🪞
AI EngineeringJavaScript

Claude Reflect

by ccplugins

Claude Reflect is an AI Engineering skill for Claude Code, published by ccplugins in awesome-claude-code-plugins.

922 stars392 forkson ccplugins/awesome-claude-code-pluginsAdded 2026/08/22Repository updated 2026/08/12
awesome-claude-codeawesome-listawesome-pluginsawesome-resourcesclaude-codeclaude-code-commandsclaude-code-hooksclaude-code-mcpclaude-code-pluginclaude-code-subagents
Install in seconds
Install Claude Reflect
Copy Claude Reflect into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/ccplugins/awesome-claude-code-plugins/tree/main/plugins/claude-reflect ~/.claude/skills/claude-reflect

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/ccplugins/awesome-claude-code-plugins.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
plugins/claude-reflect/SKILL.md in ccplugins/awesome-claude-code-plugins
Installs to
~/.claude/skills/claude-reflect
Collection
One of 25 skills cataloged from this repository
Category
AI Engineering2451 skills

What Claude Reflect does

Claude Reflect captures corrections during sessions and queues them for later review. Use it when users ask you to remember something or after meaningful work so they can run /reflect and update CLAUDE.md.

Claude Reflect is cataloged under AI Engineering on DirSkills. Claude Reflect comes from a repository tagged awesome-claude-code, awesome-list, awesome-plugins, awesome-resources and claude-code.

Documentation

README

Claude Reflect - Self-Learning System

A two-stage system that helps Claude Code learn from user corrections.

How It Works

Stage 1: Capture (Automatic) Hooks detect correction patterns ("no, use X", "actually...", "use X not Y") and queue them to ~/.claude/learnings-queue.json.

Stage 2: Process (Manual) User runs /reflect to review and apply queued learnings to CLAUDE.md files.

Available Commands

Command Purpose
/reflect Process queued learnings with human review
/reflect --scan-history Scan past sessions for missed learnings
/reflect --dry-run Preview changes without applying
/skip-reflect Discard all queued learnings
/view-queue View pending learnings without processing

When to Remind Users

This is the opening of the README. Read the full README on GitHub.

Commands Claude Reflect provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

  • /reflect
  • /skip-reflect
  • /view-queue

Frequently asked about Claude Reflect

  • What else does ccplugins publish alongside Claude Reflect?

    Claude Reflect is one of 25 skills that DirSkills catalogs from ccplugins/awesome-claude-code-plugins, the repository it ships in. Its siblings there include AI Divination, AI Meeting and Agent Manager. Each one is a separate skill with its own page in this directory, installs the same way Claude Reflect does, and is maintained by ccplugins in that same repository. The rest of the collection is listed on the ccplugins/awesome-claude-code-plugins page.

  • How does Claude Reflect compare to other AI Engineering skills?

    Claude Reflect ranks #1477 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Claude Reflect against them. Open each page to compare what they document and how they install.

More from ccplugins/awesome-claude-code-plugins

Claude Reflect is one of 25 skills cataloged on DirSkills from ccplugins/awesome-claude-code-plugins.

See all 25 skills
🔮
1w ago

AI Divination

AI Divination uses audited local tools to draw tarot, cast I Ching hexagrams, and perform Xiao Liu Ren readings. Use it when you need reproducible divination results and want the model to interpret structured JSON instead of inventing cards or lines.
AI Engineering
922392
🤝
1w ago

AI Meeting

AI Meeting runs structured multi-agent discussions to review plans, designs, proposals, and strategy choices. Use it when you need independent critique, cross-role debate, and a final decision report with provenance.
AI Engineering
922392
🤖
1w ago

Agent Manager

Agent Manager orchestrates multiple local CLI agents in parallel with tmux. Use it to start, assign, monitor, and schedule agent tasks from the command line.
Automation
922392
🧠
1w ago

Ask

Ask answers natural-language questions by searching a vault first, then deciding whether graphify or remote ingestion is needed. Use it for Second Brain questions about status, ownership, relationships, or how something works.
AI Engineering
922392
🗜️
1w ago

Compress

Compress scans a vault for broken backlinks, concept fragmentation, duplicated entities, miscategorized entities, and misnamed entities. It queues semantic fixes for review or delegates mechanical repairs to /bedrock:preserve.
Automation
922392
📄
1w ago

Confluence Fetcher

Confluence Fetcher converts Confluence pages into Markdown for internal Claude Code workflows. It tries Atlassian MCP first, then the REST API, and finally browser DOM extraction when earlier methods fail.
Automation
922392