dotnet-review
Multi-agent .NET code review - five reviewers in parallel (correctness, performance, security/observability, data/messaging/integration, generalist), then an…
A command is the one you type. It runs exactly when you ask it to, and never before.
2,159 commands across 254 plugins.
Multi-agent .NET code review - five reviewers in parallel (correctness, performance, security/observability, data/messaging/integration, generalist), then an…
Manually trigger context handoff - skip waiting for 60% threshold
Claude Code 핵심 커맨드를 한 눈에 볼 수 있는 한국어 치트시트. Use when the user asks for a cheatsheet, quick reference, or "전체 명령어 보여줘".
프로젝트에 맞는 CLAUDE.md 한국어 템플릿을 생성합니다. 웹앱, API 서버, 데이터 파이프라인, 모노레포, 사이드 프로젝트 유형을 지원합니다. Use when the user wants to create or set up CLAUDE.md in Korean.
4-phase Context Engineering workflow with guided implementation
Plan a new feature using spec-workflow-orchestrator skill
Research a topic using multi-agent-researcher skill
Audit your code for wasteful LLM API spend and get a concrete plan to cut it — cache, batching, retry caps, prompt bloat. No fabricated numbers.
WCAG compliance, ARIA, keyboard nav, screen readers
Detecting and fixing the generic AI-generated look in UI and copy
Implement working login and signup using Clerk or Supabase Auth — actual code, not just design guidance
委派模型回答/分析/审/咨询。**只读不改文件**(Read/Grep/Glob + Bash(git:*))。主 Claude 会智能补 --with-context、选模型。
多模型并行对同一问题各给独立意见(发散式 brainstorming),主 Claude 综合分歧、共识、独到见解。各模型彼此看不到对方答案,避免回声室效应。
委派模型**改文件/落盘/执行**。隐含 --write(子进程获得 Edit/Write/Bash 全权)。主 Claude 会智能补 --with-context、选模型。
Run the 5-agent Council on the current file or a specified path. Returns SHIP / REVISE / HOLD plus a revision brief.
Walk the configured watch paths and run Council on every artifact modified in the last N hours (default 24h).
Profile how top GitHub contributors work — ingest, build personas, and synthesise a capability model + learnable playbook.
Initialize local memory store + vector index for this project.
Run polygen — draft a contract from a feature description, author a verifiable SAM v2 strict-profile module against it (--legacy-bare-next for a bare…
Run polynv — elicit the invariants for a state machine. Harvest candidates from the contract's vocabulary, traces, and fleet snapshots; contribute…
Run polyvers — classify a state-machine version change into compatibility lanes, run the gates those lanes require against fleet snapshots (shape round-trip,…
Generate, edit, or create any image — photos, illustrations, website visuals, placeholders, icons, thumbnails, banners, or any graphic asset
Bootstrap the operating model and minimal delivery-planning seed (dry-run first, never overwrites)
Initialise the planning seed and record the human team, roles, and escalation channels
Validate the operating-model seed — manual binding, adapter drift, adoption state, checkpoint/evidence
Delegate any task to agy (Google Antigravity CLI) — auto-selects model by task type
Adversarial critique via agy using Gemini Pro — independent second opinion on code, plans, or arguments
Web search via agy (Google Antigravity CLI) — agy grounded web search with source citations (for general search prefer the WebSearch tool)
Run Specwright eval suite. Spawns subagents to run skills in fixture workdirs, then grades results.
Full security audit of a Solidity/Vyper/Rust contract or directory. Runs the entire vuln-skills library and dispatches DeFi specialist subagents based on…
Audit only the git diff vs main (or specified base). Optimized for PR review.
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic