skills.rest
alirezarezvani
alirezarezvaniCOMMUNITY
Explore all skills by this author →
Website𝕏@RezaRezvaniBlnGitHub

ar-status

Displays autoresearch experiment dashboards with results, active loops, and progress metrics.

25.3k|3.6k|Updated Oct 19, 2025
Search Tags:#Dashboard#status monitoring#csv export#AutoResearch#Experiment Tracking#optimization loops
One-click install
npx skills add https://github.com/alirezarezvani/claude-skills --skill ar-status
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ar-status
Source: https://github.com/alirezarezvani/claude-skills/tree/main/engineering/autoresearch-agent/skills/ar-status
Command: npx skills add https://github.com/alirezarezvani/claude-skills --skill ar-status

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Tracking the progress of multiple autoresearch experiments across domains is difficult when results, run counts, and active loops are scattered across files. This Skill consolidates experiment status into a single dashboard view.

Core Features & Use Cases

  • Full Dashboard: Shows all experiments with run counts, kept results, best metrics, percentage changes, and status in a tabular view.
  • Single Experiment Detail: Inspects one experiment by domain and name, including any active loop configuration from loop.json.
  • Export Options: Exports dashboard data as CSV or Markdown files for reporting and sharing.
  • Use Case: A researcher running optimization loops on API latency and bundle size runs /ar:ar-status to see which experiments are active, their best results, and whether scheduled loops are still running.

Quick Start

Ask the assistant to show the autoresearch experiment dashboard, or run /ar:ar-status with an optional domain or experiment name.

Frequently Asked Questions about ar-status

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I check the status of an autoresearch experiment?▼

Run /ar:ar-status followed by the experiment path, such as engineering/api-speed, to see a single experiment's results. The skill runs log_results.py with the experiment flag and also checks for an active loop.json file.

How do I export experiment results to CSV?▼

Use /ar:ar-status with the --format csv and --output flags, for example /ar:ar-status --format csv --output results.csv. This invokes log_results.py with the dashboard, format, and output arguments to write the file.

Can I view experiments for only one domain?▼

Yes, pass the --domain flag, such as /ar:ar-status --domain engineering, to list all experiments within that domain. The skill runs log_results.py with the corresponding domain argument.

How do I know if an experiment loop is still running?▼

The skill checks for a loop.json file under .autoresearch/{domain}/{name}/ for each experiment. If it exists, the dashboard shows the loop interval, cron ID, and start date alongside the experiment status.

What metrics does the experiment dashboard show?▼

The dashboard shows run count, kept results, best metric value, percentage change, status, and loop schedule per experiment. Data is grouped by domain in a tabular text format.

Related Skills

Explore More Software Engineering Skills→
Patasse97Patasse97

loop

Schedule and execute autonomous experiment loops at user-defined intervals.

Community
Advanced
Mr-Fang-VLSIMr-Fang-VLSI
8

eda-retro

Score improvement proposals and emit retro artifacts with stop and promotion criteria.

Community
Advanced
RogerGimbelRogerGimbel

onboarding-cro

Optimize post-signup onboarding flows to increase user activation.

Community
Advanced
ClaudioCeppi83ClaudioCeppi83

spotify-player

Control Spotify playback and search tracks from the terminal.

Community
Intermediate