ralph-graceful-exit

Detects Ralph Loop completion beyond <promise> tags. Use when checking if a task is complete, verifying completion status, or detecting graceful exit conditions. Implements 4-signal detection: test loops, done signals, completion indicators, and fix plan verification.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "ralph-graceful-exit" with this command: npx skills add zpankz/mcp-skillset/zpankz-mcp-skillset-ralph-graceful-exit

Ralph Graceful Exit

Purpose

Detect when a Ralph Loop iteration has truly completed its task, beyond just the <promise>DONE</promise> tag. This skill implements 4-signal detection to verify genuine completion.

Integrations

TypeReferences
hooksralph-circuit-breaker, ralph-rate-limiter, ralph-activity-log
pluginsralph-loop@claude-plugins-official

4-Signal Detection

SignalThresholdDetection Method
test_loops≥3 consecutiveOnly running tests, no code changes
done_signals≥2 occurrences"done", "complete", "finished" in output
completion_indicators≥2 patternsStrong completion language patterns
fix_plan_checkall items ✓All @fix_plan.md items checked

Detection Logic

When evaluating completion:

  1. Check activity log for test-only iterations

    grep -c "test\|pytest\|jest\|npm test" ~/.ralph-state/activity.log
    
  2. Scan recent output for done_signals patterns

    • "done", "complete", "finished", "all tests pass"
    • "implementation complete", "task finished"
  3. Look for completion_indicators in conversation

    • Strong completion language
    • Summary of what was accomplished
    • No pending TODO items mentioned
  4. Verify fix_plan if exists

    • Check if @fix_plan.md exists
    • Verify all checkbox items are checked [x]

Exit Recommendation

If ≥2 signals detected, recommend outputting:

<promise>DONE</promise>

Signal Weights

SignalWeightConfidence
fix_plan_check (all ✓)1.0High
test_loops ≥30.8High
done_signals ≥20.6Medium
completion_indicators ≥20.5Medium

Total weight ≥1.5 → Strong recommendation to exit Total weight ≥1.0 → Suggest checking completion status

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

agent-observability

No summary provided by upstream source.

Repository SourceNeeds Review
Automation

subagent-prompt-construction

No summary provided by upstream source.

Repository SourceNeeds Review
Automation

mcp_agent_mail

No summary provided by upstream source.

Repository SourceNeeds Review
Automation

agent-evaluation

No summary provided by upstream source.

Repository SourceNeeds Review