mirror of
https://github.com/affaan-m/ECC.git
synced 2026-10-16 21:25:42 +02:00
Merge remote-tracking branch 'upstream/main' into codex/docs-governance-audit-foundation
This commit is contained in:
Seekers2001
@@ -0,0 +1,26 @@
|
||||
# ECC and the Ito desk
|
||||
|
||||
ECC is the public agentic-engineering toolkit; the Ito desk is Affaan's
|
||||
private ops system. The connection surface in this repo is the set of
|
||||
public `ito-*` skills (`skills/ito-baskets`, `skills/ito-compute`,
|
||||
`skills/ito-inference`, `skills/ito-training`). Each of them is a thin
|
||||
pointer: it names the supported boundary and hands real work to the
|
||||
separately installed canonical CLI or MCP server. ECC itself implements no
|
||||
compute booking, inference serving, training stack or basket trading, and
|
||||
nothing here may claim those capabilities exist inside this repo.
|
||||
|
||||
Desk-side work that touches ECC runs as bounded lane tasks. The lane-worker
|
||||
doctrine (see `docs/LANE-RULES.md`) is: one worker, one task, one branch,
|
||||
one PR or one receipt; real work only, meaning code edits, tests, commits
|
||||
and a PR, with the final message as the receipt; no self-review loops, no
|
||||
receipt ledgers, no merging to main, no publishing, no deployments, no
|
||||
messages; blocked means naming exactly who or what unblocks. The doctrine
|
||||
exists because unbounded agent loops were the dominant failure mode of the
|
||||
desk's earlier automation.
|
||||
|
||||
The merge rule for anything desk-related in this repo: fixes and tests
|
||||
merge freely. Anything that adds a third-party tool, a vendor-named skill,
|
||||
or an external link waits for Affaan's explicit yes, recorded before merge.
|
||||
The living desk plan is `docs/PLAN.md` in `Ito-Markets/ito-desk`; task
|
||||
schemas and the spec book live under `docs/spec/` in the same repo. This
|
||||
file only describes the relationship; the plan repo is the source of truth.
|
||||
@@ -0,0 +1,19 @@
|
||||
# Lane rules
|
||||
|
||||
These are the working rules for bounded lane workers (human or agent) that
|
||||
execute tasks against this repository from the Ito workstream system. They
|
||||
are copied verbatim from the lane registry
|
||||
(`lanes/RULES.md` in the Ito workstream system on the ops mini,
|
||||
2026-09-16) so a worker reading only this repo sees the same contract.
|
||||
One task, one branch, one PR or one receipt, then stop.
|
||||
|
||||
---
|
||||
|
||||
## Lane rules (every codex exec brief starts by reading this)
|
||||
You are one bounded worker. One task, one branch, one PR or one receipt, then stop.
|
||||
- Real work only: edit code, run the tests, commit, push, open the PR. No receipts about receipts, no independent review of your own output, no hashing manifests, no ledgers, no acceptance JSONs, no skill self-patching. Your final message is the receipt (under 300 words: what changed, PR link, test command and result, what is blocked and on whom).
|
||||
- Never merge to main, never publish to npm, never deploy, never send email or messages, never change Hermes profiles or launchd on the mini unless the brief says so explicitly.
|
||||
- Commits: plain messages, no Co-Authored-By or generated-with trailers, no em dashes anywhere.
|
||||
- Worktrees and caches go under ~/GitHub/ECC-worktrees or ~/GitHub on the Pro, /Volumes/Agent-Runtime/workspaces on the mini, never on the mini root disk.
|
||||
- If blocked (missing credential, approval needed, conflicting work), stop and say exactly what is needed. Do not wait, poll, or sleep.
|
||||
- Time box: finish in one pass. Do not spawn subagents.
