Winrey Toolkit
- 3 repo stars
- Updated April 10, 2026
- winrey/claude-code-toolkit
Winrey's personal Claude Code skills including review-loop
About
winrey-toolkit is a Claude Code skill in the AI & Agent Building category. Winrey's personal Claude Code skills including review-loop
- winrey-toolkit
- AI & Agent Building
- AI-coding skill
Winrey Toolkit by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
/plugin marketplace add winrey/claude-code-toolkit/plugin install winrey-toolkit@winrey-toolkitAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| repo stars | ★ 3 |
|---|---|
| Last updated | April 10, 2026 |
| Repository | winrey/claude-code-toolkit ↗ |
What it does
Winrey's personal Claude Code skills including review-loop
README.md
claude-code-toolkit
Winrey's personal Claude Code plugin — a collection of custom skills.
Skills
review-loop
Iterative multi-round code review with isolated subagents.
Dispatches independent reviewer subagents → screens and verifies findings → fixes confirmed issues → parallel dual-path re-review (fix diff + full review) → repeats until no Critical or Important issues remain.
- Isolated subagent reviewers — each round starts fresh, no anchoring on prior findings
- Verification layer — uncertain findings are independently verified before fixing
- Parallel dual-path re-review — after fixes, review both the fix diff AND the full codebase simultaneously
- Flexible reviewer count — 1-3 reviewers based on change complexity, with customizable focus areas
- Per-round user reporting — concise summary after every cycle
- Configurable max rounds — default 5, pauses and asks user when exceeded
Installation
Add the marketplace and install:
claude plugin marketplace add winrey/claude-code-toolkit
claude plugin install winrey-toolkit
To update later:
claude plugin update winrey-toolkit
License
MIT
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10AI & Agent Buildingagents