docs: simplify hero architecture diagram
This commit is contained in:
yaojingang
@@ -24,49 +24,23 @@ It turns rough workflows, transcripts, prompts, notes, and runbooks into reusabl
|
||||
|
||||
## Architecture
|
||||
|
||||
The system is intentionally layered so users can understand it from top to bottom: route first, choose method second, validate third, then package and govern the result.
|
||||
Hero view: turn messy operational input into a governed, reusable skill package through one compact flow.
|
||||
|
||||
```mermaid
|
||||
flowchart TD
|
||||
A["Inputs<br/>workflows / prompts / transcripts / docs / notes"] --> B["Router<br/>SKILL.md"]
|
||||
B --> C["Method Layer<br/>references/"]
|
||||
B --> D["Authoring Flow<br/>scripts/yao.py"]
|
||||
|
||||
C --> C1["Archetypes"]
|
||||
C --> C2["Gate Selection"]
|
||||
C --> C3["Non-Skill Decision"]
|
||||
C --> C4["Operating Modes"]
|
||||
C --> C5["Governance"]
|
||||
C --> C6["Resource Boundaries"]
|
||||
|
||||
D --> E["Create<br/>init / template"]
|
||||
D --> F["Validate<br/>lint / boundary / governance"]
|
||||
D --> G["Evaluate<br/>trigger / suites / judge / confusion"]
|
||||
D --> H["Promote<br/>promotion policy / candidate registry"]
|
||||
D --> I["Package<br/>neutral source -> target adapters"]
|
||||
D --> J["Report<br/>history / scorecards / context / portability"]
|
||||
|
||||
E --> K["Skill Package"]
|
||||
F --> K
|
||||
G --> L["evals/"]
|
||||
H --> M["reports/"]
|
||||
I --> N["dist/ or target outputs"]
|
||||
|
||||
K --> K1["SKILL.md"]
|
||||
K --> K2["agents/interface.yaml"]
|
||||
K --> K3["manifest.json"]
|
||||
K --> K4["optional references / scripts / evals / reports"]
|
||||
|
||||
L --> M
|
||||
flowchart LR
|
||||
A["Inputs<br/>workflow / prompt / transcript / docs / notes"] --> B["Route<br/>SKILL.md"]
|
||||
B --> C["Design<br/>method + gates"]
|
||||
C --> D["Run<br/>create / validate / eval / promote"]
|
||||
D --> E["Outputs<br/>skill package + reports + adapters"]
|
||||
```
|
||||
|
||||
Read the diagram in five layers:
|
||||
Read it in 10 seconds:
|
||||
|
||||
- **Inputs**: rough operational material becomes the source for a reusable skill package.
|
||||
- **Router**: `SKILL.md` stays small and decides boundary, mode, and output contract first.
|
||||
- **Method layer**: doctrine files explain whether the request should become a skill and which quality gates it deserves.
|
||||
- **Authoring flow**: the unified CLI turns creation, validation, optimization, promotion, reporting, and packaging into one path.
|
||||
- **Evidence and outputs**: the result is not only a skill package, but also eval artifacts, governance signals, portability outputs, and iteration history.
|
||||
- **Inputs**: start from rough operational material.
|
||||
- **Route**: define boundary and trigger in a lean `SKILL.md`.
|
||||
- **Design**: choose the right archetype, gates, and resource split.
|
||||
- **Run**: use the unified CLI to build, validate, optimize, and promote.
|
||||
- **Outputs**: ship a reusable skill plus evidence, governance signals, and portability artifacts.
|
||||
|
||||
## Quick Start
|
||||
|
||||
|
||||
+12
-38
@@ -14,49 +14,23 @@ Il transforme des workflows bruts, des transcripts, des prompts, des notes et de
|
||||
|
||||
## Architecture
|
||||
|
||||
Le système est volontairement organisé par couches afin qu'un nouveau venu puisse le lire de haut en bas : d'abord le routage, ensuite la méthode, puis la validation, et enfin le packaging et la gouvernance.
|
||||
En version hero, le système tient sur une seule ligne : transformer une entrée brouillonne en skill package gouverné et réutilisable.
