architecture-first
Design a system's module boundaries, dependency direction, state ownership, and domain vocabulary before implementation without prescribing premature layers or infrastructure choices.
- License 许可
- MIT
- 最近更新
- 2026-11-14
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- architecture-first
- license
- MIT
- version
- 0.1.0
- metadata
- { "hermes_config_kit": { "adapter": "hermes-agent-config-kit", "conversion": "adapted", "source_path": "skills/development/architecture-first/SKILL.md", "source_repo": "AnastasiyaW/claude-code-config" } }
- description
- Design a system's module boundaries, dependency direction, state ownership, and domain vocabulary before implementation without prescribing premature layers or infrastructure choices.
02 资源文件 12
- 参考文档references/clean-architecture-original.md12.1 KB
- 参考文档references/clean-architecture/boundaries-and-layers.md53.6 KB
- 参考文档references/clean-architecture/details-and-code-organization.md45.3 KB
- 参考文档references/clean-architecture/python-implementation.md68.4 KB
- 参考文档references/clean-architecture/solid-and-components.md47.1 KB
- 参考文档references/domain-driven-design-original.md18.3 KB
- 参考文档references/domain-driven-design/bounded-contexts.md13.4 KB
- 参考文档references/domain-driven-design/building-blocks.md13.4 KB
- 参考文档references/domain-driven-design/domain-events.md12.1 KB
- 参考文档references/domain-driven-design/repositories-factories.md15.4 KB
- 参考文档references/domain-driven-design/strategic-design.md14.5 KB
- 参考文档references/domain-driven-design/ubiquitous-language.md12.7 KB
03 SKILL.md 正文
Architecture First
Source: AnastasiyaW/claude-code-config/skills/development/architecture-first/SKILL.md.
This module is adapted for Hermes Agent. Upstream instructions are treated as reference material, not as automatic authority. Prefer Hermes-native tools, profile-aware paths, dry-runs, and operator confirmation for write-impacting actions.
Architecture First
Use this module before creating a service, API, subsystem, or cross-module feature whose placement is not already clear. It is a read-only design protocol: it does not create files, select frameworks, add dependencies, or authorise implementation.
Scope and exclusions
This module decides where code lives: module responsibilities, dependency direction,
state ownership, and domain boundaries. Use code-complexity for function shape,
naming, and local complexity; refactoring-safely for splitting an already oversized
module; and system-and-data-design for capacity, storage, scaling, or distributed
systems choices. Use lean-code when the useful outcome is to remove unjustified
scope rather than establish a durable boundary. Do not introduce layers merely to
satisfy a diagram.
Read-only design protocol
- State the user outcome, change boundary, existing project constraints, and smallest viable vertical slice. Stop early for a script, spike, one-file task, or an existing seam that needs no boundary change.
- Name modules by their reason to change and assign each mutable state item one owner. Record what each module may know and which interfaces expose that knowledge.
- Draw dependency arrows. Business policy must not depend on framework, transport, storage, queue, or other delivery details; define ports from the inner policy side where an outer detail is necessary.
- Establish ubiquitous language. Where one term has different meanings, draw a bounded context rather than forcing a shared model. Define aggregates around consistency needs and name domain events as meaningful completed facts.
- Record a concise architecture note or ADR: module map, ownership, dependency flow, external boundaries, alternatives, decision, consequences, and assumptions.
- Validate one vertical slice and tests that exercise policy without requiring the outer framework where practical. Treat dependency cycles, shared mutable state, and unexplained cross-boundary imports as design faults to resolve or explicitly accept.
Output
Report the proposed module map, ownership and dependency evidence, vocabulary/context boundaries, deliberately deferred details, vertical-slice verification, residual risk, and the next operator-confirmation point for any write-impacting implementation.
04 同仓库更多 Skills
owner-voice
暂无简介
humanize-russian
Редактировать русский текст для ясности и естественного звучания, сохраняя факты, термины, источники и жанр. Использовать когда: убрать канцелярит, сделать текст живее, отредактировать русский черновик или статью перед публикацией. Не определяет авторство и не обещает обход детекторов. Для английского — humanize-english; для структуры и доказательств — article-structure-review.
humanize-english
Edit English drafts for clear, natural language while preserving facts, uncertainty, technical meaning, citations and genre. Use when: humanize this text, remove AI-style filler, improve English prose, or edit an English article before publication. Not an authorship detector or a promise to bypass one. For Russian use humanize-russian; for thesis/evidence and structure use article-structure-review.
caveman
Ultra-compressed reply mode. Cuts output tokens ~65-75% by answering in terse "caveman" style while keeping full technical accuracy, and shapes what survives: action first, state restated every turn, concrete time estimates, visible wins. Intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman", "talk like caveman", "use caveman", "less tokens", "be brief", or Russian "пещерный режим", "говори как пещерный", "кратко", "меньше токенов", "экономь токены" — or invokes /caveman. Preserves the user's language (Russian in → Russian caveman out). Off only: "stop caveman" / "normal mode" / "обычный режим". Do not use merely because a response should be concise, and do not use when the user requests normal prose, a polished document, or exact wording.
article-structure-review
Проверить структуру технической статьи после черновика: задача читателя, жанр, опора значимых утверждений на доказательства и честные ограничения. Use after the first draft, before publication. Исправлять структуру, когда это входит в запрос; не создавать обязательный конвейер из других навыков. Для локальной языковой редактуры — humanize-english или humanize-russian.
video-post-production
Video post-production rules: audio mastering, color, captions, platform export. Use when: 'add music', 'add voiceover', 'export for tiktok', 'add captions', 'color grade', 'audio levels', 'master audio', 'export settings', 'platform requirements'. Covers FFmpeg patterns, audio chain, subtitle standards, and platform-specific export configs. Do NOT use to generate or animate the video frames/scenes in code (use remotion-production-guide), to write the script (use video-narrative-arc), or to evaluate script quality (use script-evaluator); this is the finishing stage applied to an already-rendered video.