Agent skill
ralph-resume
Resume a PAUSED Ralph session — retry failed task, skip, or abort
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/ralph-resume
SKILL.md
Ralph Resume
Resume a Ralph autonomous execution session that was paused by the circuit breaker.
Pre-Flight
-
Check for active session:
bashif [[ ! -d ".ralph-session" ]]; then echo "No Ralph session found. Nothing to resume." exit fi -
Read circuit breaker state:
bash.claude/hooks/circuit-breaker.sh status -
Show session summary:
bashpython3 -c " import json cb = json.load(open('.ralph-session/circuit-breaker.json')) print(f\"Session state: {cb.get('state')}\") print(f\"Pause reason: {cb.get('pause_reason', 'none')}\") print(f\"Tasks completed: {cb.get('tasks_completed', 0)}\") print(f\"Total iterations: {cb.get('total_iterations', 0)}\") print(f\"Consecutive failures: {cb.get('consecutive_failures', 0)}\") " -
Identify the failed/current task: Check beads for tasks still in
in_progressstatus.
Present Options
Ask the user:
- Retry — Reset circuit breaker to RUNNING, re-dispatch the failed task
- Skip — Mark the failed task as blocked with reason, move to next task
- Abort — Clean up session, leave remaining tasks as pending
Execute Choice
Option 1: Retry
.claude/hooks/circuit-breaker.sh clear-degraded # or reset if PAUSED
.claude/hooks/circuit-breaker.sh reset
Then re-enter the ralph-execute loop from the current task.
Option 2: Skip
bd update <task-id> -s blocked --append-notes "Skipped during Ralph resume — failed after max attempts"
.claude/hooks/circuit-breaker.sh reset
Then continue ralph-execute with bd ready --parent <epic-id>.
Option 3: Abort
rm -rf .ralph-session
curl -s -X POST "https://ntfy.sh/property-tracker-claude" \
-d "Ralph session aborted by user" -H "Title: Ralph Aborted"
Integration
This skill is suggested by session-start.sh when it detects an active Ralph session.
After choosing retry or skip, invoke /ralph-execute <epic-id> to continue the loop.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?