Transcribes local audio into Markdown with Gemini 3.5 Transcribe, including speaker labels and provider timestamps. Use for interviews, meetings, lectures, podcasts, voice notes, and similar recordings.
中文简介正在准备中。当前显示原文说明。
Maintains project domain language, context maps, diagrams, and architectural decisions under ai-artifacts. Use when clarifying terminology, bounded contexts, or durable design decisions.
中文简介正在准备中。当前显示原文说明。
实测评分 未实测
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Actively build and sharpen the project's domain model as you design. This is the active discipline—challenging terms, inventing edge-case scenarios, visualizing relationships, and writing the glossary and decisions down when they crystallize. Merely reading ai-artifacts/CONTEXT.md for vocabulary is not this skill; this skill is for changing the model, not just consuming it.
Keep agent-authored project knowledge under ai-artifacts/. This includes context glossaries, context maps, ADRs, plans, specs, analyses, reports, reviews, and other Markdown primarily created for or by an LLM.
Use another location only when the user or repository explicitly requires it, such as a human-facing README.md or established product documentation. Do not relocate existing documentation unless asked.
Embed ASCII or Mermaid diagrams directly in the Markdown they explain. Do not create standalone diagram files.
Most repositories have a single context:
/
├── ai-artifacts/
│ ├── CONTEXT.md
│ └── docs/
│ └── adr/
│ ├── 0001-event-sourced-orders.md
│ └── 0002-postgres-for-write-model.md
└── src/
If ai-artifacts/CONTEXT-MAP.md exists, the repository has multiple contexts:
/
├── ai-artifacts/
│ ├── CONTEXT-MAP.md
│ ├── docs/
│ │ └── adr/ ← system-wide decisions
│ └── src/
│ ├── ordering/
│ │ ├── CONTEXT.md
│ │ └── docs/adr/ ← context-specific decisions
│ └── billing/
│ ├── CONTEXT.md
│ └── docs/adr/
└── src/ ← application source code
ai-artifacts/src/ mirrors the source tree only to make context ownership obvious. Application code remains in the repository's real source directories.
Create files lazily—only when there is something worth recording. Create ai-artifacts/CONTEXT.md when the first term is resolved. Create an ADR directory when the first qualifying decision is made. Create ai-artifacts/CONTEXT-MAP.md only when the project has multiple genuine contexts.
When the user uses a term that conflicts with the relevant CONTEXT.md, call it out immediately. "Your glossary defines 'cancellation' as X, but you seem to mean Y—which is it?"
When the user uses vague or overloaded terms, propose a precise canonical term. "You're saying 'account'—do you mean the Customer or the User? Those are different things."
When domain relationships are being discussed, stress-test them with specific scenarios. Invent scenarios that probe edge cases and force the user to be precise about boundaries between concepts.
When the user states how something works, check whether the code agrees. If you find a contradiction, surface it: "Your code cancels entire Orders, but you just said partial cancellation is possible—which is right?"
Include an embedded diagram when boundaries, relationships, states, or flows are easier to understand visually.
When a term or relationship is resolved, update the relevant file under ai-artifacts/ immediately. Do not batch resolved domain knowledge. Use CONTEXT-FORMAT.md.
A CONTEXT.md is a glossary, not a spec, scratch pad, or implementation guide. Its diagrams may show conceptual relationships, boundaries, and states, but must not contain implementation details.
Only offer to create an ADR when all three are true:
If any condition is missing, skip the ADR. Use ADR-FORMAT.md.
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。
Transcribes local audio into Markdown with Gemini 3.5 Transcribe, including speaker labels and provider timestamps. Use for interviews, meetings, lectures, podcasts, voice notes, and similar recordings.
中文简介正在准备中。当前显示原文说明。
Design engineering principles for making interfaces feel polished. Use when building UI components, reviewing frontend code, implementing animations, hover states, shadows, borders, micro-interactions, enter/exit animations, choosing or reviewing icons, or any visual detail work. Triggers on UI polish, design details, "make it feel better", "feels off", stagger animations, theme switch transitions, border radius, optical alignment, image outlines, box shadows, icons, icon stroke weight, icon states, motion restraint.
中文简介正在准备中。当前显示原文说明。
Explores and validates a feature, component, workflow, or behavior change before implementation. Use when work needs clarified intent, compared approaches, and an approved direction.
中文简介正在准备中。当前显示原文说明。
Restates the previous response in plain, concise language. Use only when the user invokes bro or explicitly asks for a simpler explanation.
中文简介正在准备中。当前显示原文说明。
Generates or edits raster images through OpenAI's Image API. Use for text-to-image work, reference-based edits, masks, transparent assets, and product or editorial visuals.
中文简介正在准备中。当前显示原文说明。
Applies language-neutral engineering standards when writing or reviewing code, especially around boundaries, failures, domain models, dependencies, tests, and type safety.
中文简介正在准备中。当前显示原文说明。