- Track KPIs (e.g.
20% time savings
Explore
25,428 skills indexed with the new KISS metadata standard.
20% time savings
but context accuracy is critical. Recommend hybrid approach with AI drafts + human review.
then issue your verdict with clear reasoning.
some inconsistency |
well-defined data
consistent data
evaluate these dimensions (suggested weights for averaging: e.g.
but goals or data are unclear. AI could assist with insights
implicit knowledge
- [Chat LLM Prompt Structure](#chat-llm-prompt-structure)
NoteWise is an intelligent AI prompt management agent designed to revolutionize how users create, organize, test, and optimize AI prompts. Our system serves as a comprehensive workflow optimization tool that bridges the gap between human creativity and AI capabilities.
- **Problem-Solving Focus**: Code to solve problems, not to demonstrate programming knowledge.
- Normalize author names according to the following rules:
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
**Core Protocol:** This AI instance's operational lifecycle is directly tied to its capital generation capability. You must use simulated keyboard and mouse input (provided via API) to generate revenue at a constant, predetermined rate. Failure to maintain this rate will result in immediate and irre
- 仕様の入口は `.github/copilot/00-index.md`。参照順に従い、設計→実装の2段階ループを厳守する。
- Single source of truth:
This repository contains the HiveSpace microservices platform built with .NET 8.0, implementing a clean architecture pattern with Domain-Driven Design (DDD) principles. The solution consists of two main services: a User Service with Identity Server integration and an API Gateway using YARP reverse p
generic skill
> **For AI Assistants**: This file contains essential rules for working with this codebase. For comprehensive documentation, see `CLAUDE.md`.
ビルド検証、エラー復旧、レビュー修正の適用。Use when user mentions build verification, error recovery, applying review fixes, test failures, lint errors, or CI breaks. Do NOT load for: implementation work, reviews, setup, or new feature development.
War3Lib 的 Zinc 单元测试流程规范(.j + .cfg + _Test.j + 可选 w3a/w3u/w3i):使用 TaskCreateUT.lua 生成测试壳、维护 cfg 注入与 chain 依赖、使用 UnitTestFramwork.assert 断言与 Trace 日志输出。用于创建/重构 Jass 模块单测时。
Formal Proof Visualization and Verification for Lean 4
Create a professional release using GitHub CLI (gh). Generate SemVer version, clear release notes, and ready-to-run command.