yikart/aitoearn

1

sync-service-docs 为指定服务维护产品文档与代码的同步。文档不存在时以 OpenAPI 规范为基础从头生成；文档已存在时根据 git diff 更新受影响章…

yikart/aitoearn

48

2

to-prd Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to …

yikart/aitoearn

26

3

grill-me Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of …

yikart/aitoearn

21

4

improve-codebase-architecture Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/a…

yikart/aitoearn

20

5

caveman Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keepi…

yikart/aitoearn

19

6

design-taste-frontend Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right de…

yikart/aitoearn

19

7

diagnose Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument…

yikart/aitoearn

19

8

imagegen-frontend-web Elite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUT…

yikart/aitoearn

19

9

impeccable Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adap…

yikart/aitoearn

19

10

prototype Build a throwaway prototype to flesh out a design before committing to it. Routes between two branches — a runnable t…

yikart/aitoearn

19

11

to-issues Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet verti…

yikart/aitoearn

19

12

write-a-skill Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to …

yikart/aitoearn

19

13

zoom-out Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a …

yikart/aitoearn

19

14

grill-with-docs Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates docum…

yikart/aitoearn

18

15

handoff Compact the current conversation into a handoff document for another agent to pick up.

yikart/aitoearn

18

16

karpathy-guidelines Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid…

yikart/aitoearn

18

17

setup-matt-pocock-skills Sets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know this repo…

yikart/aitoearn

18

18

tdd Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, me…

yikart/aitoearn

18

19

triage Triage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, …

yikart/aitoearn

18

20

vercel-react-best-practices React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing…

yikart/aitoearn

18

21

crawling-social-media Downloads and extracts content from social media platforms. Use when user wants to crawl, download, or extract videos…

yikart/aitoearn

2

22

analyzing-videos Analyzes video content and extracts highlights. Use when user wants to analyze video, extract highlights, create vide…

yikart/aitoearn

1