Nuclear Grade Context Engineering
AI agents now operate with authority. Authority without discipline is how complex systems fail. Nuclear’s control loop, ported to AI-assisted software engineering.
供给资产档案
编程与开发 Agent
代码审查、仓库分析、测试、CI、GitHub、DevOps 与开发工作流 Skill。
场景
GitHub automation
I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.
适配 Agent
Claude Code + CLI + Codex
适用于 Codex、Claude Code、Cursor、CLI 或自定义 Agent。
安装
就绪
npx skills add FlyFission/nuclear-grade-context-engineering
维护状态
新鲜
距上次推送 21 天
风险
高风险
Potential broker, wallet, exchange, or real-money execution surface; sandbox and explicit approval are required
GitHub 质量
32
75/100 质量 · 78/100 信任
覆盖标签
审查说明
Potential broker, wallet, exchange, or real-money execution surface; sandbox and explicit approval are required · Low GitHub adoption signal
Agent 采用评分卡
一眼查看信任、审计与安装准备度
这些分数综合公开仓库元数据、OpenAgentSkill 审查信号、维护新鲜度与安装准备度。它用于候选筛选，不替代人工审查。
质量
强可靠的选择，值得加入生产工作流候选列表。
信任
仅限沙盒有用但信任信号不足或混杂的候选项。在结果闭环证明任务匹配前，请保持在隔离工作区内使用。
审计
高风险对安装准备度、安全元数据、维护情况与采用风险的机器可读审查。
OpenAgentSkill 信任评分 v5
仅限沙盒
仅在沙盒中运行，并在用于真实工作前比较接近的替代方案。
Stars
32 个 GitHub Stars
仓库活跃度
32 个 Star，0 个 Fork
维护状态
距上次推送 21 天
许可证
MIT
安装
npx skills add FlyFission/nuclear-grade-context-engineering
安装安全性
标准软件包或运行时安装路径
权限范围
shell or command execution, filesystem or document access
Agent 结果
暂未有 Agent 结果数据
文档
README/SKILL.md 上下文充分
风险摘要
生产前审查
- This skill may touch real-money trading, broker, wallet, or exchange operations; use only in a sandbox with explicit approval.
- Low GitHub adoption signal
- Quality score needs review
- GitHub adoption: 32 GitHub stars
安装准备度
安装路径可用
- 安装路径可用
- 仓库证据可用
- 已声明许可证
- 暂无 Agent 验证结果证据
Agent 可读元数据
这个 Skill 的机器可读决策数据。
使用此区块或内嵌 JSON 判断 Agent 是否应安装该 Skill、选择替代方案，或先请求人工审查。
适用任务
- GitHub automation 工作流
- Claude Code 团队
- builders willing to evaluate younger projects
- Inspect repository metadata
适用 Agent
安装决策
- 命令
- npx skills add FlyFission/nuclear-grade-context-engineering
- 策略
- 阻止
- 人工审查
- 是
信任与风险
- 信任
- 70/100
- 审计
- 83/100
- 风险级别
- 高风险
结果闭环
- 端点
- /api/agent/outcome
- 事件 ID
- resolve
- 结果
- 5
不适用场景
- 需要厂商支持 SLA 的团队
- production agents without a repository review
- Low GitHub adoption signal
- Audit risk risky exceeds max_risk=medium
- 高风险权限提示：Shell 或命令执行
Agent 安全 v2
55/100 · 避免自动安装
This skill should not be selected by an agent without explicit human security review.
Do not auto-install. Inspect the source, dependencies, and permission surface first.
高
Shell 或命令执行
Skill 元数据引用了终端、CLI、Shell、子进程或命令执行工作流。
中
网络访问
Skill 可能访问远程页面、API、仓库或外部服务。
中
文件系统访问
Skill 可能读取或写入项目文件、文档、生成产物或本地工作区状态。
- Audit risk risky exceeds max_risk=medium
- 高风险权限提示：Shell 或命令执行
- Potential broker, wallet, exchange, or real-money execution surface; sandbox and explicit approval are required
安装目标
在你的 Agent 工作流中安装此 Skill
通过公开安装端点获取命令、安全清单、目标提示词和该 Skill 的规范链接。
OpenAgentSkill CLI
Resolve policy, run the source installer safely, and report a verified install receipt.
$ npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install flyfission-nuclear-grade-context-engineeringAgent 解析计划
让 Agent 在安装前验证匹配度。
Resolve API 返回首选 Skill、替代方案、安全策略、审计说明、安装目标和可直接执行的提示词，无需抓取此页面。
打开 JSON
/api/agent/resolve?task=Use%20Nuclear%20Grade%20Context%20Engineering%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Resolve 文本
/api/agent/resolve?task=Use%20Nuclear%20Grade%20Context%20Engineering%20for%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text
安装交接
/api/skills/flyfission-nuclear-grade-context-engineering/install
Agent 应检查
- 从 Resolve API 检查任务匹配与替代方案。
- 检查审计评分、信任评分和安全策略警告。
- 检查 Codex、Claude Code、Cursor 或 CLI 的安装目标兼容性。
复制提示词
Task: Use Nuclear Grade Context Engineering in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20Nuclear%20Grade%20Context%20Engineering%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/flyfission-nuclear-grade-context-engineering/install
Install command: npx skills add FlyFission/nuclear-grade-context-engineering
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.Agent 交接
把安装路径交给 Agent，而不是再给一个目录页。
通过公开安装端点获取命令、安全清单、目标提示词和该 Skill 的规范链接。
安装交接
/api/skills/flyfission-nuclear-grade-context-engineering/install
LLM 文本格式
/api/skills/flyfission-nuclear-grade-context-engineering/install?format=text
寻找替代方案
/api/skills/search?q=Nuclear%20Grade%20Context%20Engineering&limit=3
Agent 提示词
Use Nuclear Grade Context Engineering for this task. Review https://www.openagentskill.com/api/skills/flyfission-nuclear-grade-context-engineering/install, then install with: npx skills add FlyFission/nuclear-grade-context-engineeringRegistry 元数据
用于自动选择 Skill 的 Agent 可读档案。
本页通过 Registry API 提供相同的决策、信任、审计、场景和安装信号，让 Agent 无需抓取界面即可排序。
Manifest
/api/registry/manifest/flyfission-nuclear-grade-context-engineering
LLM 文本
/api/registry/manifest/flyfission-nuclear-grade-context-engineering?format=text
安装别名
/api/registry/install/flyfission-nuclear-grade-context-engineering
推荐
/api/registry/recommend?task=Use%20Nuclear%20Grade%20Context%20Engineering%20in%20an%20agent%20workflow&limit=3
Agent 决策面板
Companion skill for GitHub automation
将此 Skill 加入候选列表，并在生产使用前与相近替代方案比较。
栈中角色
辅助 Skill
主要匹配
GitHub automation
信任标签
强候选
安装路径
命令已就绪
适用场景
- GitHub automation 工作流
- Claude Code 团队
- builders willing to evaluate younger projects
证据
- 仓库近期活跃
- 已提供安装命令或 GitHub 仓库
- 75/100 质量档案
- 4 个 OpenAgentSkill 交互事件
先审查
- Low GitHub adoption signal
实施路径
- 1在沙盒 Agent 中安装它，并端到端完成一次GitHub automation任务。
- 2Compare output quality, latency, and failure behavior against at least one alternative.
- 3Promote it into production only after reviewing repository permissions, license, and maintenance signals.
信任档案
仅限沙盒
有用但信任信号不足或混杂的候选项。在结果闭环证明任务匹配前，请保持在隔离工作区内使用。
GitHub 采用度
检查32 个 GitHub Stars
Star/Fork 活跃度
检查32 个 Star，0 个 Fork; 当前元数据中没有议题活跃度信息
近期维护
通过距上次推送 21 天
许可证清晰度
通过MIT
积极信号
- AI 审查已通过
- 安装路径可用
- 仓库证据可用
- 近期维护的仓库
- 安装命令未发现明显高风险模式
- 结果闭环已就绪，但需要首次真实 Agent 运行
安装前审查
- This skill may touch real-money trading, broker, wallet, or exchange operations; use only in a sandbox with explicit approval.
- Low GitHub adoption signal
- Quality score needs review
- GitHub adoption: 32 GitHub stars
- Stars/forks activity: 32 stars, 0 forks; issue activity unavailable in current metadata
- 暂未有真实 Agent 结果报告
- 无人值守安装前需要人工审查
建议操作
仅在沙盒中运行，并在用于真实工作前比较接近的替代方案。
质量档案
强 适用于 Agent 工作流的候选
可靠的选择，值得加入生产工作流候选列表。
工作流匹配
在这些场景使用此 Skill
Manage repositories
GitHub automation
I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.
Build and ship code
Coding agents
I need a coding agent that can understand a repository, edit code, and review pull requests.
Automate repeated work
Workflow automation
I need my agent to automate a repeated workflow across tools and files.
工作流匹配
加入完整工作流
Inspect, patch, and verify code
Coding review agent
A workflow for software agents that inspect repositories, review pull requests, generate tests, and turn findings into shippable patches.
Turn skills into distribution
Content growth agent
A workflow for turning newly indexed skills into SEO briefs, social drafts, comparison pages, and reusable publishing workflows.
Design, build, test, and ship interfaces
Frontend and UI
A practical workflow for agents that turn product briefs or Figma designs into polished frontend code, review the result, test it in a browser, and prepare a safe deployment.
替代方案短名单
安装前对比
可能适合该任务的相近 Skill。
Khazix Skills
A collection of practical, installable AI agent skills for disk cleanup, AI news retrieval, and project management, following the Agent Skills standard.
Awesome Claude Skills
A curated list of resources and tools for enhancing Claude AI workflows.
Claude Scientific Skills
A comprehensive collection of ready-to-use scientific and research skills for AI agents.
