[{"data":1,"prerenderedAt":4},["ShallowReactive",2],{"readme:claude-reflect":3},"\u003Ch1>claude-reflect\u003C\u002Fh1>\n\u003Cp>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FBayramAnnakov\u002Fclaude-reflect\u002Fstargazers\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FBayramAnnakov\u002Fclaude-reflect?style=flat-square\" alt=\"GitHub stars\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FBayramAnnakov\u002Fclaude-reflect\u002Freleases\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fversion-2.6.0-blue?style=flat-square\" alt=\"Version\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fopensource.org\u002Flicenses\u002FMIT\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-green?style=flat-square\" alt=\"License: MIT\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FBayramAnnakov\u002Fclaude-reflect\u002Factions\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Ftests-160%20passing-brightgreen?style=flat-square\" alt=\"Tests\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FBayramAnnakov\u002Fclaude-reflect#platform-support\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fplatform-macOS%20%7C%20Linux%20%7C%20Windows-lightgrey?style=flat-square\" alt=\"Platform\" \u002F>\u003C\u002Fa>\u003C\u002Fp>\n\u003Cp>A self-learning system for Claude Code that captures corrections and discovers workflow patterns — turning them into permanent memory and reusable skills.\u003C\u002Fp>\n\u003Ch2>What it does\u003C\u002Fh2>\n\u003Ch3>1. Learn from Corrections\u003C\u002Fh3>\n\u003Cp>When you correct Claude (\"no, use gpt-5.1 not gpt-5\"), it remembers forever.\u003C\u002Fp>\n\u003Cpre>\u003Ccode>┌─────────────────┐     ┌─────────────────┐     ┌─────────────────┐\n│  You correct    │ ──► │  Hook captures  │ ──► │  \u002Freflect adds  │\n│  Claude Code    │     │  to queue       │     │  to CLAUDE.md   │\n└─────────────────┘     └─────────────────┘     └─────────────────┘\n      (automatic)            (automatic)            (manual review)\n\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Ch3>2. Discover Workflow Patterns (NEW in v2)\u003C\u002Fh3>\n\u003Cp>Analyzes your session history to find repeating tasks that could become reusable commands.\u003C\u002Fp>\n\u003Cpre>\u003Ccode>┌─────────────────┐     ┌─────────────────┐     ┌─────────────────┐\n│  Your past      │ ──► │ \u002Freflect-skills │ ──► │   Generates     │\n│  sessions       │     │ finds patterns  │     │   \u002Fcommands     │\n└─────────────────┘     └─────────────────┘     └─────────────────┘\n    (68 sessions)         (AI-powered)            (you approve)\n\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Cp>Example: You've asked \"review my productivity\" 12 times → suggests creating \u003Ccode>\u002Fdaily-review\u003C\u002Fcode>\u003C\u002Fp>\n\u003Ch2>Key Features\u003C\u002Fh2>\n\u003Ctable>\n\u003Cthead>\n\u003Ctr>\n\u003Cth>Feature\u003C\u002Fth>\n\u003Cth>What it does\u003C\u002Fth>\n\u003C\u002Ftr>\n\u003C\u002Fthead>\n\u003Ctbody>\u003Ctr>\n\u003Ctd>\u003Cstrong>Permanent Memory\u003C\u002Fstrong>\u003C\u002Ftd>\n\u003Ctd>Corrections sync to CLAUDE.md — Claude remembers across sessions\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>\u003Cstrong>Skill Discovery\u003C\u002Fstrong>\u003C\u002Ftd>\n\u003Ctd>Finds repeating patterns in your history → generates commands\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>\u003Cstrong>Multi-language\u003C\u002Fstrong>\u003C\u002Ftd>\n\u003Ctd>AI understands corrections in any language\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>\u003Cstrong>Skill Improvement\u003C\u002Fstrong>\u003C\u002Ftd>\n\u003Ctd>Corrections during \u003Ccode>\u002Fdeploy\u003C\u002Fcode> improve the deploy skill itself\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003C\u002Ftbody>\u003C\u002Ftable>\n\u003Ch2>Installation\u003C\u002Fh2>\n\u003Cpre>\u003Ccode class=\"language-bash\"># Add the marketplace\nclaude plugin marketplace add bayramannakov\u002Fclaude-reflect\n\n# Install the plugin\nclaude plugin install claude-reflect@claude-reflect-marketplace\n\n# IMPORTANT: Restart Claude Code to activate the plugin\n\u003C\u002Fcode>\u003C\u002Fpre>\n\u003Cp>After installation, \u003Cstrong>restart Claude Code\u003C\u002Fstrong> (exit and reopen). Then hooks auto-configure and commands are ready.