-org/agent-toolkit/skills/refine-ticket .claude/skills/refine-ticket $ npx degit eai-org/agent-toolkit/skills/review-code-assistant .claude/skills/review-code-assistant $ npx degit eai-org/agent-toolkit/skills/review-ticket .claude/skills/review-ticket $ npx degit eai-org/agent-toolkit/skills/run-nx-checks .claude/skills/run-nx-checks $ npx degit eai-org/agent-toolkit/skills/self-improve .claude/skills/self-improve $ npx degit eai-org/agent-toolkit/skills/self-review .claude/skills/self-review $ npx degit eai-org/agent-toolkit/skills/split-plan-tasks .claude/skills/split-plan-tasks $ npx degit eai-org/agent-toolkit/skills/use-conversational-language .claude/skills/use-conversational-language $ npx degit eai-org/agent-toolkit/skills/verify-understanding .claude/skills/verify-understanding
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 (29)
agentify-projectattach-to-ticketcheck-ticket-implementationcompact-docs-writercompact-skill-creatorcontext-checkupcreate-implementation-plancreate-manual-test-instructionsexecute-plan-tasksexplain-in-simple-languagefetch-pr-reviewfetch-ticketfresh-eyes-reviewgrill-mehandoverharden-artifactmaintainer-reviewmemory-doctorprepare-promptrefine-pr-reviewrefine-ticketreview-code-assistantreview-ticketrun-nx-checksself-improveself-reviewsplit-plan-tasksuse-conversational-languageverify-understanding
Similar rigs
Graite0x/amp
amp up your Claude Code setup — the harness pattern in one command
Pragmatist 1.1k tok ·
pawelgrzybek/dotfiles
—
Minimalist 307 tok ·
G-Eskayo/marvin
Open-source memory, routing, and skills layer for Claude Code — persistent memory, 27 skills, autonomous background agents, and a self-measuring bench
Skill Collector 3.9k tok ·
rastasheep/dotfiles
dotfiles by @rastasheep
Minimalist 1.8k tok ·