open-gsd/gsd-pi
A powerful meta-prompting, context engineering and spec-driven development system that enables agents to work for long periods of time autonomously without losing track of the big picture
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
$ git clone --depth 1 https://github.com/open-gsd/gsd-pi 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 open-gsd/gsd-pi/src/resources/extensions/gsd/skills/gsd-headless .claude/skills/gsd-headless $ npx degit open-gsd/gsd-pi/src/resources/skills/accessibility .claude/skills/accessibility $ npx degit open-gsd/gsd-pi/src/resources/skills/agent-browser .claude/skills/agent-browser $ npx degit open-gsd/gsd-pi/src/resources/skills/api-design .claude/skills/api-design $ npx degit open-gsd/gsd-pi/src/resources/skills/best-practices .claude/skills/best-practices $ npx degit open-gsd/gsd-pi/src/resources/skills/btw .claude/skills/btw $ npx degit open-gsd/gsd-pi/src/resources/skills/code-optimizer .claude/skills/code-optimizer $ npx degit open-gsd/gsd-pi/src/resources/skills/core-web-vitals .claude/skills/core-web-vitals $ npx degit open-gsd/gsd-pi/src/resources/skills/create-gsd-extension .claude/skills/create-gsd-extension $ npx degit open-gsd/gsd-pi/src/resources/skills/create-mcp-server .claude/skills/create-mcp-server $ npx degit open-gsd/gsd-pi/src/resources/skills/create-skill .claude/skills/create-skill $ npx degit open-gsd/gsd-pi/src/resources/skills/create-workflow .claude/skills/create-workflow $ npx degit open-gsd/gsd-pi/src/resources/skills/debug-like-expert .claude/skills/debug-like-expert $ npx degit open-gsd/gsd-pi/src/resources/skills/decompose-into-slices .claude/skills/decompose-into-slices $ npx degit open-gsd/gsd-pi/src/resources/skills/dependency-upgrade .claude/skills/dependency-upgrade $ npx degit open-gsd/gsd-pi/src/resources/skills/design-an-interface .claude/skills/design-an-interface $ npx degit open-gsd/gsd-pi/src/resources/skills/forensics .claude/skills/forensics $ npx degit open-gsd/gsd-pi/src/resources/skills/frontend-design .claude/skills/frontend-design $ npx degit open-gsd/gsd-pi/src/resources/skills/github-workflows .claude/skills/github-workflows $ npx degit open-gsd/gsd-pi/src/resources/skills/grill-me .claude/skills/grill-me $ npx degit open-gsd/gsd-pi/src/resources/skills/handoff .claude/skills/handoff $ npx degit open-gsd/gsd-pi/src/resources/skills/lint .claude/skills/lint $ npx degit open-gsd/gsd-pi/src/resources/skills/make-interfaces-feel-better .claude/skills/make-interfaces-feel-better $ npx degit open-gsd/gsd-pi/src/resources/skills/observability .claude/skills/observability $ npx degit open-gsd/gsd-pi/src/resources/skills/react-best-practices .claude/skills/react-best-practices $ npx degit open-gsd/gsd-pi/src/resources/skills/review .claude/skills/review $ npx degit open-gsd/gsd-pi/src/resources/skills/security-review .claude/skills/security-review $ npx degit open-gsd/gsd-pi/src/resources/skills/spike-wrap-up .claude/skills/spike-wrap-up $ npx degit open-gsd/gsd-pi/src/resources/skills/tdd .claude/skills/tdd $ npx degit open-gsd/gsd-pi/src/resources/skills/userinterface-wiki .claude/skills/userinterface-wiki $ npx degit open-gsd/gsd-pi/src/resources/skills/verify-before-complete .claude/skills/verify-before-complete $ npx degit open-gsd/gsd-pi/src/resources/skills/web-design-guidelines .claude/skills/web-design-guidelines $ npx degit open-gsd/gsd-pi/src/resources/skills/web-quality-audit .claude/skills/web-quality-audit $ npx degit open-gsd/gsd-pi/src/resources/skills/write-docs .claude/skills/write-docs $ npx degit open-gsd/gsd-pi/src/resources/skills/write-milestone-brief .claude/skills/write-milestone-brief
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 (35)
gsd-headlessaccessibilityagent-browserapi-designbest-practicesbtwcode-optimizercore-web-vitalscreate-gsd-extensioncreate-mcp-servercreate-skillcreate-workflowdebug-like-expertdecompose-into-slicesdependency-upgradedesign-an-interfaceforensicsfrontend-designgithub-workflowsgrill-mehandofflintmake-interfaces-feel-betterobservabilityreact-best-practicesreviewsecurity-reviewspike-wrap-uptdduserinterface-wikiverify-before-completeweb-design-guidelinesweb-quality-auditwrite-docswrite-milestone-brief
Similar rigs
gsd-build/gsd-2
A powerful meta-prompting, context engineering and spec-driven development system that enables agents to work for long periods of time autonomously without losing track of the big picture
Skill Collector 5.0k tok ·
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 ·
charly3pins/dotfiles
My personal dotfiles
Skill Collector 1.4k tok ·
addyosmani/web-quality-skills
Agent Skills for optimizing web quality based on Lighthouse and Core Web Vitals.
Pragmatist 1.9k tok ·