anchor-inference/daedalus
A personal, self-developing AI agent you run yourself: its own app window on macOS, Linux and Windows, a web app on your phone, Telegram if you want it. Real tools (shell, browser, git, MCP), projects with an orchestrated team, and changes
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 anchor-inference/daedalus/skills ./rig-daedalus/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 anchor-inference/daedalus/skills/accessibility .claude/skills/accessibility $ npx degit anchor-inference/daedalus/skills/animation-systems .claude/skills/animation-systems $ npx degit anchor-inference/daedalus/skills/audit-ai-design-slop .claude/skills/audit-ai-design-slop $ npx degit anchor-inference/daedalus/skills/calendar .claude/skills/calendar $ npx degit anchor-inference/daedalus/skills/canvas-design .claude/skills/canvas-design $ npx degit anchor-inference/daedalus/skills/composition-patterns .claude/skills/composition-patterns $ npx degit anchor-inference/daedalus/skills/core-web-vitals .claude/skills/core-web-vitals $ npx degit anchor-inference/daedalus/skills/excalidraw .claude/skills/excalidraw $ npx degit anchor-inference/daedalus/skills/figures .claude/skills/figures $ npx degit anchor-inference/daedalus/skills/frontend-design .claude/skills/frontend-design $ npx degit anchor-inference/daedalus/skills/gsap .claude/skills/gsap $ npx degit anchor-inference/daedalus/skills/html-artifacts .claude/skills/html-artifacts $ npx degit anchor-inference/daedalus/skills/iterate-until-verified .claude/skills/iterate-until-verified $ npx degit anchor-inference/daedalus/skills/landing-page .claude/skills/landing-page $ npx degit anchor-inference/daedalus/skills/mcp .claude/skills/mcp $ npx degit anchor-inference/daedalus/skills/no-ai-design-slop .claude/skills/no-ai-design-slop $ npx degit anchor-inference/daedalus/skills/pricing-page .claude/skills/pricing-page $ npx degit anchor-inference/daedalus/skills/progressive-blur .claude/skills/progressive-blur $ npx degit anchor-inference/daedalus/skills/react-best-practices .claude/skills/react-best-practices $ npx degit anchor-inference/daedalus/skills/research-sources .claude/skills/research-sources $ npx degit anchor-inference/daedalus/skills/scheduling .claude/skills/scheduling $ npx degit anchor-inference/daedalus/skills/self-develop .claude/skills/self-develop $ npx degit anchor-inference/daedalus/skills/skill-authoring .claude/skills/skill-authoring $ npx degit anchor-inference/daedalus/skills/tailwindcss .claude/skills/tailwindcss $ npx degit anchor-inference/daedalus/skills/telegram-output .claude/skills/telegram-output $ npx degit anchor-inference/daedalus/skills/theme-factory .claude/skills/theme-factory $ npx degit anchor-inference/daedalus/skills/threejs .claude/skills/threejs $ npx degit anchor-inference/daedalus/skills/variants .claude/skills/variants $ npx degit anchor-inference/daedalus/skills/web-artifacts-builder .claude/skills/web-artifacts-builder $ npx degit anchor-inference/daedalus/skills/web-design-guidelines .claude/skills/web-design-guidelines $ npx degit anchor-inference/daedalus/skills/web-design-reviewer .claude/skills/web-design-reviewer $ npx degit anchor-inference/daedalus/skills/web-quality-audit .claude/skills/web-quality-audit $ npx degit anchor-inference/daedalus/skills/webapp-testing .claude/skills/webapp-testing $ npx degit anchor-inference/daedalus/skills/websearch .claude/skills/websearch $ npx degit anchor-inference/daedalus/skills/writing-error-messages .claude/skills/writing-error-messages $ npx degit anchor-inference/daedalus/skills/writing .claude/skills/writing
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 (36)
accessibilityanimation-systemsaudit-ai-design-slopcalendarcanvas-designcomposition-patternscore-web-vitalsexcalidrawfiguresfrontend-designgsaphtml-artifactsiterate-until-verifiedlanding-pagemcpno-ai-design-sloppricing-pageprogressive-blurreact-best-practicesresearch-sourcesschedulingself-developskill-authoringtailwindcsstelegram-outputtheme-factorythreejsvariantsweb-artifacts-builderweb-design-guidelinesweb-design-reviewerweb-quality-auditwebapp-testingwebsearchwriting-error-messageswriting
Similar rigs
RodrigoTomeES/getmcp
One command. Every AI app. Install and configure MCP servers across 19 applications - from Claude Desktop to VS Code to Cursor. 3k+ servers ready, with automatic config generation for JSON, JSONC, YAML, and TOML.
Skill Collector 3.7k tok ·
LeastBit/Claude_skills_zh-CN
Anthropics/skills中文学习版本 来自：https://github.com/anthropics/skills
Skill Collector 608 tok ·
HAR5HA-7663/My_Claude_Setup
Full export of my Claude Code setup — settings, skills, agents, hooks, statusline, plugins, MCP configs + agent install instructions
Skill Collector 7.5k tok ·
anthropics/skills
Public repository for Agent Skills
Skill Collector 1.3k tok ·