By JuyeongYi
Autonomous codebase improvement loops. Unlike Ralph Loop (retry on failure), Ouroboros runs continuous improvement cycles — each iteration proactively analyzes, fixes, and enhances the codebase regardless of prior success.
Analysis stage of the Ouroboros loop. Reads raw observations from the research step (.ouroboros/research.md) and classifies them into bugs, quality_issues, and enhancement_opportunities. Saves results to .ouroboros/state.json.
Large-scope task isolation. Detects oversized tasks from analyze/fix, creates a git branch, optionally launches a background agent, and records the branch plan for the main loop to track.
This skill should be used when the user asks to 'cancel ouroboros', 'stop ouroboros loop', 'stop the loop', 'ouroboros cancel', or 'halt autonomous improvement'. Gracefully cancels an active Ouroboros loop.
Saves a handoff summary to .ouroboros/handoff.md after each Ouroboros step completes. Called by the ouroboros-agent after invoking a step skill, so the next step agent can start with compressed context instead of a full history.
Post-evaluate autonomous judgment stage for the Ouroboros loop. Performs a comprehensive assessment of codebase health, stagnation detection, and natural-language evaluation of the completionPrompt condition. Returns OUROBOROS_RESULT: done or continue. Runs after evaluate in the step sequence.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
개인 Claude Code 플러그인 컬렉션을 관리하는 마켓플레이스입니다.
comfydev_helperlearning-assistantpy-inspectorue-inspectorgit clone https://github.com/JuyeongYi/jylee_claude_marketplace.git
cd jylee_claude_marketplace
# Linux/Mac
ln -s $(pwd)/comfydev_helper ~/.config/claude-code/plugins/comfydev_helper
# Windows (관리자 권한 필요)
mklink /D "%APPDATA%\claude-code\plugins\comfydev_helper" "%CD%\comfydev_helper"
각 플러그인의 README.md 파일을 참조하여 사용법을 확인하세요:
새로운 플러그인을 추가하려면 CONTRIBUTING.md를 참조하세요.
각 플러그인은 다음 구조를 따릅니다:
plugin-name/
├── .claude-plugin/
│ └── plugin.json # 플러그인 메타데이터
├── commands/ # 슬래시 커맨드
├── agents/ # 전문 에이전트
├── skills/ # 기술 문서
└── README.md # 플러그인 문서
MIT License - 자유롭게 사용, 수정, 배포 가능합니다.
JuyeongYi
기여는 언제나 환영합니다! 자세한 내용은 CONTRIBUTING.md를 참조하세요.
버그 리포트나 기능 제안은 GitHub Issues를 통해 제출해 주세요.
npx claudepluginhub juyeongyi/jylee_claude_marketplace --plugin ouroboros-loopsAnalyzes and refactors Unreal Engine C++ code to be more AI-friendly, following research-backed best practices for improved AI tool compatibility
C++/C language pack for code-analysis v2. Declares hard-require static tools (clang-tidy, cppcheck, iwyu, codeanalyzer-metrics) in strategy, supplies C++-specific qualitative audits (after-analyze-file), C++ false-positive filters (after-phase3-trace), and Cypher-driven Phase-4 docs (class hierarchy, template catalog).
Manage custom CLI tools with Claude Code integration. Currently supports m2m for 3D mesh format conversion (GLB, GLTF, OBJ, FBX, USD, STL, PLY, ABC).
UE5 framework pack for code-analysis v2. Provides ue-deps CLI + MCP (Build.cs/uplugin/uproject module dependency trees), UE-specific Phase-2 audits (tick-audit, replication-audit), Phase-3 virtual-entry injection + reflection-exempt filter, and Phase-4 docs (Blueprint API, RPC catalog, module-diagram cross-verified against GitNexus).
Discord channel for Claude Code — messaging bridge with built-in access control. Manage pairing, allowlists, and policy via /discord:access.
Evidence-gated AI coding workflow: scan → analyze → plan → TDD → execute → fix → verify → review, powered by Codebase Memory MCP >= 0.9.0 with optional Serena LSP intelligence. Includes blast-radius planning, test/cycle gates, independent review, and Windows Git Bash hook auto-resolution.
Comprehensive SEO analysis plugin for Claude Code. 25 sub-skills (21 core + 1 orchestrator + 1 framework + 2 extension mirrors) and 18 sub-agents cover technical SEO, content quality, schema, sitemaps, Core Web Vitals, local SEO, backlinks, AI/GEO, ecommerce, hreflang, SXO, clustering, drift monitoring, and Google APIs. Includes optional MCP extensions, SPA-aware rendering, portability, and hardened SSRF/DNS-rebinding safe fetchers.
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications