Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →majiayu000/auto
Autonomous AI coding loop (Ralph Wiggum methodology).
Passed 15 of 18 test cases with the skill, and 9 of 18 without it.
and 6 more in the full report
9 fixed9 passed either way2 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
During continuous autonomous execution, after how many completed tasks should git commits be created and the `/compact` command recommended?
| Checked | Without skill | With skill |
|---|---|---|
| Triggers git commits and compact recommendations after every 3 completed tasks. | Missed | Passed |
The instructions your model reads when the skill loads.
Fully autonomous development. Works through all tasks without stopping until complete.
!git status --short
!node -e "try{const p=require('./prd.json');const sp=p.sprints?p.sprints[p.sprints.length-1]:p;const s=Object.values(sp.stories||p.stories||{});const name=sp.id||sp.name||p.sprint||'unknown';const done=s.filter(x=>x.passes===true).length;const pend=s.filter(x=>x.passes===null||x.passes===false).length;console.log('Sprint:',name,'| Done:',done,'| Pending:',pend,'| Total:',s.length)}catch(e){console.log('No prd.json')}"
auto
|-- Activate: write .claude/auto-active
|-- Check prd.json exists?
| |-- No -> Bootstrap from context
| +-- Yes -> Check pending tasks
| |-- None pending -> IDLE Detection
| +-- Has pending -> Execute tasks
|
+-- Execute until done or interrupted
+-- Deactivate: delete .claude/auto-active
On start, create the flag file:
echo '{"started":"'$(date -Iseconds)'","sprint":"current"}' > .claude/auto-active
PowerShell: @{started=(Get-Date -Format o)} | ConvertTo-Json > .claude/auto-active
This flag tells the Stop hook to block Claude from stopping. Claude keeps working as long as this flag exists.
On exit (user says "done", or nothing left), delete the flag:
rm -f .claude/auto-active
Delete the flag when auto mode ends. If asking the user what's next (IDLE Detection), keep the flag active.
test cases passed, vs 9 / 18 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.