review-lessons

Reviews all LessonsLearned.GLOBAL.md files and produces per-skill and global recommendations.

1|Updated Apr 14, 2026
One-click install
npx skills add https://github.com/bhanford9/vs-code-copilot-tools --skill review-lessons-bhanford9
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: review-lessons
Source: https://github.com/bhanford9/vs-code-copilot-tools/tree/main/skills/review-lessons
Command: npx skills add https://github.com/bhanford9/vs-code-copilot-tools --skill review-lessons-bhanford9

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Aggregates, analyzes, and escalates actionable LessonsLearned entries by scanning every LessonsLearned.GLOBAL.md file across skills, applying escalation criteria to surface items that require further attention or promotion.

Core Features & Use Cases

  • Parallel subagent evaluation: spawns workers to assess each global lesson file against standardized criteria.
  • Global escalation pipeline: uses the lessons-learned criteria to classify findings as Promote, Hook, Stale, or OK.
  • Unified reporting: produces per-skill tables and a consolidated action plan to guide maintenance workflows.

Quick Start

Run the review-lessons workflow to generate escalation recommendations from all LessonsLearned.GLOBAL.md files.

Frequently Asked Questions about review-lessons

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

FAQPage Schema
How do I automate escalation reviews for lessons learned across multiple skills?

Automate escalation reviews by spawning parallel subagents to scan all LessonsLearned.GLOBAL.md files, classify actionable entries against standardized criteria, and output consolidated maintenance recommendations.

What is the best way to classify stale or actionable entries in a global lessons learned file?

Classify entries in a global lessons learned file by applying standardized escalation criteria to sort findings into Promote, Hook, Stale, or OK categories for maintenance prioritization.

How does parallel subagent evaluation work for maintenance workflows?

Parallel subagent evaluation works by spawning concurrent workers that assess each global lesson file independently against standardized criteria, then aggregating results into a unified per-skill action plan.

Can I generate a consolidated action plan from scattered lessons learned files?

Yes, you can generate a consolidated action plan by reading all global lessons files, applying escalation criteria to surface items requiring attention, and merging per-skill tables into unified recommendations.

When do I need to run an escalation pipeline for quality assurance feedback loops?

Run an escalation pipeline during periodic maintenance reviews of the feedback loop when you need to surface actionable entries from global lessons files and determine their handling across all skills.

Does this workflow require any dependencies to process global lessons files?

No, this workflow operates dependency-free, reading all global lessons files directly and consulting internal lessons-learned criteria to evaluate entries without requiring external components or modules.