retrospect

Periodically review recent vault work — edits, the activity log, and feedback — and propose durable refinements: corrections to promote into SCHEMA.md, knowledge to capture, conventions to add or prun

4rigs use it

0%of all rigs

19.0kavg rig context tax

Get it

$ npx degit meain/dotfiles/agents/.agents/skills/retrospect .claude/skills/retrospect

From the most-starred rig that ships it: meain/dotfiles. Same-named skills in different rigs may differ — review before use.

Often used together with

handoff · 2 backlog · 2 gopls-lsp@claude-plugins-official · 1 frontend-design@claude-plugins-official · 1 recall · 1 commit · 1 self-review · 1 double-check · 1 code-review@claude-plugins-official · 1 skill-creator@claude-plugins-official · 1

Rigs using retrospect (4)

meain/dotfiles

If there is a shell, there is a way!

★ 285 setup Claude CodeCodex 36 skills 38 agents 5 hooks 1d ago

YOLO Cowboy 5.3k tok ·

mikeprasad/aria-knowledge

Applied reasoning, persistent agent memory, context engineering, and human-governed trust for AI coding agents — Claude Code, Claude Cowork, Codex, Cursor, Antigravity. Compatible with Obsidian.

★ 17 project Claude CodeCodexCursor 12 mcp 39 skills 25d ago

MCP Hoarder 68.1k tok ·

chicken-noodle-chris/tome

Tome is a Claude Code plugin and a CLI tool with skills and scripts to create an llm-wiki based on karpathy's suggestion, with a quartz rendering layer for enhanced user readability, and a CLI that keeps the content to-spec. It's meant to

★ 7 project Claude Code 6 skills 2mo ago

Pragmatist 650 tok ·

ngc-shj/claude-code-config

Safe default settings for Claude Code with agentic multi-model architecture

★ 1 setup Claude Code 9 skills 15 hooks 26d ago

Fort Knox 1.9k tok ·