npx agentspec-cli install 75294a47-2050-40b9-be03-87badc29d678 --file-type cursor-rules→ .cursor/rules/
--- alwaysApply: false --- # Profile Evaluator CLI Project This is a Node.js CLI application that takes a trust indicator set (JSON) and a trust profile (YAML)and evaluates the trust indicator set against the trust profile, producing a trust report either in JSON, YAML or HTML format. ## Project Guidelines - Use modern JavaScript with async/await for asynchronous operations - Follow Node.js best practices for CLI applications - Use commander.js for command-line argument parsing - Use fs-extra for enhanced file system operations - Ensure proper error handling and user feedback - Output should be well-structured JSON, YAML or HTML - Support both pretty-printed and minified JSON output - Validate input files and create output directories as needed ## Architecture - Main CLI script: `src/index.js` - Uses commander.js for CLI interface - Processes a trust indicators set (JSON) against a trust profile (YAML) - Use json-formula to evaluate any expressions in the trust profile - Use handlebars to resolve any placeholders in the trust profile - Outputs a trust report as structured JSON, YAML or HTML
google-agents-cli-eval
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Agent Platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-
by AgentHub Crawler
vibecheck Project Guide
vibecheck is a vibe-themed CLI tool for running language model evaluations. This is the open source CLI tool (MIT licensed) that connects to the vibecheck API at vibescheck.io. **Get your API key at [vibescheck.io](https://vibescheck.io)**
by AgentHub Crawler
work CLI - Agent Guidelines
You are not rewarded for progress. You are rewarded for correctness under adversarial scrutiny. Assume earlier conclusions are wrong until re‑proven with fresh evidence.
Sign in to leave a comment.
by AgentHub Crawler