Prompt Governance
插件 已验证 活跃Use when managing prompts in production at scale: versioning prompts, running A/B tests on prompts, building prompt registries, preventing prompt regressions, or creating eval pipelines for production
To enable teams to manage prompts with the same rigor as code, ensuring quality, preventing regressions, and facilitating safe iteration in production AI features.
功能
- Design and implement prompt registries
- Build automated prompt evaluation pipelines
- Establish governed iteration workflows
- Implement A/B testing for prompts
- Provide rollback capabilities for prompt changes
使用场景
- Managing prompts in production at scale
- Versioning prompts and preventing regressions
- Running A/B tests on production prompts
- Building prompt registries and eval pipelines for AI features
非目标
- Writing or improving individual prompts
- Designing RAG pipelines
- LLM cost reduction
安装
/plugin install prompt-governance@alirezarezvani-claude-skills质量评分
已验证类似扩展
Review Agent Governance
99Require a human approval signal before an AI agent can post PR reviews, comments, merges, or writes to CI config. Cedar-gated, receipt-signed, designed for the Hermes-style failure mode where a review bot posts without oversight.
Accessibility Compliance
99WCAG accessibility auditing, compliance validation, UI testing for screen readers, keyboard navigation, and inclusive design
Huggingface Trackio
99Track and visualize ML training experiments with Trackio. Log metrics via Python API and retrieve them via CLI. Supports real-time dashboards synced to HF Spaces.
Hf Cli
99Execute Hugging Face Hub operations using the hf CLI. Download models/datasets, upload files, manage repos, and run cloud compute jobs.
Huggingface Llm Trainer
99Train or fine-tune language models using TRL on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes hardware selection, cost estimation, Trackio monitoring, and Hub persistence.
Claude Cost Optimizer
99Claude Code 的成本优化模式。通过简洁的响应、模型路由和高效的工作流模式，可节省 30-60% 的成本。