\u003C\u002Fp>\n\u003Cblockquote>\n\u003Cp>\u003Cstrong>First run?\u003C\u002Fstrong> When you run \u003Ccode>\u002Freflect\u003C\u002Fcode> for the first time, you'll be prompted to scan your past sessions for learnings.\u003C\u002Fp>\n\u003C\u002Fblockquote>\n\u003Ch3>Prerequisites\u003C\u002Fh3>\n\u003Cul>\n\u003Cli>\u003Ca href=\"https:\u002F\u002Fclaude.ai\u002Fcode\" rel=\"nofollow ugc noopener\">Claude Code\u003C\u002Fa> CLI installed\u003C\u002Fli>\n\u003Cli>Python 3.6+ (included on most systems)\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch3>Platform Support\u003C\u002Fh3>\n\u003Cul>\n\u003Cli>\u003Cstrong>macOS\u003C\u002Fstrong>: Fully supported\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Linux\u003C\u002Fstrong>: Fully supported\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Windows\u003C\u002Fstrong>: Fully supported (native Python, no WSL required)\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch2>Commands\u003C\u002Fh2>\n\u003Ctable>\n\u003Cthead>\n\u003Ctr>\n\u003Cth>Command\u003C\u002Fth>\n\u003Cth>Description\u003C\u002Fth>\n\u003C\u002Ftr>\n\u003C\u002Fthead>\n\u003Ctbody>\u003Ctr>\n\u003Ctd>\u003Ccode>\u002Freflect\u003C\u002Fcode>\u003C\u002Ftd>\n\u003Ctd>Process queued learnings with human review\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>\u003Ccode>\u002Freflect --scan-history\u003C\u002Fcode>\u003C\u002Ftd>\n\u003Ctd>Scan ALL past sessions for missed learnings\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>\u003Ccode>\u002Freflect --dry-run\u003C\u002Fcode>\u003C\u002Ftd>\n\u003Ctd>Preview changes without applying\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>\u003Ccode>\u002Freflect --targets\u003C\u002Fcode>\u003C\u002Ftd>\n\u003Ctd>Show detected config files (CLAUDE.md, AGENTS.md)\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>\u003Ccode>\u002Freflect --review\u003C\u002Fcode>\u003C\u002Ftd>\n\u003Ctd>Show queue with confidence scores and decay status\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>\u003Ccode>\u002Freflect --dedupe\u003C\u002Fcode>\u003C\u002Ftd>\n\u003Ctd>Find and consolidate similar entries in CLAUDE.md\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>\u003Ccode>\u002Freflect --include-tool-errors\u003C\u002Fcode>\u003C\u002Ftd>\n\u003Ctd>Include tool execution errors in scan\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>\u003Ccode>\u002Freflect-skills\u003C\u002Fcode>\u003C\u002Ftd>\n\u003Ctd>Discover skill candidates from repeating patterns\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>\u003Ccode>\u002Freflect-skills --days N\u003C\u002Fcode>\u003C\u002Ftd>\n\u003Ctd>Analyze last N days (default: 14)\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>\u003Ccode>\u002Freflect-skills --project <path>\u003C\u002Fcode>\u003C\u002Ftd>\n\u003Ctd>Analyze specific project\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>\u003Ccode>\u002Freflect-skills --all-projects\u003C\u002Fcode>\u003C\u002Ftd>\n\u003Ctd>Scan all projects for cross-project patterns\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>\u003C\u002Ftd>\n\u003Ctd>\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003C\u002Ftbody>\u003C\u002Ftable>\n",1784240406980]