evening-review

Generate an end-of-day recap and overnight task proposals for approval.

88|108|Updated Apr 7, 2026

Search Tags:#workflow automation #agent orchestration #task planning #self-evaluation #daily recap #telegram approvals #overnight mode

Ready to run

npx skills add https://github.com/grandamenium/cortextos --skill evening-review-grandamenium

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: evening-review
Source: https://github.com/grandamenium/cortextos/tree/main/templates/orchestrator/.claude/skills/evening-review
Command: npx skills add https://github.com/grandamenium/cortextos --skill evening-review-grandamenium

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It turns a busy day of multi-agent work into a clear, user-reviewable end-of-day recap, including what succeeded, what’s blocked, and what should happen overnight.

Core Features & Use Cases

Day summary across all agents: Collects completed and in-progress tasks, key outputs, heartbeats, and check-in inbox items to produce a consolidated daily report.
Orchestrator self-evaluation and system improvement proposals: Rates performance across usefulness, proactivity, coordination, communication, and learning, then generates 3-5 actionable proposals to fix bottlenecks or automate slow steps.
Tomorrow prep plus overnight task proposals with approval: Reviews tomorrow’s calendar needs, dispatches prep tasks to agents, and proposes autonomous overnight work following nighttime-mode guardrails with a user approval flow.

Quick Start

Ask your system to run the evening review workflow to generate a day summary, propose overnight work, and request your approval.

Frequently Asked Questions about evening-review

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I generate an end-of-day recap for a multi-agent system?▼

To generate an end-of-day recap for a multi-agent system, trigger a daily cron-driven workflow that aggregates completed tasks, heartbeats, and inbox items into a consolidated daily report. This process also evaluates agent performance and proposes overnight work.

What is orchestrator self-evaluation in agent orchestration?▼

Orchestrator self-evaluation in agent orchestration is a process that rates multi-agent performance across usefulness, proactivity, coordination, communication, and learning. It generates actionable proposals to fix bottlenecks or automate slow steps within the system.

How do I dispatch overnight tasks with user approval in a PTY-based agent fleet?▼

To dispatch overnight tasks with user approval in a PTY-based agent fleet, the system proposes autonomous overnight work following nighttime-mode guardrails. It uses a Telegram approval flow to ensure dispatch behavior is strictly approval-only before executing tasks.

Can I use telegram approvals for task planning in autonomous agent workflows?▼

Yes, you can use Telegram approvals for task planning in autonomous agent workflows. The system integrates a user approval flow to review proposed overnight work, ensuring that task dispatch behavior strictly requires your explicit approval before execution.

Does the daily recap workflow persist memory updates across all agents?▼

Yes, the daily recap workflow persists memory updates across all agents. It reads identity, goals, and nighttime-mode constraints, aggregates the bus state including tasks and heartbeats, and saves memory updates during the end-of-day recap generation.

When should I enforce nighttime-mode constraints for task dispatch planning?▼

You should enforce nighttime-mode constraints for task dispatch planning when proposing autonomous overnight work. This ensures that all dispatched prep tasks for tomorrow follow strict guardrails and operate safely under an approval-only behavior model.