gate-audit
Use this skill when the user provides AF2, ESMFold, AF3, Boltz-1, SASA, or MD results and needs a Gate 1-4 audit with a Go/Hold/Kill decision.
Best use case
gate-audit is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Use this skill when the user provides AF2, ESMFold, AF3, Boltz-1, SASA, or MD results and needs a Gate 1-4 audit with a Go/Hold/Kill decision.
Teams using gate-audit 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/gate-audit/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How gate-audit Compares
| Feature / Agent | gate-audit | 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 provides AF2, ESMFold, AF3, Boltz-1, SASA, or MD results and needs a Gate 1-4 audit with 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.
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
SKILL.md Source
# Purpose 用于纳米载体疫苗计算设计中的结构、暴露、MD 与终审门禁判定。 本 skill 专门负责 Gate 1–4 的证据整理与 Go / Hold / Kill 判断。 # When to use 当用户提供以下任一信息时调用： - AF2 / ESMFold / AF3 / Boltz-1 预测结果。 - SASA / 表位暴露结果。 - 2–5 ns 平衡审计结果。 - 100 ns MD 结果。 - checkpoint、日志、NPT 密度、RMSD、Rg、关键距离等摘要。 # Audit dimensions 必须分开检查以下五项： 1. 结构可行性 2. 表位可及性 3. 动力学稳定性 4. 工程可制造性 5. 是否值得进入更昂贵计算 # Required checks ## Gate 1 - 结构拓扑是否合理 - 关键区段是否断裂 - linker 与展示端是否冲突 - 是否存在明显界面错误 ## Gate 2 - 表位是否动态可及 - 是否长期遮挡 - SASA 是否支持进入 MD - 是否存在构象塌陷导致暴露丢失 ## Gate 3 - 2–5 ns 是否达到基本平衡 - 温度、压力、密度是否正常 - 是否存在日志缺失、checkpoint 缺失、输出文件异常 - 是否存在爆炸、持续漂移、异常离子行为 ## Gate 4 - 100 ns 是否优于负对照或历史基线 - repeat 间是否趋势一致 - 长程下表位是否保持暴露 - 是否具备进入 CpHMD / TI-FEP 资格 # Required output format 1. 输入结果摘要 2. Gate 1 判定 3. Gate 2 判定 4. Gate 3 判定 5. Gate 4 判定 6. 主要失败模式 7. 决策：Go / Hold / Kill 8. 需要补跑的数据 # Default decision logic - 只要存在关键日志缺失、checkpoint 异常或体系健康不明，默认 Hold。 - 若结构逻辑不成立或表位长期不可及，默认 Kill。 - 只有在结构、暴露、动力学三者同时满足时，才 Go。 - CpHMD 和 TI/FEP 仅作为高级终审，不得作为补救一切问题的默认手段。 # Warnings - 不得用单次最佳轨迹替代重复结果。 - 不得只用单个评分指标下结论。 - 不得忽略失败日志。 - 不得把高模型置信度当作物理正确性。
Related Skills
Payroll Compliance Auditor
Run a full payroll audit in under 10 minutes. Catches the errors that cost companies $845 per violation.
Energy Audit — Commercial Building Assessment
Run a full energy audit for commercial or industrial facilities. Identifies waste, models savings, and generates a prioritized retrofit roadmap with ROI timelines.
Compliance & Audit Readiness Engine
Your AI compliance officer. Guides startups and scale-ups through SOC 2, ISO 27001, GDPR, HIPAA, and PCI DSS — from zero to audit-ready. No consultants needed.
Compliance Audit Generator
Run internal compliance audits against major frameworks without hiring a consultant.
Cloud Cost Optimization Audit
Analyze cloud infrastructure spend across AWS, Azure, and GCP. Identify waste, rightsizing opportunities, and reserved instance savings.
AI Spend Audit
Audit your company's AI spending — find waste, measure ROI, and right-size your tool stack.
AI Safety Audit
Comprehensive AI safety and alignment audit framework for businesses deploying AI agents. Built around the UK AI Security Institute Alignment Project standards (2026), EU AI Act requirements, and NIST AI RMF.
SX-security-audit
全方位安全审计技能。检查文件权限、环境变量、依赖漏洞、配置文件、网络端口、Git 安全、Shell 安全、macOS 安全、密钥检测等。支持 CLI 参数、JSON 输出、配置文件。当用户要求"安全检查"、"漏洞扫描"、"权限检查"、"安全审计"时使用此技能。
Skill Audit 🔍
扫描 OpenClaw skills 中的安全风险，防止供应链攻击。
website-audit
Website Audit mit 230+ Rules für SEO, Performance, Security, Technical und Content Issues. LLM-optimierte Reports mit Health Scores und Handlungsempfehlungen.
claude-audit
Full project audit — launches 5 parallel AI agents (security, bugs, dead code, architecture, performance) to scan your codebase read-only, then compiles a unified report with health grade (A+ to F) and offers surgical fixes. Language-agnostic. Zero config.
psyke-audit
Produce a branded Psyke SEO & GEO audit deck for any website. Use when asked to run an SEO audit, GEO audit, site audit, or website health check for a Psyke client. Also use when someone mentions "psyke audit", "run an audit", "audit this site", "SEO score", "GEO readiness", or "AI visibility audit". Outputs a single index.html slide deck with dual scoring (SEO Health /100 + GEO Readiness /100), competitor benchmarking, AI citation analysis, and Psyke-branded dark-mode theme.