Sno Station
Sno Station은 AI 에이전트를 하나의 팀으로 묶는 오픈소스 워크스테이션으로, 로컬 머신에서 에이전트 협업을 가능하게 함
Claude Code 플러그인을 관리·설치해 코드 리뷰와 개발 흐름을 지원
Manage and install Claude Code plugins for code review and development workflows
AI가 요약 · README에서
플러그인Shell · PythonGitHub @juanmhidalgo직접 설치운영자 미확인
써 보셨어요? 한 번만 눌러 주세요. 로그인은 필요 없어요.
아직 감지된 업데이트가 없습니다. GitHub 릴리스가 나오면 여기에 보입니다.
개인 계정의 공개 저장소 소유자는 GitHub로 로그인해 운영자를 확인하고 소개를 직접 관리할 수 있습니다. 관리자 승인은 필요하지 않습니다.
로그인한 뒤 확인 파일을 만들어 이 저장소의 기본 브랜치에 30분 안에 커밋해 주세요. 다른 브랜치나 포크의 파일은 인정하지 않습니다. 파일을 올린 뒤 아래에서 확인하면 관리자 승인 없이 관리할 수 있습니다. 자격을 유지하려면 파일을 남겨 두세요.
로그인이 필요하면 로그인 화면으로 이동합니다. 로그인 후 이곳으로 돌아와 원하는 확인 버튼을 다시 눌러 주세요.
설치형 프로젝트는 배포 도메인 없이도 확인할 수 있습니다. 개인 저장소는 GitHub 로그인으로, 조직 저장소는 위의 저장소 확인 파일로 직접 확인해 주세요.
README 전체를 불러오는 중입니다. 아래는 저장된 발췌입니다.
Personal Claude Code plugins for development workflows.
See WORKFLOW.md for how to use these plugins together across the development lifecycle, and CONNECTORS.md for which plugins integrate with which external systems (GitHub gh CLI, ClickUp MCP, etc.).
Comprehensive code review workflow with skeptical AI feedback triage.README 전문 보기 ↗Personal Claude Code plugins for development workflows.
See WORKFLOW.md for how to use these plugins together across the development lifecycle, and CONNECTORS.md for which plugins integrate with which external systems (GitHub gh CLI, ClickUp MCP, etc.).
# Add this marketplace
/plugin marketplace add juanmhidalgo/claude-plugins
# Or from local path
/plugin marketplace add /path/to/claude-plugins
Comprehensive code review workflow with skeptical AI feedback triage.
Commands:
/code-review/branch - Review branch vs base/code-review/staged - Review staged changes/code-review/triage - Triage AI feedback (Copilot, Gemini)/code-review/dismiss - Dismiss false positives on GitHub/code-review/fixes-plan - Generate fix tracking document/code-review/implement-fix - Implement fixes, asking for technical decisions/code-review/mark-fixed - Verify and mark fixes/code-review/resolve-fixed - Resolve GitHub threads for fixed issuesInstall:
/plugin install code-review@juanmhidalgo-plugins
Create and manage Product Requirements Documents (PRDs) with AI assistance.
Commands:
/prd:refine [file | issue-url] - Improve existing PRD or convert vague issue to PRD/prd:validate [file | issue-url] - Verify implementation matches PRD criteria/prd:analyze [file | issue-url | text] - Identify gaps, edge cases, and ambiguitiesFor creating new specs from scratch, use /feature-dev:spec.
Install:
/plugin install prd-toolkit@juanmhidalgo-plugins
Critical feature discussion, idea refinement, and adversarial review of technical documents.
Commands:
/discuss:feature [feature or idea] - Critical analysis, identify gaps and risks/discuss:brainstorm [problem] - Generate 4-6 alternative approaches/discuss:challenge [proposal] - Argue against to stress-test/discuss:tradeoffs [A vs B] - Compare options with pros/cons matrix/discuss:adversarial-doc-review [doc-path] - Red-team a written PRD/ADR/spec in a fresh context, reporting only what would cause a bad design decision/discuss:grill [plan or idea] - Interview you in rounds, each question with a recommended answer, until every decision is settled/discuss:wait-what [the part that lost you] - Re-explain the last message simply, in the conversation's languageInstall:
/plugin install discuss@juanmhidalgo-plugins
Translate unstructured customer/CSM/Sales/Support requests into engineering signals: feasibility reports, customer-facing reply drafts, and anticipated-objection Q&A. Sits before /discuss:feature and /feature-dev:spec in the workflow.
Commands:
/intake:feasibility <request or path> - Decompose a customer ask into capabilities + constraints, research each in parallel against the codebase, produce a Status × Effort × Evidence map with risk callout, phased recommendation, and Excluded for this customer list/intake:respond-draft <report> - Summarize a feasibility report for CSM in plain language. No customer-facing draft (CSM owns customer voice); no calendar commitments (uses commitment categories and [CSM TO CONFIRM TIMELINE] placeholders)/intake:objection-prep <report> - Anticipate CSM/Sales/customer pushback against a feasibility report; outputs a Q&A list with prepped factual responsesInstall:
/plugin install intake@juanmhidalgo-plugins
Session retrospectives built on what the Claude Code logs actually measured — cost, wall clock, permission denials, hook blocks, slowest turns — instead of asking how the session felt. Every finding names the file that fixes it.
Commands:
/retro:session [--last N] [--session <id>] - Digest this project's session logs, rank the friction by what it cost, and route each finding to a destination: a CLAUDE.md rule, a memory file, a permission rule, a hook, or a fix to a plugin in this repo. Scoped to one project per runInstall:
/plugin install retro@juanmhidalgo-plugins
# Refresh marketplace metadata
/plugin marketplace update juanmhidalgo-plugins
# Reinstall to get latest version
/plugin uninstall code-review@juanmhidalgo-plugins
/plugin install code-review@juanmhidalgo-plugins
gh CLI installed and authenticatedThese plugins use git, gh, and standard test-runner CLIs heavily. To avoid per-call permission prompts, merge the rules from settings.example.json into your ~/.claude/settings.json (user-wide) or the project-level .claude/settings.json. The example also denies common destructive operations (rm -rf, git push --force, git reset --hard) and reads against .env/credentials paths.
This is a community project and is not affiliated with, endorsed, or supported by Anthropic.
These plugins are provided "as is" without warranty of any kind. Use at your own risk. The author is not responsible for any damages or issues arising from the use of these plugins.
MIT License - See LICENSE for details.