|
||||
|
||||
```mermaid
|
||||
flowchart TD
|
||||
A["Entrées<br/>workflows / prompts / transcripts / docs / notes"] --> B["Routeur<br/>SKILL.md"]
|
||||
B --> C["Couche méthode<br/>references/"]
|
||||
B --> D["Flux auteur<br/>scripts/yao.py"]
|
||||
|
||||
C --> C1["Skill Archetype"]
|
||||
C --> C2["Gate Selection"]
|
||||
C --> C3["Non-Skill Decision"]
|
||||
C --> C4["Operating Modes"]
|
||||
C --> C5["Governance"]
|
||||
C --> C6["Resource Boundaries"]
|
||||
|
||||
D --> E["Création<br/>init / template"]
|
||||
D --> F["Validation<br/>lint / boundary / governance"]
|
||||
D --> G["Évaluation<br/>trigger / suites / judge / confusion"]
|
||||
D --> H["Promotion<br/>promotion policy / candidate registry"]
|
||||
D --> I["Packaging<br/>neutral source -> target adapters"]
|
||||
D --> J["Rapports<br/>history / scorecards / context / portability"]
|
||||
|
||||
E --> K["Skill Package"]
|
||||
F --> K
|
||||
G --> L["evals/"]
|
||||
H --> M["reports/"]
|
||||
I --> N["dist/ ou sorties cibles"]
|
||||
|
||||
K --> K1["SKILL.md"]
|
||||
K --> K2["agents/interface.yaml"]
|
||||
K --> K3["manifest.json"]
|
||||
K --> K4["references / scripts / evals / reports optionnels"]
|
||||
|
||||
L --> M
|
||||
flowchart LR
|
||||
A["Entrées<br/>workflow / prompt / transcript / docs / notes"] --> B["Routage<br/>SKILL.md"]
|
||||
B --> C["Conception<br/>méthode + garde-fous"]
|
||||
C --> D["Exécution<br/>create / validate / eval / promote"]
|
||||
D --> E["Sorties<br/>skill package + rapports + adapters"]
|
||||
```
|
||||
|
||||
On peut lire ce schéma en cinq couches :
|
||||
Lecture en 10 secondes :
|
||||
|
||||
- **Couche d'entrée** : les matériaux opérationnels bruts servent de source au futur skill package.
|
||||
- **Couche de routage** : `SKILL.md` reste léger et définit d'abord les frontières, le mode et le contrat de sortie.
|
||||
- **Couche méthode** : les documents de doctrine déterminent si la demande mérite d'être skillifiée et quels garde-fous elle doit recevoir.
|
||||
- **Couche de flux auteur** : le CLI unifié relie création, validation, optimisation, promotion, reporting et packaging.
|
||||
- **Couche preuves et sorties** : le résultat n'est pas seulement un skill package, mais aussi des evals, des signaux de gouvernance, des sorties de portabilité et un historique d'itération.
|
||||
- **Entrées** : on part de workflows, prompts, documents et notes dispersés.
|
||||
- **Routage** : un `SKILL.md` léger définit d'abord la frontière et le déclenchement.
|
||||
- **Conception** : on choisit le bon archetype, les bons gates et la bonne séparation des ressources.
|
||||
- **Exécution** : la CLI unifiée construit, valide, optimise et promeut le skill.
|
||||
- **Sorties** : on obtient un skill package réutilisable avec ses preuves d'évaluation, de gouvernance et de portabilité.
|
||||
|
||||
## Quick Start
|
||||
|
||||
|
||||
+12
-38
@@ -14,49 +14,23 @@
|
||||
|
||||
## アーキテクチャ
|
||||
|
||||
このシステムは層構造になっており、新しい利用者でも上から順に理解できます。最初に route を決め、次に method を選び、その後に検証し、最後に package と governance を扱います。
|
||||
Hero 版では、全体の流れは 1 本です。ばらばらの入力を、統制された再利用可能な skill package に変えます。
|
||||
|
||||
```mermaid
|
||||
flowchart TD
|
||||
A["入力<br/>workflow / prompt / transcript / docs / notes"] --> B["ルーター<br/>SKILL.md"]
|
||||
B --> C["メソッド層<br/>references/"]
|
||||
B --> D["作者フロー<br/>scripts/yao.py"]
|
||||
|
||||
C --> C1["Skill Archetype"]
|
||||
C --> C2["Gate Selection"]
|
||||
C --> C3["Non-Skill Decision"]
|
||||
C --> C4["Operating Modes"]
|
||||
C --> C5["Governance"]
|
||||
C --> C6["Resource Boundaries"]
|
||||
|
||||
D --> E["作成<br/>init / template"]
|
||||
D --> F["検証<br/>lint / boundary / governance"]
|
||||
