MCP App StoreMCP App Store
from Claude Code Settings1,450
Analyze a development or agent session to capture learnings and improve CLAUDE.md instructions; supports quick and deep analysis modes.
This skill analyzes a conversation or development session to identify issues, extract lessons learned, and propose concrete improvements to CLAUDE.md (agent instructions). It supports a Quick mode for focused CLAUDE.md edits and a Deep mode for comprehensive session analysis, generating action items and implementation steps.
Use Reflection after a multi-step development session, post-mortem, or when Claude's behavior deviates from expectations. Choose Quick mode for fast instruction tweaks and Deep mode for full session retrospectives and documentation updates.
Agent types that can use this skill include Claude-style instruction agents and other conversational developer assistants that read and edit CLAUDE.md or similar project-level instruction files.
Reflection is a Claude Code skill for analyzing development sessions and improving CLAUDE.md instructions, offering quick and deep analysis modes. No bundled scripts — it's purely instructional, relying on the agent to follow written steps. The SKILL.md is well-structured with clear mode selection and phased workflows, but lacks concrete output contracts and has no automation beyond manual agent guidance. Niche audience (Claude Code users who want structured reflection); limited uniqueness as similar prompts exist.
Pure-instruction skill with no scripts. Security is strong — no external calls, no credentials, no destructive commands. References git commit but that's agent-directed, not scripted. Architecture is decent but could benefit from separating references/ for examples. Usefulness is moderate: niche audience, and similar reflection prompts are common in the Claude Code ecosystem.
Caveman Compress
Compress natural-language memory files into a compact 'caveman' format to save LLM tokens while preserving code, links, and structure.
Chinese Software Copyright Application
Generate complete Chinese software copyright application materials (application form, code documentation, user manual, design docs) and export them to PDF from
CTF Write-up Generator
Generate a concise, reproducible submission-style CTF writeup with a one-path solution script, metadata, and a short checklist for fast verification.
Verifying Markdown Formatting
Checks Markdown files for structural and stylistic formatting issues (headings, lists, code blocks, links) and applies deterministic fixes.
Code Spec Backfill
Identify missing function-level contracts and backfill docstrings and type annotations; report ambiguous gaps with misuse scenarios. Incremental, state-driven w
Azure External Attack Surface Management
Provides expert guidance for Azure External Attack Surface Management (EASM): quotas, configuration, integrations, and exporting inventory to analytics platform
Smalltalk MCP
Connects an LLM (Claude/OpenAI/etc.) to a live Smalltalk (Squeak/Cuis) image over MCP for browsing, evaluating and modifying Smalltalk code.
Ubiquitous Language Glossary
Extract a DDD-style ubiquitous language glossary from conversation: identify domain terms, flag ambiguities, propose canonical terms, and write the result to UB