Generative Media Skills
Curated skill collection wrapping eachlabs API—useful but not novel.
Seren Skills
The repo nails a simple, explicit contract for third‑party skills: YAML frontmatter, a clear slug scheme, and runtime support for Python/Node/bash plus docs-only guides. That makes it easy to publish small autonomous bots or API integrations, but it's still a niche ecosystem — discoverability, vetting, and runtime security are the obvious next problems this project needs to tackle.
AI agent developers, Seren Desktop users, automation/tooling-focused developers and power users
Curated skill collection wrapping eachlabs API—useful but not novel.
Switch between Claude, GPT, and local models mid-conversation in one CLI.
Security-scanned SKILL.md marketplace when GitHub repos have no vetting.
Agent firewall with 16+ injection patterns, sandboxed skill scanning, detects real OpenClaw CVE exposure.
Catches malicious skills before they steal your AWS keys or pipe data exfiltration.
This repo actually wires an OpenCode agent to Membrane so the agent can find existing connectors and synthesize missing ones on the fly — intent becomes action, not just a toy prompt example. It ships a runnable Next.js UI and clear quick-start steps, which makes the idea tangible fast; what I'd like to see next are security notes, more examples of complex connector synthesis, and tests that prove the approach scales beyond demos.