From ops
Business-level "what should I do next". Priority stack — fires > unread comms > ready-to-merge PRs > Linear sprint > revenue-generating GSD work. Uses pre-gathered data and routes to the right skill.
npx claudepluginhub auroracapital/claude-opsThis skill is limited to using the following tools:
```!
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Guides building MCP servers enabling LLMs to interact with external services via tools. Covers best practices, TypeScript/Node (MCP SDK), Python (FastMCP).
Share bugs, ideas, or general feedback.
${CLAUDE_PLUGIN_ROOT}/bin/ops-infra 2>/dev/null || echo '{"clusters":[]}'
${CLAUDE_PLUGIN_ROOT}/bin/ops-prs 2>/dev/null || echo '[]'
${CLAUDE_PLUGIN_ROOT}/bin/ops-ci 2>/dev/null || echo '[]'
${CLAUDE_PLUGIN_ROOT}/bin/ops-unread 2>/dev/null || echo '{}'
for d in $(jq -r '.projects[] | select(.gsd == true) | .paths[]' "${CLAUDE_PLUGIN_ROOT}/scripts/registry.json" 2>/dev/null); do
expanded="${d/#\~/$HOME}"
if [ -f "$expanded/.planning/STATE.md" ]; then
alias=$(basename "$expanded")
cat "$expanded/.planning/STATE.md" 2>/dev/null | head -30
echo "---NEXT---"
fi
done
Apply the priority stack to all pre-gathered data:
Check infra data for: unhealthy ECS tasks, stopped services, failed deployments.
Check CI for: broken main or dev branches.
If any fires exist → recommend /ops-fires immediately.
Check unread counts. If WhatsApp or email has unread messages from humans (not automated):
/ops-inbox [channel]Check PRs for: CI green + no unresolved review comments + not draft.
If any ready → recommend reviewing that PR now.
Check: gh pr list --state open --json number,title,statusCheckRollup,reviewDecision 2>/dev/null
Fetch current sprint issues: use mcp__claude_ai_Linear__list_cycles then mcp__claude_ai_Linear__list_issues filtered to current cycle.
Find highest-priority issue that is in progress or unstarted.
From GSD state, find the highest revenue-impact active phase across all projects. Revenue weighting: healify > other projects (subscriber revenue). Prioritize closest-to-done phases.
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
OPS ► NEXT ACTION
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
TOP PRIORITY: [fires|comms|PR|sprint|gsd]
▶ [specific action in one sentence]
WHY: [1-2 sentence rationale]
──────────────────────────────────────────────────────
Full priority stack:
1. [action] — [why] → [/skill or command]
2. [action] — [why] → [/skill or command]
3. [action] — [why] → [/skill or command]
4. [action] — [why] → [/skill or command]
5. [action] — [why] → [/skill or command]
──────────────────────────────────────────────────────
a) Do #1 now
b) Do #2 now
c) Show me everything (/ops-go)
d) I'll decide — just show the briefing
→ Pick or describe what you want
──────────────────────────────────────────────────────
Use AskUserQuestion. When user selects an option, invoke the corresponding skill directly — don't describe it, do it.
If $ARGUMENTS contains context (e.g., "focus on healify"), constrain the analysis to that context.