Use Ontoly Software Graph evidence, CLI reports, MCP, and official Ontoly Agent Skills before searching source files when reviewing architecture, dependencies, request flows, configuration, impact, or security-sensitive ownership.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Use this skill when the user asks Codex to understand a TypeScript repository's architecture, dependency graph, request flow, service ownership, configuration usage, impact radius, package topology, or security-sensitive code paths.
Ontoly is a deterministic Software Graph compiler. It does not answer questions with AI. It builds graph evidence that Codex can query before falling back to source search.
Check whether .ontoly/SoftwareGraph.json exists.
If the graph is missing or stale, ask before installing dependencies or writing generated graph files. Then run:
pnpm add -D @0xsarwagya/ontoly-cli
pnpm ontoly build .
Inspect graph quality before answering:
pnpm ontoly coverage .
pnpm ontoly stats .
Prefer Ontoly graph queries before repository-wide source search:
pnpm ontoly architecture --json
pnpm ontoly report dependencies --format markdown
pnpm ontoly report routes --format markdown
pnpm ontoly query impact <node-id>
pnpm ontoly trace <node-id-or-name>
Start Ontoly MCP when the environment supports MCP-backed tools:
pnpm ontoly mcp
Use source files only when the graph is missing, stale, low confidence, or insufficient for the question.
When answering, cite graph evidence:
Never claim certainty beyond Ontoly evidence. If graph coverage is incomplete, say exactly which part is inferred or unresolved.
Ontoly publishes task-specific Agent Skills in its own repository. To inspect or install them with the open skills CLI:
npx skills add 0xsarwagya/ontoly --list
npx skills add 0xsarwagya/ontoly --skill architecture-review
npx skills add 0xsarwagya/ontoly --skill impact-analysis
npx skills add 0xsarwagya/ontoly --skill request-tracing
Use those official skills when the task maps directly to one of their workflows.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Use AtomLane to compile and execute safe atomic parallel plans on macOS and native Windows Preview for worthwhile independent argv tasks, dependency DAGs, supported platform entrypoints, or Apple-silicon operators. Use at task start or an execution boundary when structured local work may contain two or more worthwhile units; skip plain answers, one quick command, and work whose effects cannot be safely bounded.
中文简介正在准备中。当前显示原文说明。
Register a deferred decision in the debt registry. Trigger by judgment, not a marker scan, whenever a future reader would ask "why this way?": an unmade decision, stub, loosened type, bypassed check, swallowed error, a default picked "for now", or a TODO/FIXME/HACK/XXX marker. Trigger immediately whenever you defer work, or when the user invokes $add. Over-register freely; the developer drops with "drop A", "drop A,C", or "drop all".
中文简介正在准备中。当前显示原文说明。
ADK 框架适配层。为 LangChain / EINO / AutoGen / AgentScope / CrewAI 提供框架特定的 代码模板、惯用模式、API 映射和项目结构，供 agent-dev-workshop Phase 5 代码生成使用。 每个框架 reference 文件标注 verified_date 用于版本锁定。
中文简介正在准备中。当前显示原文说明。
中文调试修复技能。用于报错、测试失败、页面异常、功能不符合预期、需要定位根因并做最小修复时。触发语包括"进入调试模式""帮我修问题""报错了""测试失败""页面坏了""找根因"。
中文简介正在准备中。当前显示原文说明。
交互式 AI Agent 开发工作坊：通过 6 阶段深度协作对话，引导用户完成 Agent 需求分析、架构设计、 工具定义、Prompt 与编排设计、代码生成、验证迭代，产出可直接运行的 Agent 项目。 框架无关设计优先，支持 LangChain / EINO / AutoGen / AgentScope / CrewAI 等 ADK 框架。
中文简介正在准备中。当前显示原文说明。
中文漂移审计技能。用于项目或学习过程变乱、上下文漂移、任务分叉、多个方案冲突、命名不一致、Codex 可能顺手改多了时。触发语包括"漂移检查""感觉跑偏了""项目变乱了""检查是否失控""分叉太多""上下文漂移"。
中文简介正在准备中。当前显示原文说明。