MCP App StoreMCP App Store
from claude-reflect1,051
Capture user corrections during sessions and manage a /reflect flow to apply learnings to CLAUDE.md for future behavior improvements.
Claude Reflect is a small self-learning system for Claude Code that captures user corrections and preference signals during sessions, queues them for review, and provides a manual /reflect command to apply vetted learnings to CLAUDE.md or project-specific CLAUDE files. It focuses on preserving human-in-the-loop oversight while making agent behavior incremental and maintainable.
Use when users provide corrections, say 'remember this', or when there's a pattern of repeated fixes. It's helpful during prolonged collaboration, onboarding project rules, or when you want to retain model-specific conventions across sessions.
Best suited for agents built on Claude Code or similar environments that support session hooks and manual command entry.
Claude-reflect is a self-learning system for Claude Code that captures user corrections via hooks and queues them for review. The SKILL.md is clear and well-structured. However, all 9 scripts fail to import the lib.reflect_utils module which was not included in the packaged scripts, making them non-functional as delivered. The code quality is decent with docstrings and error handling, but the missing dependency is a critical gap. No security concerns — purely local file operations.
lib.reflect_utilsWell-designed concept with good separation of concerns (hooks for capture, commands for review). The lib/ module exclusion may be an artifact of the audit fetch process rather than a packaging flaw in the original repo. Scripts have proper error handling (exit 0 on exceptions for hooks, which is correct non-blocking behavior). No security issues — purely local operations on ~/.claude/ files.
Development Worktree
Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.
Readwise Reader Document Management
Manage Readwise Reader documents: list, save, search, move, tag, highlight, export and bulk-edit via official and custom CLIs.
Bounty Hunter — Atlas
Persona skill: 'Atlas' — a profit-focused developer persona for discovering, evaluating and executing paid bounties or freelance tasks with ROI-aware workflows.
Junshi — Research Advisor
Daily strategic research advisor that scans arXiv/venues, digests papers, and proposes bold, ranked research ideas tailored to the user's profile.
Full Stack Builder
End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.
ezBookkeeping API Tools
Command-line API tools for ezBookkeeping: record and query transactions, retrieve accounts/categories/tags, and fetch exchange rates for self-hosted personal fi
Feishu Voice Sender
Convert MP3s and send them as native Feishu voice messages (playable voice clips) to users or groups.
Claw Bench
Benchmarking skill that guides an agent through a structured suite of capability tests and reporting steps for leaderboard submission.