KS
Killer-Skills

retro — how to use retro how to use retro, retro ai agent skill, retro vs other optimization tools, retro install guide, what is retro, retro alternative, retro setup tutorial, retro efficiency optimization, retro for ai developers

v1.0.0
GitHub

About this Skill

Ideal for AI Agents like Claude, AutoGPT, or LangChain requiring efficiency improvements through automated task analysis and optimization. Retro is a skill that analyzes agent memory, detects repeated patterns, and proposes automation opportunities to optimize AI agent efficiency.

Features

Analyzes `.claude/agent-memory/*/MEMORY.md` files to detect repeated patterns
Proposes automation opportunities based on repeated patterns
Checks for context bloating in MEMORY.md files with over 200 lines
Suggests sub-agent creation for uncovered areas
Recommends shared rule creation for duplicated knowledge

# Core Topics

WHITS-ISLAND WHITS-ISLAND
[0]
[0]
Updated: 3/6/2026

Quality Score

Top 5%
30
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add WHITS-ISLAND/inspirehub-mobile/retro

Agent Capability Analysis

The retro MCP Server by WHITS-ISLAND is an open-source Categories.community integration for Claude and other AI agents, enabling seamless task automation and capability expansion. Optimized for how to use retro, retro ai agent skill, retro vs other optimization tools.

Ideal Agent Persona

Ideal for AI Agents like Claude, AutoGPT, or LangChain requiring efficiency improvements through automated task analysis and optimization.

Core Value

Empowers agents to analyze their memory and propose efficiency enhancements, automating repetitive tasks and improving performance by identifying repeated patterns in `.claude/agent-memory/*/MEMORY.md` files and suggesting skill automation and sub-agent deployment.

Capabilities Granted for retro MCP Server

Automating repetitive task identification
Analyzing agent memory for efficiency improvements
Proposing sub-agent deployment for enhanced performance
Detecting context bloat in MEMORY.md files

! Prerequisites & Limits

  • Requires access to `.claude/agent-memory` and `.claude/skills` directories
  • Limited to agents with MEMORY.md files
  • Context bloat detection limited to 200-line threshold in MEMORY.md files
Project
SKILL.md
1.9 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

振り返り・効率化スキル

エージェントのメモリを分析し、効率化のための提案を行う。

処理フロー

1. エージェントメモリ分析

  • .claude/agent-memory/*/MEMORY.md を全て読み込み
  • 各ファイルの行数をチェック(200行超 → コンテキスト肥大化警告)
  • 「Repeated Patterns」セクションから繰り返しパターンを集約

2. スキル化候補の検出

  • 繰り返しパターンを分析し、スキル化で自動化できるものを提案
  • 既存スキル(.claude/skills/*/SKILL.md)と重複しないか確認

3. サブエージェント増設の判断

  • 「Pain Points」セクションから、既存エージェントではカバーできない領域を検出
  • 新エージェント作成の提案(役割・ツール・スコープ)

4. コンテキスト肥大化チェック

  • MEMORY.mdの行数 > 200行: 整理推奨
  • 同じ知見が複数エージェントに重複: 共有ルール化を提案

5. レポート出力

出力フォーマット

markdown
1## 振り返りレポート 2 3### コンテキスト状況 4| エージェント | MEMORY.md行数 | ステータス | 5|-------------|--------------|-----------| 6| kotlin-dev | 45行 | 正常 | 7| ios-dev | 210行 | 要整理 | 8 9### スキル化候補 10- [ ] (パターン名)((エージェント名)で(N)回以上実施) 11 12### サブエージェント増設提案 13- (提案またはなし) 14 15### ルール追加提案 16- [ ] (提案)

エージェントメモリ規約

各エージェントのMEMORY.mdに以下のセクションを維持する:

  • Repeated Patterns: 繰り返し行った作業パターン
  • Pain Points: 既存の仕組みでは解決しにくかった課題
  • Lessons Learned: 学んだ知見・ベストプラクティス

Related Skills

Looking for an alternative to retro or building a Categories.community AI Agent? Explore these related open-source MCP Servers.

View All

widget-generator

Logo of f
f

widget-generator is an open-source AI agent skill for creating widget plugins that are injected into prompt feeds on prompts.chat. It supports two rendering modes: standard prompt widgets using default PromptCard styling and custom render widgets built as full React components.

149.6k
0
Design

chat-sdk

Logo of lobehub
lobehub

chat-sdk is a unified TypeScript SDK for building chat bots across multiple platforms, providing a single interface for deploying bot logic.

73.0k
0
Communication

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication