opt-prompt-eval
CommunityRecords retro JSONL logs for prompt evaluation, ensuring traceability.
Authorhjung3113
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill enables precise recording of post-task retrospective data for normalized prompts, maintaining accountability and improving prompt workflows.
Core Features & Use Cases
- Retro Log Recording: Writes a JSONL row with detailed metrics after a prompt task completes.
- Traceability: Links retro entries to specific decision IDs and session contexts.
- Use Case: A team reviews a prompt’s performance by capturing latency and token usage after closure, facilitating continuous optimization.
Quick Start
Invoke /opt-prompt-eval <decision_id> after prompt completion to log retro data for analysis.
Dependency Matrix
Required Modules
append.shsession-stats.sh
Components
scripts
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: opt-prompt-eval Download link: https://github.com/hjung3113/vocpage/archive/main.zip#opt-prompt-eval Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.