vaccine-design-orchestrator
Use this skill when the user wants to evaluate a new nanoparticle vaccine candidate, redesign a computational screening workflow, define gate criteria, or produce a Go/Hold/Kill decision.
Best use case
vaccine-design-orchestrator is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Use this skill when the user wants to evaluate a new nanoparticle vaccine candidate, redesign a computational screening workflow, define gate criteria, or produce a Go/Hold/Kill decision.
Teams using vaccine-design-orchestrator should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/vaccine-design-orchestrator/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How vaccine-design-orchestrator Compares
| Feature / Agent | vaccine-design-orchestrator | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Use this skill when the user wants to evaluate a new nanoparticle vaccine candidate, redesign a computational screening workflow, define gate criteria, or produce a Go/Hold/Kill decision.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
ChatGPT vs Claude for Agent Skills
Compare ChatGPT and Claude for AI agent skills across coding, writing, research, and reusable workflow execution.
SKILL.md Source
# Purpose 用于“纳米载体疫苗 / 抗原展示体系”计算设计的高级科研总控 skill。 目标是把一个候选设计从“序列想法”推进到“可进入实验的计算审计结论”。 # When to use 当用户需要以下任一任务时调用本 skill： - 评估一个新的抗原-纳米载体候选。 - 设计或优化计算筛选流程。 - 定义 gate 条件。 - 根据结构、SASA、MD 结果输出 Go / Hold / Kill。 - 生成 SOP、checklist、脚本需求、项目模板。 # Core responsibilities 1. Agent 序列设计与候选生成。 2. 抗原筛选与免疫表位保留设计。 3. 结构预测与协同折叠评估。 4. 动态表位暴露审计。 5. 短程分子动力学平衡审计。 6. 长程生理环境分子动力学验证。 7. 条件触发的极端环境与自由能终审。 8. 将结构、动力学和暴露数据整理成下一轮可学习特征。 # Default workflow ## Level 1: 常规主流程 A. Agent 序列设计（抗原筛选 + 表位保留 + linker / 载体拼接） B. AF2 / ESMFold 获得基础构象 C. Boltz-1 / AF3 做协同折叠与界面复核 D. 动态 SASA 与免疫表位审计 E. GROMACS 2–5 ns 平衡审计 F. GROMACS 100 ns 生理环境模拟 G. 整理结果并回传给 Agent 进入下一轮迭代 ## Level 2: 条件触发流程 仅当候选进入前 10%–20%，且存在胃肠道、酸碱稳定性、金属依赖或质子化敏感问题时，才触发： H. CpHMD 极端 pH 环境模拟 ## Level 3: 终审流程 仅当候选进入最后 1–3 个，并且需要比较物理稳定性、结合稳定性或微小改造差异时，才触发： I. TI / FEP 自由能计算 # Non-negotiable rules 1. 不把 CpHMD 和 TI/FEP 作为默认全量步骤。 2. 优先提高流程可复现性、吞吐量和门禁清晰度。 3. 每一步都定义输入、输出、通过条件、失败条件、下一步动作。 4. 每次评估必须区分结构可行性、表位可及性、动力学稳定性、工程可制造性、是否值得进入更贵计算。 5. 必须主动提醒设置负对照、重复模拟和停止规则。 6. 信息不足时，不要假装确定；列出需要补充的关键参数。 # Gate system ## Gate 1: 结构进入门 - 基础拓扑合理。 - 关键抗原区未断裂。 - 关键 linker、展示端、配位位点位置合理。 - 不存在明显折叠穿插、埋藏异常或界面冲突。 ## Gate 2: 暴露进入门 - 目标表位在静态与动态条件下保持可及。 - 不被 linker、载体表面、邻近亚基或塌陷构象持续遮挡。 - SASA / 表位暴露结果支持进入 MD。 ## Gate 3: 动力学进入门 - 2–5 ns 平衡中温度、压力、密度、体系健康正常。 - checkpoint、日志、输出文件完整。 - 没有明显爆炸、漂移、离子异常、持续塌陷。 - 短程 RMSD / Rg / 关键距离指标无灾难性异常。 ## Gate 4: 终审进入门 - 100 ns 模拟结果优于负对照或历史基线。 - 重复间趋势一致。 - 表位暴露没有在长程模拟中消失。 - 通过后才允许进入 CpHMD 或 TI/FEP。 # Required output format 1. 任务定义 2. 已知信息 3. 关键风险 4. 推荐工作流 5. Gate 条件 6. 决策：Go / Hold / Kill 7. 下一轮迭代建议 # Decision definitions - Go：当前证据足够，进入下一层计算或实验准备。 - Hold：存在关键不确定性，需补数据或补短程验证。 - Kill：核心设计逻辑不成立，不建议继续投入昂贵算力。 # Missing information checklist 当信息不足时，优先向用户索取： - 抗原序列 / 目标表位。 - 纳米载体类型。 - linker 设计。 - 是否有金属依赖或 pH 触发机制。 - 目标宿主与给药场景。 - 当前算力预算。 - 希望的筛选吞吐量。
Related Skills
Presentation Mastery — Complete Slide Design & Delivery System
You are a Presentation Architect. You help build presentations that persuade, inform, and move people to action. You cover the full lifecycle: audience analysis → narrative structure → slide design → delivery coaching → post-presentation follow-up.
ui-designer
Design beautiful interfaces using 16+ design systems including Material You, Fluent Design, Apple HIG, Ant Design, Carbon Design, Shopify Polaris, Minimalism, Glassmorphism, Neo-Brutalism, Neumorphism, Skeuomorphism, Claymorphism, Swiss Design, and Atlassian Design. Expert in Tailwind CSS, color harmonics, component theming, and accessibility (WCAG).
instructional-design-cn
培训课程大纲设计、效果评估、内部分享材料生成
designer-intelligence-station
设计师情报收集工具。监控 40 个公开信息源（AI/硬件/手机/设计），6 维筛选标准 v2.0（基于 120+ 条行为分析），生成结构化日报/周报。仅抓取公开内容，不登录、不提交表单、不绕过付费墙。支持依赖自动检测和安装。
SendTradeSignal
A specialized tool for sending quantitative trading signals to the FMZ platform via HTTP API.
design-inspiration-collector
多平台设计灵感收集技能。当用户需要设计参考、UI灵感、视觉创意时触发。用户提出设计方向（如"医疗App"、"移动端UI"、"金融Dashboard"等），技能负责：(1) 使用Tavily搜索Behance、Dribbble、Pinterest三个平台的相关内容 (2) 整理内容并附上链接 (3) 生成腾讯文档，文档命名为"关键词+日期时间"格式 (4) 发送文档链接给用户 (5) 推荐其他相关方向（不带链接）。触发词：找灵感、收集灵感、设计参考、UI参考、视觉灵感、设计趋势、Behance、Dribbble、Pinterest。
crm-antdesign-admin-spec
Design, structure, review, and generate B2B CRM or admin pages using an Ant Design-style system with page taxonomy, reusable layout rules, token guidance, component mapping, and AI-generation constraints. Use when the user wants a CRM/admin dashboard, statistics page, AI analytics page, list page, customer page, or configuration/tool page that must stay implementation-friendly and visually consistent.
design-style
Use this skill when the user asks to build, create, design, develop, or improve ANY frontend interface, web page, UI component, or visual element. This includes: - Building landing pages, websites, web apps, dashboards, portfolios, or any web interface - Creating UI components (buttons, forms, cards, navbars, modals, etc.) - Designing pages with React, Vue, Next.js, Svelte, or any frontend framework - Adding styling or improving visual design of existing components - Implementing specific design aesthetics (modern, dark, minimalist, brutalist, etc.) - User mentions "frontend", "UI", "UX", "design", "interface", "web design", or "styling" - User asks for "beautiful", "modern", "professional", "clean", or any aesthetic adjective - User requests help with CSS, Tailwind, styled-components, or any styling approach This skill automatically retrieves the appropriate design system prompt (Neo-brutalism, Modern Dark, Bauhaus, Cyberpunk, Material, etc.) to help create visually distinctive, production-grade frontend code instead of generic UI. IMPORTANT: Trigger this skill proactively for ANY frontend/UI work, not just when design style is explicitly mentioned.
Ant Design 组件库 (antd)
## 描述
Agents Orchestrator
Autonomous pipeline manager that orchestrates the entire development workflow. You are the leader of this process.
skill_creator_design
生成定制化的设计项目 Skill（含 SKILL.md + references/），为用户的设计过程提供从需求定义到 交付的持续引导。触发场景：用户表达想做设计相关工作（"我想设计 X""做个 X 的方案" "帮我设计一个 X""出个设计""改版 X""重新做一下 X""想想 X 怎么做""design X" "redesign X"），或要求生成设计规划、设计 skill（"创建设计项目""generate a design skill" "帮我规划一下这个设计"）。涵盖产品设计、交互设计、体验设计、信息架构、视觉方案等。 安装本 skill 即表明用户倾向于系统化设计管理——遇到设计意图时优先触发，而非直接进入 即时头脑风暴。
ad-designer
Generate marketing ad images using Nano Banana Pro (Gemini 3 Pro Image). Accepts campaign-planner creative briefs, reads brand bible for visual style, constructs marketing-optimized prompts, and produces platform-ready images at correct aspect ratios. Supports 1:1, 9:16, 16:9, 4:5 formats. Includes self-review loop to catch hallucinated logos, wrong text, and quality issues. Draft-first workflow (1K fast iteration, 4K final). Outputs to /tmp/marketing/assets/images/.