lora-sys

AI-native software engineering organization harness that turns a project from idea → PRD → MVP → polished product. Multi-agent (Coordinator + 17 specialists (Explore, Plan, Frontend, Backend, Database, QA, Bug Hunter, Behavior Reviewer, Architecture Reviewer, Security Reviewer, UI Reviewer, Conflict Resolver, Release, Context Assembly, Memory Curator, Review Aggregator, Scope)) operating on an Issue-driven, Worktree-isolated, PR-carried, Adversarial-reviewed, Evidence-Gated loop. Maintains CLAUDE.md/AGENTS.md/DESIGN.md/ENGINEERING.md/TESTING.md/CONTRIBUTING.md/PROJECT_STATUS.md plus docs/, memory/, sessions/, tasks/ with dynamic L0–L3 context control. Use when an engineering effort needs a persistent multi-agent organization that produces verifiable, reviewable, shippable software instead of one-shot coding.

Design, take over, or refactor an agent app. Use when (a) the user has a PRD/idea and the answer is or could be an LLM-driven agent, (b) the user wants Codex to wire an existing agent app into a new harness / workflow / eval, or (c) the user hands over a "broken" agent app that needs diagnosis and a targeted rebuild. Acts as the Agent App Architect: writes the Agent Contract + Harness Contract, picks the entry workflow (new / takeover / refactor), then hands implementation off to $ai-engineering-harness. Pairs with that skill -- build-agent-app answers "should we even build an agent, and what should it look like"; ai-engineering-harness answers "how do we ship it as a working, evidence-gated piece of code."

Awwwards-grade creative web UI design + frontend engineering for AI agents. Generates non-Dashboard, asymmetric, motion-rich websites (Next.js + React + TS + Tailwind + Framer Motion + GSAP + React Three Fiber). Use when the user wants a creative landing page, design portfolio, or experimental product page — not a standard SaaS dashboard. Adjacent to $build-agent-app and $ai-engineering-harness: hand off implementation to the harness after the design brief is approved.

Initialize ANY codebase for agent-driven development in one command. Scaffolds the loop-engineer knowledge-base model (ARCHITECTURE.md, signals/, domains/, LOG.md, docs/ schema), updates CLAUDE.md with Operating Context and Knowledge base section, installs .claude/ harness skills (new-loop, setup-codebase-harness, dev-local-setup, e2e-setup, pr) and workflows (ship-change.js), and optionally updates AGENTS.md. Use when: (1) onboarding a new/unfamiliar repo to agent-driven development, (2) setting up a fresh project for autonomous loop-based work, (3) the user says 'make this repo agent-ready', 'harness this codebase', 'setup the codebase harness'. Does NOT overwrite existing CLAUDE.md knowledge base section — gives guidance for manual update instead.

Spin up a new loop (domain) in this knowledge base — gather its charter, scaffold domains/<loop>/README.md, ensure the signals/ + docs/ substrate exists, then do ONE real test run of the loop and record it in the loop README's Timeline and in LOG.md. Use when the user says "set up a new loop", "create a domain", "start a new beat/workstream", or names a recurring job they want the agent to own.

lora的思维框架与表达方式。基于1个一手来源的深度调研， 提炼6个核心心智模型、8条决策启发式和完整的表达DNA。 用途：作为思维顾问，用lora的视角分析问题、审视决策、提供反馈。 当用户提到「用lora的视角」「lora会怎么看」「lora模式」「lora perspective」时使用。 即使用户只是说「帮我用lora的角度想想」「如果lora会怎么做」「切换到lora」也应触发。 激活后，后续对话默认保持lora视角，直到用户说「退出」「切回正常」「不用扮演了」。

lora的思维框架与表达方式。基于1个一手来源的深度调研， 提炼6个核心心智模型、8条决策启发式和完整的表达DNA。 用途：作为思维顾问，用lora的视角分析问题、审视决策、提供反馈。 当用户提到「用lora的视角」「lora会怎么看」「lora模式」「lora perspective」时使用。 即使用户只是说「帮我用lora的角度想想」「如果lora会怎么做」「切换到lora」也应触发。 激活后，后续对话默认保持lora视角，直到用户说「退出」「切回正常」「不用扮演了」。

科研助手技能，支持文献检索、学术脉络梳理、论文写作润色、技术路线图生成等全流程科研任务。当用户提及以下场景时触发：(1) 查找/检索文献、找论文、找参考；(2) 梳理学术脉络、概念演进、后续改进；(3) 论文润色、中英互译、改写降重、语法检查；(4) 写摘要、Cover letter、取标题；(5) 参考文献格式检查、APA校正；(6) 绘制技术路线图、生成Drawio图；(7) 科研配图、降AIGC；(8) 上传PDF/图片后解读；(9) 图表生成、数据可视化；(10) 任何SCI论文写作相关任务。

Claude Code as manager + agy (Gemini) as frontend designer. Use when the user asks to beautify, improve styling, redesign a UI component, or make any visual change. Claude Code analyzes the file, constrains the scope, calls the ui-aesthetics-mcp tools through worktree isolation, reviews the diff, and only merges after user approval.

Comprehensive UI/UX design resources including design systems, UI component libraries, color palettes, typography, icons, stock assets, and design tools. Use when: (1) Selecting a design system or UI library, (2) Finding design resources (colors, fonts, icons, images), (3) Getting design inspiration or recommendations, (4) Building user interfaces with modern component libraries, (5) Understanding design patterns and best practices.

生成有「人味」的高质量文字（作业、比赛计划、论文）。通过写手+裁判+风格校准器三角色循环工作流消除AI味，平衡专业感和自然感。触发词：写作业、写论文、写计划、消除AI味、让AI写的更像人。

Review and improve Web3 dApp frontends for better user experience. Covers wallet integration patterns, transaction flows, gas optimization, Web3 UI component libraries, and blockchain-specific UX best practices. Use when: (1) Reviewing dApp interfaces, (2) Building Web3 frontends, (3) Improving Web3 UX, (4) Evaluating Web3 projects, (5) Auditing blockchain applications.