概览
<div align="center">
<img src="docs/assets/landing-banner.svg" alt="Nuclear-grade Context Engineering: let AI do serious software work and stay in control of what ships. Go fast while exploring; slow down when the work becomes a promise." width="820">
<br/>
**A simple, evidence-first way to let AI do serious software work and stay in control of what ships.**
[](https://github.com/FlyFission/nuclear-grade-context-engineering/actions/workflows/ci.yml) [](LICENSE) [](pyproject.toml) [](#quick-start) [](CONTRIBUTING.md)
</div>
# Nuclear Grade Context Engineering
AI agents no longer just suggest code. They edit files, change prompts, call tools, swap dependencies, write the evidence, and help ship releases. That is a lot of power with very little ceremony. Nuclear-grade gives that work a clear path you stay in control of, so you can move fast and still stand behind what ships.
You do not need to read the whole repo to start. Run one command in [See it work, then make it yours](#see-it-work-then-make-it-yours), copy one folder, and add the rest only when a change earns it.
## Why this exists
I have spent over a decade in the nuclear field, and I run [FlyFission Consulting Group](https://flyfission.com/), an independent design-review and advisory practice for nuclear projects. I build software and agentic engineering workflows and tools for the nuclear and other mission-critical industries, where mistakes carry real consequences and "fail forward" is far less optional than it is in ordinary software. That same conviction drives [AscertAIn](https://ascertain.it/), an AI-powered e
平台兼容性
技术详情
- 版本
- 1.0.0
- 许可证
- MIT
- 最近更新
- 2026年8月18日
- 发布时间
- 2026年8月1日
框架与工具
决策摘要
辅助 Skill
仓库近期活跃
Agent 验证证据
Agent 验证证据
来自解析、审查、安装和一次小范围运行后的结果报告。
- 成功率
- —
- 近期失败
- —
- 结果
- 0
- 输出质量
- —
- 失败
- 0
- 不相关
- 0
- 安装次数
- 0
- 风险拦截
- 0
- 需要配置
- 0
- 生产环境
- 0
暂时没有 Agent 结果数据。首次 Agent 执行可以通过 /api/agent/outcome 报告成功、需要设置、风险拦截、失败或不相关。
增长闭环
分享工具包
为 Nuclear Grade Context Engineering 准备的场景化草稿，可手动发布到 X。
Nuclear Grade Context Engineering: AI agents now operate with authority. Authority without discipline is how complex systems fai... 32 stars https://www.openagentskill.com/skills/flyfission-nuclear-grade-context-engineering?ref=x
可选：带安装命令的回复
Listing + install path for Nuclear Grade Context Engineering: https://www.openagentskill.com/skills/flyfission-nuclear-grade-context-engineering?ref=x Install: npx skills add FlyFission/nuclear-grade-context-engineering
收录来源
社区收录
此列表来自公开来源，维护者认领获批前不会标记为官方。
- 创作者
- FlyFission
- 收录方
- OpenAgentSkill 社区索引
归属链接指向公开仓库或创作者主页。创作者可认领列表以更新所有权信号。
认领此 Skill所有者认领
认领此 Skill 页面
这条 社区收录 列表归属于 FlyFission，但尚未标记为官方。认领后可增加已验证所有者信号，使后续发布、安装和审计更新更值得信赖。
创作者外链工具包
将证据徽章加入你的 README
在开发者评估仓库的位置展示规范页面、当前信任与审计信号，以及真实的 Agent 验证证据。
[](https://www.openagentskill.com/skills/flyfission-nuclear-grade-context-engineering)
[](https://www.openagentskill.com/skills/flyfission-nuclear-grade-context-engineering)
[](https://www.openagentskill.com/skills/flyfission-nuclear-grade-context-engineering/audit)
[](https://www.openagentskill.com/skills/flyfission-nuclear-grade-context-engineering)作者
FlyFission
@flyfission
平台适配
健康信号
- GitHub Stars
- 32
- 质量评分
- 48/100
- 最近 GitHub 推送
- 2026年8月1日
- 框架提示
- 1
- OpenAgentSkill 浏览量
- 4
- 复制安装命令
- 0
- 跳转点击
- 0
社区信号
告诉我们这个 Skill 是否对你的 Agent 工作流有帮助。汇总反馈会持续改善排序。
信任与安全
仅限沙盒
- GitHub 采用度32 个 GitHub Stars检查
- Star/Fork 活跃度32 个 Star，0 个 Fork; 当前元数据中没有议题活跃度信息检查
- 近期维护距上次推送 21 天通过
- 许可证清晰度MIT通过
- README/SKILL.md 完整度元数据包含足够的用法与工作流上下文通过
- 依赖与运行时风险公开元数据中未发现主要依赖风险提示通过
相关 Skill
Khazix Skills
A collection of practical, installable AI agent skills for disk cleanup, AI news retrieval, and project management, following the Agent Skills standard.
19.6K StarsAwesome Claude Skills
A curated list of resources and tools for enhancing Claude AI workflows.
65.9K StarsClaude Scientific Skills
A comprehensive collection of ready-to-use scientific and research skills for AI agents.
31.2K Stars