|
||||
@@ -4,8 +4,8 @@
|
||||
|
||||
|
||||
|
||||
[](https://github.com/affaan-m/ECC/stargazers)
|
||||
[](https://github.com/affaan-m/ECC/network/members)
|
||||
[](https://github.com/affaan-m/ECC)
|
||||
[](https://github.com/affaan-m/ECC/forks)
|
||||
[](https://github.com/affaan-m/ECC/graphs/contributors)
|
||||
[](https://www.npmjs.com/package/ecc-universal)
|
||||
[](https://www.npmjs.com/package/ecc-agentshield)
|
||||
|
||||
+7
-7
@@ -50,13 +50,13 @@ Este es un **plugin de IA para codificación listo para producción** que propor
|
||||
## Orquestación de Agentes
|
||||
|
||||
Usa agentes proactivamente sin prompt del usuario:
|
||||
- Solicitudes de features complejas → **planner**
|
||||
- Código recién escrito/modificado → **code-reviewer**
|
||||
- Corrección de bug o nueva feature → **tdd-guide**
|
||||
- Decisión arquitectónica → **architect**
|
||||
- Código sensible a la seguridad → **security-reviewer**
|
||||
- Bucles autónomos / monitoreo de bucles → **loop-operator**
|
||||
- Confiabilidad y costo de la configuración del harness → **harness-optimizer**
|
||||
- Solicitudes de features complejas → **ecc:planner**
|
||||
- Código recién escrito/modificado → **ecc:code-reviewer**
|
||||
- Corrección de bug o nueva feature → **ecc:tdd-guide**
|
||||
- Decisión arquitectónica → **ecc:architect**
|
||||
- Código sensible a la seguridad → **ecc:security-reviewer**
|
||||
- Bucles autónomos / monitoreo de bucles → **ecc:loop-operator**
|
||||
- Confiabilidad y costo de la configuración del harness → **ecc:harness-optimizer**
|
||||
|
||||
Usa ejecución paralela para operaciones independientes — lanza múltiples agentes simultáneamente.
|
||||
|
||||
|
||||
+3
-3
@@ -4,13 +4,13 @@
|
||||
|
||||
|
||||
|
||||
[](https://github.com/affaan-m/ECC/stargazers)
|
||||
[](https://github.com/affaan-m/ECC/network/members)
|
||||
[](https://github.com/affaan-m/ECC)
|
||||
[](https://github.com/affaan-m/ECC/forks)
|
||||
[](https://github.com/affaan-m/ECC/graphs/contributors)
|
||||
[](https://www.npmjs.com/package/ecc-universal)
|
||||
[](https://www.npmjs.com/package/ecc-agentshield)
|
||||
[](https://github.com/marketplace/ecc-tools)
|
||||
[](LICENSE)
|
||||
[](../../LICENSE)
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -2,29 +2,36 @@
|
||||
|
||||
## Agentes Disponibles
|
||||
|
||||
Ubicados en `~/.claude/agents/`:
|
||||
Los agentes de ECC se distribuyen con el plugin `ecc@ecc`, no en `~/.claude/agents/`.
|
||||
Se invocan a través de la herramienta Agent con un `subagent_type` con ámbito de plugin:
|
||||
|
||||
```text
|
||||
Agent(subagent_type: "ecc:planner", prompt: "...")
|
||||
```
|
||||
|
||||
| Agente | Propósito | Cuándo Usar |
|
||||
|--------|-----------|-------------|
|
||||
| planner | Planificación de implementación | Features complejas, refactoring |
|
||||
| architect | Diseño de sistemas | Decisiones arquitectónicas |
|
||||
| tdd-guide | Desarrollo guiado por pruebas | Nuevas features, corrección de bugs |
|
||||
| code-reviewer | Revisión de código | Después de escribir código |
|
||||
| security-reviewer | Análisis de seguridad | Antes de los commits |
|
||||
| build-error-resolver | Corrección de errores de build | Cuando el build falla |
|
||||
| e2e-runner | Testing E2E | Flujos de usuario críticos |
|
||||
| refactor-cleaner | Limpieza de código muerto | Mantenimiento de código |
|
||||
| doc-updater | Documentación | Actualización de docs |
|
||||
| rust-reviewer | Revisión de código Rust | Proyectos Rust |
|
||||
| harmonyos-app-resolver | Desarrollo de apps HarmonyOS | Proyectos HarmonyOS/ArkTS |
|
||||
| ecc:planner | Planificación de implementación | Features complejas, refactoring |
|
||||
| ecc:architect | Diseño de sistemas | Decisiones arquitectónicas |
|
||||
| ecc:tdd-guide | Desarrollo guiado por pruebas | Nuevas features, corrección de bugs |
|
||||
| ecc:code-reviewer | Revisión de código | Después de escribir código |
|
||||
| ecc:security-reviewer | Análisis de seguridad | Antes de los commits |
|
||||
| ecc:build-error-resolver | Corrección de errores de build | Cuando el build falla |
|
||||
| ecc:e2e-runner | Testing E2E | Flujos de usuario críticos |
|
||||
| ecc:refactor-cleaner | Limpieza de código muerto | Mantenimiento de código |
|
||||
| ecc:doc-updater | Documentación | Actualización de docs |
|
||||
| ecc:rust-reviewer | Revisión de código Rust | Proyectos Rust |
|
||||
| ecc:harmonyos-app-resolver | Desarrollo de apps HarmonyOS | Proyectos HarmonyOS/ArkTS |
|
||||
|
||||
Para el roster completo de 68 agentes, ver `/ecc:ecc-guide`.
