Experimental Claude routing advice, prompt authoring and prompt review using shared model profiles. Separates placement from capability, preserves selected tiers in handoffs, and checks profile consistency. Routing quality, savings and Codex compatibility are not established.
USE AT YOUR OWN RISK — Felipe Blassioli's personal sandbox plugin. Experimental skills: GCP observability (Cloud Error Reporting triage by blast radius, Cloud Logging noise triage, and error → trace → offending-code root-cause) and skill authoring (rewrite a rigid skill in the cursor-team-kit register beside the…
Release governance for the agent-skills marketplace: versioning, validating, releasing, and promoting plugins and skills (marketplace.json / plugin.json / registry alignment). For maintainers, not app developers. Skill authoring and auditing live in the skill-studio plugin.
Author, audit, and enhance Claude Code skills and plugins. A best-practice toolkit: create skills from scratch or adapt external sources (skill-create), audit skills for quality, context-efficiency, and portfolio overlap (skill-audit), and improve them with an eval/benchmark loop (skill-enhance). Bundles helper…
★not rated 2 1mo agoA
tokens not measured
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: