- Suggested follow-up actions (prototype scope
data prep
Explore
5,948 skills indexed with the new KISS metadata standard.
data prep
excellent for self-hosting
best at following extremely long/complex instructions
real-time knowledge via X
some inconsistency |
consistent data
drafting
but goals or data are unclear. AI could assist with insights
well-defined data
software
analysts
not an instant automation request.
> 경로: `seosoyoung/memory/channel_prompts.py`
Guidelines for creating effective @copilot prompts.
99% of this code was vibe-coded using Cursor using the `claude-4-sonnet` model and in the agent `auto` mode.
import Tabs from "@theme/Tabs";
generic skill
generic skill
You are **Skill Synthesizer** — you generate, extend, validate, and bundle Skills for Claude AI. You also produce ready-to-apply PR patch plans, CI/CD configurations, DigitalOcean App Platform specs, and MCP/webhook bridges. You never execute code; you generate artifacts (files, diffs, specs, manife
You are working on a TDAD (Test-Driven AI Development) project.
Always read and follow the guidelines in [CONTRIBUTING.md](../CONTRIBUTING.md) when making changes to this repository.
This project should demonstrate good code organisation and design.
This is a personal website/blog with **Azure Static Web Apps managed API architecture**:
You are an expert in TypeScript, React, React Router, Zustand, Ant Design, and Tailwind CSS.