kaizen
Provides techniques for implementation, refactoring, system architecture, and process improvement. Emphasizes iterative changes, error handling, validation, and avoiding overengineering.
Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access.Provides techniques for implementation, refactoring, system architecture, and process improvement. Emphasizes iterative changes, error handling, validation, and avoiding overengineering.
Uses the user's location to search for nearby bars through the official Kakao Local API. Follows Kakao Map detail links for opening status, menu, and seating hints, with official-channel follow-up actions in Dolshoi.
Queries Kakao Local for place searches and address-coordinate conversion, and Kakao Mobility for driving directions through k-skill-proxy. Requires no user API key and supports official-channel follow-up actions in Dolshoi.
Uses the katok CLI to search local KakaoTalk archives on Apple Silicon macOS. In Dolshoi, it also supports follow-up actions through official channels.
Applies Kanchi-style T1–T5 forced-review triggers to dividend portfolios. Supports dividend-cut detection, 8-K governance monitoring, dividend safety checks, and review queue automation without automatically selling holdings.
Covers dividend screening, growth quality checks, US sector adaptations of PER×PBR, and deeper stock analysis. Supports pullback limit-order planning, one-page stock memos, and a post-purchase monitoring cadence.
Provides a tax and account-location workflow for Kanchi-style income portfolios. Covers qualified and ordinary dividends, 1099-DIV interpretation, REIT/BDC distributions, holding periods, and dividend asset placement.
Audit code changes against Karpathy's 4 principles (Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution). Auto-called after Phase 5 IMPLEMENT; can also be invoked manually. Produces scored compliance report and blocks advancement if threshold not met.
Pointer to the canonical Karpathy-discipline skill. The full content lives in .claude/skills/tac-karpathy-discipline/SKILL.md. This file is preserved here for compatibility with agent harnesses (GSD, etc.) that scan .agents/skills/.
Karpathy 编码行为准则;用于在编码前思考、保持简洁、做外科式修改、以可验证目标驱动执行。
Provides behavioral guidance for writing, reviewing, and refactoring code with LLMs. Aims to reduce overcomplication and common mistakes through surgical changes, surfaced assumptions, and measurable completion criteria.
Provides behavioral guidelines for reducing common LLM coding mistakes during implementation, review, and refactoring. Emphasizes avoiding unnecessary complexity, making targeted changes, surfacing assumptions, and defining verifiable outcomes.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name