Skill570 estrellas del repoactualizado today

bernstein-alerts

Bernstein Alerts fetches and categorizes system problems by severity (critical, warning, info) using the `scripts/alerts.sh` script, displaying failed tasks, stalled agents, budget warnings, and blocked items. Use this when users ask about problems, errors, or diagnostics, providing actionable next steps like retrying failed tasks, killing stalled agents, or reviewing approvals.

Ver fuente Repositorio: bernstein

Instalar en Claude Code

Copiar

git clone --depth 1 https://github.com/sipyourdrink-ltd/bernstein /tmp/bernstein-alerts && cp -r /tmp/bernstein-alerts/packages/cursor-plugin/skills/bernstein-alerts ~/.claude/skills/bernstein-alerts

Después abre una sesión nueva de Claude Code; el skill carga automáticamente.

Definición

SKILL.md

# Bernstein Alerts

Surface problems that need attention right now.

## When to Use

- User asks "any problems?" or "what needs my attention?"
- User asks about errors, failures, or warnings
- Something seems wrong and user wants a diagnostic
- User says "is anything broken?"

## Instructions

1. Run `scripts/alerts.sh` to fetch current alerts.
2. Categorize and present by severity:

```
## Alerts

### Critical
- Task TASK-042 FAILED: "TypeError in auth middleware" - agent ses-a1b2 (backend)
  → Fix: Review the error, create a follow-up task, or retry

### Warning
- Budget at 85% ($4.25 / $5.00) - consider increasing budget or pausing low-priority tasks
- Agent ses-e5f6 stalled for 3m 20s - consider killing it with /bernstein-agents

### Info
- 2 tasks blocked, waiting for human approval - use /bernstein-approve to review
```

3. For each alert, suggest a concrete action:
   - Failed task → offer to create a retry task or inspect the error
   - Stalled agent → offer to kill it
   - Budget warning → show cost breakdown
   - Blocked task → link to approval flow

Del mismo repositorio

orchestratorSubagent

Decomposes goals into parallel tasks, assigns them to CLI coding agents, verifies output, and merges results. Use when a task is too large for a single agent.

runSlash Command

Start a Bernstein orchestration run with a goal

statusSlash Command

Show current Bernstein orchestration status

stopSlash Command

Gracefully stop a running Bernstein orchestration

bernstein-agentsSkill

bernstein-approveSkill

bernstein-costSkill

bernstein-create-taskSkill