Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Show DAG state, agent progress, and branch status for an AgentHub session. Use when the user runs /hub:status or asks how the AgentHub agents are doing.
.claude/skills/alirezarezvani-status/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 84% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -54% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 50% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -70% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -57% | 0% |
Show experiment results, active loops, and progress across all experiments.
/ar:status # Full dashboard
/ar:status engineering/api-speed # Single experiment detail
/ar:status --domain engineering # All experiments in a domain
/ar:status --format markdown # Export as markdown
/ar:status --format csv --output results.csv # Export as CSVbashpython {skill_path}/scripts/log_results.py --experiment {domain}/{name}
Also check for active loop:
bashcat .autoresearch/{domain}/{name}/loop.json 2>/dev/null
If loop.json exists, show:
Active loop: every {interval} (cron ID: {id}, started: {date})bashpython {skill_path}/scripts/log_results.py --domain {domain}
bashpython {skill_path}/scripts/log_results.py --dashboard
For each experiment, also check for loop.json and show loop status.
bash# 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}
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 —| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 4,496 | 5,337 | +19% | 1 | 1 | 0% | 792 | 1,459 | +84% | 0 | 0 | — |
case-02 | fail→pass | 8,135 | 2,422 | -70% | 1 | 1 | 0% | 1,669 | 776 | -54% | 0 | 0 | — |
case-03 | fail→pass | 5,974 | 6,308 | +6% | 1 | 1 | 0% | 1,070 | 1,603 | +50% | 0 | 0 | — |
case-04 | fail→fail | 8,625 | 5,698 | -34% | 1 | 1 | 0% | 1,586 | 1,536 | -3% | 0 | 0 | — |
case-05 | pass→pass | 9,611 | 8,916 | -7% | 1 | 1 | 0% | 2,054 | 2,237 | +9% | 0 | 0 | — |
case-06 | pass→pass | 11,347 | 8,384 | -26% | 1 | 1 | 0% | 2,167 | 1,969 | -9% | 0 | 0 | — |
case-07 | fail→pass | 14,047 | 1,754 | -88% | 1 | 1 | 0% | 2,520 | 757 | -70% | 0 | 0 | — |
case-08 | fail→pass | 12,439 | 2,502 | -80% | 1 | 1 | 0% | 2,128 | 921 | -57% | 0 | 0 | — |
case-09 | pass→pass | 6,649 | 2,571 | -61% | 1 | 1 | 0% | 1,252 | 978 | -22% | 0 | 0 | — |
case-10 | pass→pass | 6,358 | 1,802 | -72% | 1 | 1 | 0% | 1,112 | 805 | -28% | 0 | 0 | — |
case-11 | pass→pass | 6,073 | 1,450 | -76% | 1 | 1 | 0% | 1,078 | 726 | -33% | 0 | 0 | — |
case-12 | fail→pass | 9,542 | 1,611 | -83% | 1 | 1 | 0% | 1,712 | 757 | -56% | 0 | 0 | — |
case-13 | pass→pass | 3,430 | 1,641 | -52% | 1 | 1 | 0% | 555 | 754 | +36% | 0 | 0 | — |
case-14 | fail→pass | 11,763 | 1,485 | -87% | 1 | 1 | 0% | 1,878 | 714 | -62% | 0 | 0 | — |
case-15 | fail→pass | 5,297 | 1,642 | -69% | 1 | 1 | 0% | 822 | 660 | -20% | 0 | 0 | — |
case-16 | fail→pass | 8,423 | 2,075 | -75% | 1 | 1 | 0% | 1,461 | 828 | -43% | 0 | 0 | — |
case-17 | fail→pass | 7,960 | 1,870 | -77% | 1 | 1 | 0% | 1,372 | 777 | -43% | 0 | 0 | — |
case-18 | fail→pass | 12,327 | 2,033 | -84% | 1 | 1 | 0% | 2,029 | 783 | -61% | 0 | 0 | — |
case-19 | fail→pass | 10,887 | 8,688 | -20% | 1 | 1 | 0% | 2,015 | 2,076 | +3% | 0 | 0 | — |
case-20 | fail→pass | 9,423 | 2,800 | -70% | 1 | 1 | 0% | 1,711 | 1,010 | -41% | 0 | 0 | — |
case-21 | fail→fail | 5,249 | 1,453 | -72% | 1 | 1 | 0% | 927 | 706 | -24% | 0 | 0 | — |
case-22 | fail→pass | 9,381 | 2,059 | -78% | 1 | 1 | 0% | 1,670 | 906 | -46% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +64 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.