Experiment Dashboard Viewer

/ar:ar-status — Experiment Dashboard

by alirezarezvani · MIT license · ★ 26,349 on GitHub · updated Aug 30

Show experiment dashboard with results, active loops, and progress. Use when the user runs /ar:ar-status or asks how an autoresearch experiment is going.

---
name: "ar-status"
description: "Show experiment dashboard with results, active loops, and progress. Use when the user runs /ar:ar-status or asks how an autoresearch experiment is going."
command: /ar:ar-status
---

# /ar:ar-status — Experiment Dashboard

Show experiment results, active loops, and progress across all experiments.

## Usage

```
/ar:ar-status                                  # Full dashboard
/ar:ar-status engineering/api-speed            # Single experiment detail
/ar:ar-status --domain engineering             # All experiments in a domain
/ar:ar-status --format markdown                # Export as markdown
/ar:ar-status --format csv --output results.csv  # Export as CSV

Overview

Show experiment results, active loops, and progress across all experiments.

Manual install (npx, ZIP)

Claude Codenpx skills add alirezarezvani/claude-skills --skill ar-status -g -a claude-code

Claude Code (manual)

mkdir -p ~/.claude/skills && curl -sL https://codeload.github.com/alirezarezvani/claude-skills/tar.gz/19392f7a0826 \
  | tar -xz -C ~/.claude/skills --strip-components=4 claude-skills-19392f7a0826/engineering/autoresearch-agent/skills/ar-status

Windows (PowerShell)

New-Item -ItemType Directory -Force "$HOME\.claude\skills" | Out-Null; Invoke-WebRequest "https://m.agentalley.io/zip/3709d998192069e5d788/ar-status.zip" -OutFile "$env:TEMP\ar-status.zip"; Expand-Archive "$env:TEMP\ar-status.zip" -DestinationPath "$HOME\.claude\skills" -Force

Claude.ai / desktopDownload the ZIP and upload it under Settings → Capabilities → Skills.

Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

SKILL.md1.9 KB

Read the files here

alirezarezvani/19392f71 file

SKILL.md1.9 KB

Shared references1SKILL.md reads these from elsewhere in the repo. Not in the ZIP.

log_results.pyengineering/autoresearch-agent/skills/autoresearch-agent/scripts/15.0 KB

Get them on GitHub ↗

SKILL.md

Show the full text72 lines

ar-status/SKILL.md72 lines · 1.9 KB

PreviewCode

Outline

RawView on GitHub

/ar:ar-status — Experiment Dashboard

Show experiment results, active loops, and progress across all experiments.

Usage

/ar:ar-status                                  # Full dashboard
/ar:ar-status engineering/api-speed            # Single experiment detail
/ar:ar-status --domain engineering             # All experiments in a domain
/ar:ar-status --format markdown                # Export as markdown
/ar:ar-status --format csv --output results.csv  # Export as CSV

What It Does

Single experiment

python {skill_path}/scripts/log_results.py --experiment {domain}/{name}

Also check for active loop:

cat .autoresearch/{domain}/{name}/loop.json 2>/dev/null

If loop.json exists, show:

Active loop: every {interval} (cron ID: {id}, started: {date})

Domain view

python {skill_path}/scripts/log_results.py --domain {domain}

Full dashboard

python {skill_path}/scripts/log_results.py --dashboard

For each experiment, also check for loop.json and show loop status.

Export

# CSV
python {skill_path}/scripts/log_results.py --dashboard --format csv --output {file}

# Markdown
python {skill_path}/scripts/log_results.py --dashboard --format markdown --output {file}

Output Example

DOMAIN          EXPERIMENT          RUNS  KEPT  BEST         CHANGE    STATUS   LOOP
engineering     api-speed            47    14   185ms        -76.9%    active   every 1h
engineering     bundle-size          23     8   412KB        -58.3%    paused   —
marketing       medium-ctr           31    11   8.4/10       +68.0%    active   daily
prompts         support-tone         15     6   82/100       +46.4%    done     —

1	---
2	name: "ar-status"
3	description: "Show experiment dashboard with results, active loops, and progress. Use when the user runs /ar:ar-status or asks how an autoresearch experiment is going."
4	command: /ar:ar-status
5	---
6
7	# /ar:ar-status — Experiment Dashboard
8
9	Show experiment results, active loops, and progress across all experiments.
10
11	## Usage
12
13	```
14	/ar:ar-status # Full dashboard
15	/ar:ar-status engineering/api-speed # Single experiment detail
16	/ar:ar-status --domain engineering # All experiments in a domain
17	/ar:ar-status --format markdown # Export as markdown
18	/ar:ar-status --format csv --output results.csv # Export as CSV
19	```
20
21	## What It Does
22
23	### Single experiment
24
25	```bash
26	python {skill_path}/scripts/log_results.py --experiment {domain}/{name}
27	```
28
29	Also check for active loop:
30	```bash
31	cat .autoresearch/{domain}/{name}/loop.json 2>/dev/null
32	```
33
34	If loop.json exists, show:
35	```
36	Active loop: every {interval} (cron ID: {id}, started: {date})
37	```
38
39	### Domain view
40
41	```bash
42	python {skill_path}/scripts/log_results.py --domain {domain}
43	```
44
45	### Full dashboard
46
47	```bash
48	python {skill_path}/scripts/log_results.py --dashboard
49	```
50
51	For each experiment, also check for loop.json and show loop status.
52
53	### Export
54
55	```bash
56	# CSV
57	python {skill_path}/scripts/log_results.py --dashboard --format csv --output {file}
58
59	# Markdown
60	python {skill_path}/scripts/log_results.py --dashboard --format markdown --output {file}
61	```
62
63	## Output Example
64
65	```
66	DOMAIN EXPERIMENT RUNS KEPT BEST CHANGE STATUS LOOP
67	engineering api-speed 47 14 185ms -76.9% active every 1h
68	engineering bundle-size 23 8 412KB -58.3% paused —
69	marketing medium-ctr 31 11 8.4/10 +68.0% active daily
70	prompts support-tone 15 6 82/100 +46.4% done —
71	```
72