2957 posts
Universal E2E & manual acceptance testing skills for Claude Code — every run writes a protocol
Brainstorm game design with AI; hand the output to another AI to build directly — with deterministic consistency checkers.
Claude Code pack for Instagram & Facebook content creators: FTC/Meta disclosure, copyright, brand-safety & no-fabricated-stats guardrails +...
Agent skill and reference runtime for maintaining a git-backed business ontology: source intake, review gates, evals, and MCP/GBrain boundar...
Compliance guardrails, skills, loops & review agents for US residential real estate agents on Claude Code (Fair Housing + fact-accuracy). No...
Creating, writing, or scaffolding a SquadJS plugin, adding a server-side feature to a Squad server via SquadJS, or deciding whether SquadJS...
What happens when a ponytail goes the other way? The manbun takes over.
Email-sending capability for AI agents (ships as a Claude Code skill) and humans. Gmail sending runs server-side via Apps Script: idempotent...
Guardrails, skills, loops, hooks & review agents for database + website builders on Claude Code (Next.js + Supabase).
Evidence-first engineering guardrails for coding agents: audit instructions, review change scope, record execution proof, and explain reposi...
Predictive permissioning and approval ledgers for Codex, Claude Code, and coding agents
Open-source agent skill: scout product growth opportunities before you write code
