Shire31/agent-eval-ops-coach
Portable Codex skill for Langfuse eval ops, experiment runs, attribution, and evidence-backed agent iteration
Portable Codex skill for Langfuse eval ops, experiment runs, attribution, and evidence-backed agent iteration
npx skills add Shire31/agent-eval-ops-coachPortable Codex skill for Langfuse eval ops, experiment runs, attribution, and evidence-backed agent iteration
A CLI for Ralph + Beads-style development with harnesses like Claude Code and Codex
Map, inspect, and audit AI-agent markdown ecosystems (skills, agents, commands, hooks) as a graph.
Local, free LLM API backend (ollama-backed): OpenAI-compatible endpoint + agents with persistent memory & directives, model management, optional auth, and a web client.
SDK libraries for Modal
The Civic Coherence Lens — a four-dimension reading frame for civic-AI tools, from Divergent Kind. A Claude Skill.
Recently updated AI agent skill repository: vrbegft/codex-skill-test