D --> G["評価<br/>trigger / suites / judge / confusion"]
|
||||
D --> H["昇格<br/>promotion policy / candidate registry"]
|
||||
D --> I["パッケージ化<br/>neutral source -> target adapters"]
|
||||
D --> J["レポート<br/>history / scorecards / context / portability"]
|
||||
|
||||
E --> K["Skill Package"]
|
||||
F --> K
|
||||
G --> L["evals/"]
|
||||
H --> M["reports/"]
|
||||
I --> N["dist/ または target outputs"]
|
||||
|
||||
K --> K1["SKILL.md"]
|
||||
K --> K2["agents/interface.yaml"]
|
||||
K --> K3["manifest.json"]
|
||||
K --> K4["optional references / scripts / evals / reports"]
|
||||
|
||||
L --> M
|
||||
flowchart LR
|
||||
A["入力<br/>workflow / prompt / transcript / docs / notes"] --> B["ルート定義<br/>SKILL.md"]
|
||||
B --> C["設計<br/>method + gates"]
|
||||
C --> D["実行<br/>create / validate / eval / promote"]
|
||||
D --> E["出力<br/>skill package + reports + adapters"]
|
||||
```
|
||||
|
||||
この図は 5 つの層として読むとわかりやすいです。
|
||||
10 秒で読むならこうです。
|
||||
|
||||
- **入力層**: 断片的な運用資料を skill 化の原材料にします。
|
||||
- **ルーター層**: `SKILL.md` は軽量のまま、境界、モード、出力契約を先に決めます。
|
||||
- **メソッド層**: method 文書が、skill 化すべきか、どの quality gate が必要かを決めます。
|
||||
- **作者フロー層**: 統一 CLI が作成、検証、最適化、昇格、レポート、パッケージ化を一つの流れにします。
|
||||
- **証拠と出力層**: 最終成果は skill package だけでなく、eval 結果、governance signal、portability 出力、iteration history も含みます。
|
||||
- **入力**: workflow、prompt、文書、メモなどの粗い素材から始めます。
|
||||
- **ルート定義**: まず軽量な `SKILL.md` で境界と trigger を決めます。
|
||||
- **設計**: 適切な archetype、gate、資源の分割を選びます。
|
||||
- **実行**: 統一 CLI で作成、検証、最適化、昇格を進めます。
|
||||
- **出力**: 最終的に skill package と、評価・ガバナンス・移植性の証拠が残ります。
|
||||
|
||||
## Quick Start
|
||||
|
||||
|
||||
+12
-38
@@ -14,49 +14,23 @@
|
||||
|
||||
## Архитектура
|
||||
|
||||
Система специально построена слоями, чтобы новый пользователь мог понять ее сверху вниз: сначала routing, затем method, потом validation, а уже после этого packaging и governance.
|
||||
В hero-версии вся система сводится к одной линии: превратить разрозненный вход в управляемый и переиспользуемый skill package.
|
||||
|
||||
```mermaid
|
||||
flowchart TD
|
||||
A["Входы<br/>workflows / prompts / transcripts / docs / notes"] --> B["Router<br/>SKILL.md"]
|
||||
B --> C["Method layer<br/>references/"]
|
||||
B --> D["Authoring flow<br/>scripts/yao.py"]
|
||||
|
||||
C --> C1["Skill Archetype"]
|
||||
C --> C2["Gate Selection"]
|
||||
C --> C3["Non-Skill Decision"]
|
||||
C --> C4["Operating Modes"]
|
||||
C --> C5["Governance"]
|
||||
C --> C6["Resource Boundaries"]
|
||||
|
||||
D --> E["Создание<br/>init / template"]
|
||||
D --> F["Проверка<br/>lint / boundary / governance"]
|
||||
D --> G["Оценка<br/>trigger / suites / judge / confusion"]
|
||||
D --> H["Промоушен<br/>promotion policy / candidate registry"]
|
||||
D --> I["Упаковка<br/>neutral source -> target adapters"]
|
||||
D --> J["Отчеты<br/>history / scorecards / context / portability"]
|
||||
|
||||
E --> K["Skill Package"]
|
||||
F --> K
|
||||
G --> L["evals/"]
|
||||
H --> M["reports/"]
|
||||
I --> N["dist/ или target outputs"]
|
||||
|
||||
K --> K1["SKILL.md"]
|
||||
K --> K2["agents/interface.yaml"]
|
||||
K --> K3["manifest.json"]
|
||||
K --> K4["optional references / scripts / evals / reports"]
|
||||
|
||||
L --> M
|
||||
flowchart LR
|
||||
A["Входы<br/>workflow / prompt / transcript / docs / notes"] --> B["Маршрут<br/>SKILL.md"]
|
||||
B --> C["Проектирование<br/>method + gates"]
|
||||
C --> D["Исполнение<br/>create / validate / eval / promote"]
|
||||
D --> E["Выходы<br/>skill package + reports + adapters"]
|
||||
```
|
||||
|
||||
Эту схему удобнее читать как 5 слоев:
|
||||
Как читать это за 10 секунд:
|
||||
|
||||
- **Слой входов**: разрозненные операционные материалы становятся сырьем для будущего skill package.
