AndyMelnykov/pm-loops
Automated PM workflows with independent maker/checker agents, persistent memory, quality gates, and human oversight.
stack: Python
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 AndyMelnykov/pm-loops/.claude ./rig-pm-loops # inspect, then merge into .claude/ 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 AndyMelnykov/pm-loops/.claude/skills/ai-quality-watchdog .claude/skills/ai-quality-watchdog $ npx degit AndyMelnykov/pm-loops/.claude/skills/competitive-brief .claude/skills/competitive-brief $ npx degit AndyMelnykov/pm-loops/.claude/skills/feedback-digest .claude/skills/feedback-digest $ npx degit AndyMelnykov/pm-loops/.claude/skills/launch-readiness .claude/skills/launch-readiness $ npx degit AndyMelnykov/pm-loops/.claude/skills/loop-builder .claude/skills/loop-builder $ npx degit AndyMelnykov/pm-loops/.claude/skills/metric-anomaly .claude/skills/metric-anomaly $ npx degit AndyMelnykov/pm-loops/.claude/skills/onboarding-friction .claude/skills/onboarding-friction $ npx degit AndyMelnykov/pm-loops/.claude/skills/product-review-hardening .claude/skills/product-review-hardening $ npx degit AndyMelnykov/pm-loops/.claude/skills/sales-deal-intelligence .claude/skills/sales-deal-intelligence $ npx degit AndyMelnykov/pm-loops/.claude/skills/spec-drift-check .claude/skills/spec-drift-check $ npx degit AndyMelnykov/pm-loops/.claude/skills/sprint-prep-sweep .claude/skills/sprint-prep-sweep $ npx degit AndyMelnykov/pm-loops/.claude/skills/stale-doc-sweep .claude/skills/stale-doc-sweep $ npx degit AndyMelnykov/pm-loops/.claude/skills/start-here .claude/skills/start-here $ npx degit AndyMelnykov/pm-loops/.claude/skills/weekly-business-review .claude/skills/weekly-business-review
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 (14)
Similar rigs
Chee-0806/ai-product-studio
AI 产品设计工位:不写代码的产品经理只对 AI 说话,PRD 与可点原型自动保持一致。AI product workspace — PRD + clickable prototype, kept in sync by agents.
Skill Collector 3.9k tok · · Q0
CorvusWing/CorvusWing
A deterministic process around a probabilistic model.
Skill Collector 1.4k tok · · Q0
AIDevGTM/gtm-cofounder
#1 Product of The Day @ Product Hunt. The GTM co-founder you don't have. Open-source GTM Agent Skills for developer tools and AI products, for founders, GTM hires, and founding AEs: positioning, first users, launch, pricing. Sharpened by Fr
Skill Collector 3.5k tok · · Q3
mannobeats/hyper-taste
Agent skills with taste: interfaces nobody can tell were made by AI, and AGENTS.md kept in sync for every agent.
Skill Collector 1.8k tok · · Q0