Cc-skills status

Show current loop state. TRIGGERS - ru status, loop status, autonomous status, check ru state.

install
source · Clone the upstream repo
git clone https://github.com/terrylica/cc-skills
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/terrylica/cc-skills "$T" && mkdir -p ~/.claude/skills && cp -r "$T/plugins/ru/skills/status" ~/.claude/skills/terrylica-cc-skills-status && rm -rf "$T"
manifest: plugins/ru/skills/status/SKILL.md
source content

RU: Status

Self-Evolving Skill: This skill improves through use. If instructions are wrong, parameters drifted, or a workaround was needed — fix this file immediately, don't defer. Only update for real, reproducible issues.

/usr/bin/env bash << 'RALPH_UNIVERSAL_STATUS'
PROJECT_DIR="${CLAUDE_PROJECT_DIR:-$(pwd)}"

echo "========================================"
echo "  RALPH UNIVERSAL STATUS"
echo "========================================"
echo ""

STATE_FILE="$PROJECT_DIR/.claude/ru-state.json"
CONFIG_FILE="$PROJECT_DIR/.claude/ru-config.json"

if [[ ! -f "$STATE_FILE" ]]; then
    echo "State: NOT STARTED"
    echo "       Run /ru:start to begin"
    exit 0
fi

STATE=$(jq -r '.state // "unknown"' "$STATE_FILE" 2>/dev/null || echo "unknown")
echo "State: $STATE"
echo "Project: $PROJECT_DIR"

if [[ -f "$CONFIG_FILE" ]]; then
    echo ""
    echo "Configuration:"
    jq -r '.loop_limits | "  Time: \(.min_hours)h - \(.max_hours)h\n  Iterations: \(.min_iterations) - \(.max_iterations)"' "$CONFIG_FILE" 2>/dev/null || echo "  (unable to read config)"
fi

if [[ -f "$PROJECT_DIR/.claude/ru-start-timestamp" ]]; then
    START_TS=$(cat "$PROJECT_DIR/.claude/ru-start-timestamp")
    NOW_TS=$(date +%s)
    ELAPSED_SECS=$((NOW_TS - START_TS))
    ELAPSED_MINS=$((ELAPSED_SECS / 60))
    echo ""
    echo "Elapsed: ${ELAPSED_MINS} minutes"
fi
RALPH_UNIVERSAL_STATUS

Self-Evolving Skill: This skill improves through use. If instructions are wrong, parameters drifted, or a workaround was needed — fix this file immediately, don't defer. Only update for real, reproducible issues.

Examples

# Check if loop is running
/ru:status

# Quick check from terminal
cat .claude/ru-state.json 2>/dev/null | jq -r '.state' || echo "not started"

Troubleshooting

IssueCauseSolution
NOT STARTEDLoop never initializedRun
/ru:start
State: unknownCorrupted state fileDelete
.claude/ru-state.json
No configurationConfig file missingRun
/ru:wizard
for guided setup
jq not foundjq not installed
brew install jq

Post-Execution Reflection

After this skill completes, check before closing:

  1. Did the command succeed? — If not, fix the instruction or error table that caused the failure.
  2. Did parameters or output change? — If the underlying tool's interface drifted, update Usage examples and Parameters table to match.
  3. Was a workaround needed? — If you had to improvise (different flags, extra steps), update this SKILL.md so the next invocation doesn't need the same workaround.

Only update if the issue is real and reproducible — not speculative.