|
||||
- **Слой routing**: `SKILL.md` остается легким и сначала определяет границы, режим и output contract.
|
||||
- **Слой method**: doctrinal docs определяют, стоит ли вообще skill-изировать запрос и какие quality gates ему нужны.
|
||||
- **Слой authoring flow**: единый CLI связывает создание, проверку, оптимизацию, promotion, reporting и packaging.
|
||||
- **Слой доказательств и выходов**: итогом становится не только skill package, но и eval-артефакты, governance signals, portability outputs и история итераций.
|
||||
- **Входы**: стартуем с workflow, prompt, документов и заметок.
|
||||
- **Маршрут**: компактный `SKILL.md` сначала задает границу и trigger.
|
||||
- **Проектирование**: выбираются нужные archetype, quality gates и разбиение ресурсов.
|
||||
- **Исполнение**: единый CLI создает, проверяет, оптимизирует и продвигает skill.
|
||||
- **Выходы**: результатом становится skill package плюс доказательства оценки, governance и portability.
|
||||
|
||||
## Quick Start
|
||||
|
||||
|
||||
+12
-38
@@ -14,49 +14,23 @@
|
||||
|
||||
## 架构图
|
||||
|
||||
这套系统是分层设计的，方便新用户从上到下理解：先路由，再选方法，再做验证，最后再打包和治理。
|
||||
Hero 版可以压缩成一条主线：把零散输入变成一个可治理、可复用的 skill 包。
|
||||
|
||||
```mermaid
|
||||
flowchart TD
|
||||
A["输入<br/>workflow / prompt / transcript / docs / notes"] --> B["路由入口<br/>SKILL.md"]
|
||||
B --> C["方法层<br/>references/"]
|
||||
B --> D["作者流<br/>scripts/yao.py"]
|
||||
|
||||
C --> C1["Skill Archetype"]
|
||||
C --> C2["Gate Selection"]
|
||||
C --> C3["Non-Skill Decision"]
|
||||
C --> C4["Operating Modes"]
|
||||
C --> C5["Governance"]
|
||||
C --> C6["Resource Boundaries"]
|
||||
|
||||
D --> E["创建<br/>init / template"]
|
||||
D --> F["校验<br/>lint / boundary / governance"]
|
||||
D --> G["评测<br/>trigger / suites / judge / confusion"]
|
||||
D --> H["晋升<br/>promotion policy / candidate registry"]
|
||||
D --> I["打包<br/>neutral source -> target adapters"]
|
||||
D --> J["报告<br/>history / scorecards / context / portability"]
|
||||
|
||||
E --> K["Skill Package"]
|
||||
F --> K
|
||||
G --> L["evals/"]
|
||||
H --> M["reports/"]
|
||||
I --> N["dist/ 或目标导出物"]
|
||||
|
||||
K --> K1["SKILL.md"]
|
||||
K --> K2["agents/interface.yaml"]
|
||||
K --> K3["manifest.json"]
|
||||
K --> K4["可选 references / scripts / evals / reports"]
|
||||
|
||||
L --> M
|
||||
flowchart LR
|
||||
A["输入<br/>workflow / prompt / transcript / docs / notes"] --> B["路由<br/>SKILL.md"]
|
||||
B --> C["设计<br/>方法 + 质量门"]
|
||||
C --> D["执行<br/>create / validate / eval / promote"]
|
||||
D --> E["产出<br/>skill 包 + 报告 + 适配层"]
|
||||
```
|
||||
|
||||
可以把这张图理解成 5 层：
|
||||
10 秒理解这张图：
|
||||
|
||||
- **输入层**：把零散的操作材料作为 skill 的原始输入。
|
||||
- **路由层**：`SKILL.md` 保持轻量，优先定义边界、模式和输出契约。
|
||||
- **方法层**：方法文档决定这件事该不该 skill 化、该上哪些质量门。
|
||||
- **作者流层**：统一 CLI 把创建、校验、优化、晋升、报告和打包串成一条路径。
|
||||
- **证据与产出层**：最终产出不只是 skill 包，还包括 eval 结果、治理信号、portability 产物和迭代历史。
|
||||
- **输入**：从零散的 workflow、prompt、文档和笔记出发。
|
||||
- **路由**：先用精简的 `SKILL.md` 定义边界和触发。
|
||||
- **设计**：选择合适的 archetype、gates 和资源拆分方式。
|
||||
- **执行**：通过统一 CLI 完成创建、校验、优化和晋升。
|
||||
- **产出**：最终得到 skill 包，以及评测、治理和 portability 证据。
|
||||
|
||||
## Quick Start
|
||||
|
||||
|
||||
Reference in New Issue
Block a user