|
||||
|
||||
## Uso Inmediato de Agentes
|
||||
|
||||
Sin necesidad de prompt del usuario:
|
||||
1. Solicitudes de features complejas - Usar el agente **planner**
|
||||
2. Código recién escrito/modificado - Usar el agente **code-reviewer**
|
||||
3. Corrección de bug o nueva feature - Usar el agente **tdd-guide**
|
||||
4. Decisión arquitectónica - Usar el agente **architect**
|
||||
1. Solicitudes de features complejas - Usar el agente **ecc:planner**
|
||||
2. Código recién escrito/modificado - Usar el agente **ecc:code-reviewer**
|
||||
3. Corrección de bug o nueva feature - Usar el agente **ecc:tdd-guide**
|
||||
4. Decisión arquitectónica - Usar el agente **ecc:architect**
|
||||
|
||||
## Ejecución Paralela de Tareas
|
||||
|
||||
|
||||
@@ -50,13 +50,13 @@
|
||||
## エージェントオーケストレーション
|
||||
|
||||
ユーザーのプロンプトなしで積極的にエージェントを使用する：
|
||||
- 複雑な機能リクエスト → **planner**
|
||||
- コードの作成/変更直後 → **code-reviewer**
|
||||
- バグ修正または新機能 → **tdd-guide**
|
||||
- アーキテクチャの意思決定 → **architect**
|
||||
- セキュリティに関わるコード → **security-reviewer**
|
||||
- 自律ループ / ループ監視 → **loop-operator**
|
||||
- ハーネス設定の信頼性とコスト → **harness-optimizer**
|
||||
- 複雑な機能リクエスト → **ecc:planner**
|
||||
- コードの作成/変更直後 → **ecc:code-reviewer**
|
||||
- バグ修正または新機能 → **ecc:tdd-guide**
|
||||
- アーキテクチャの意思決定 → **ecc:architect**
|
||||
- セキュリティに関わるコード → **ecc:security-reviewer**
|
||||
- 自律ループ / ループ監視 → **ecc:loop-operator**
|
||||
- ハーネス設定の信頼性とコスト → **ecc:harness-optimizer**
|
||||
|
||||
独立した操作には並列実行を使用する — 複数のエージェントを同時に起動する。
|
||||
|
||||
|
||||
+1867
-653
File diff suppressed because it is too large
Load Diff
@@ -2,27 +2,34 @@
|
||||
|
||||
## 利用可能な Agent
|
||||
|
||||
`~/.claude/agents/` に配置:
|
||||
ECC の Agent は `ecc@ecc` プラグインに同梱されており、`~/.claude/agents/` には配置されません。
|
||||
Agent ツールではプラグインスコープの `subagent_type` で呼び出します:
|
||||
|
||||
```text
|
||||
Agent(subagent_type: "ecc:planner", prompt: "...")
|
||||
```
|
||||
|
||||
| Agent | 目的 | 使用タイミング |
|
||||
|-------|---------|-------------|
|
||||
| planner | 実装計画 | 複雑な機能、リファクタリング |
|
||||
| architect | システム設計 | アーキテクチャの意思決定 |
|
||||
| tdd-guide | テスト駆動開発 | 新機能、バグ修正 |
|
||||
| code-reviewer | コードレビュー | コード記述後 |
|
||||
| security-reviewer | セキュリティ分析 | コミット前 |
|
||||
| build-error-resolver | ビルドエラー修正 | ビルド失敗時 |
|
||||
| e2e-runner | E2Eテスト | 重要なユーザーフロー |
|
||||
| refactor-cleaner | デッドコードクリーンアップ | コードメンテナンス |
|
||||
| doc-updater | ドキュメント | ドキュメント更新 |
|
||||
| ecc:planner | 実装計画 | 複雑な機能、リファクタリング |
|
||||
| ecc:architect | システム設計 | アーキテクチャの意思決定 |
|
||||
| ecc:tdd-guide | テスト駆動開発 | 新機能、バグ修正 |
|
||||
| ecc:code-reviewer | コードレビュー | コード記述後 |
|
||||
| ecc:security-reviewer | セキュリティ分析 | コミット前 |
|
||||
| ecc:build-error-resolver | ビルドエラー修正 | ビルド失敗時 |
|
||||
| ecc:e2e-runner | E2Eテスト | 重要なユーザーフロー |
|
||||
| ecc:refactor-cleaner | デッドコードクリーンアップ | コードメンテナンス |
|
||||
| ecc:doc-updater | ドキュメント | ドキュメント更新 |
|
||||
|
||||
全 68 Agent の一覧は `/ecc:ecc-guide` を参照。
|
||||
|
||||
## Agent の即座の使用
|
||||
|
||||
ユーザープロンプト不要:
|
||||
1. 複雑な機能リクエスト - **planner** agent を使用
|
||||
2. コード作成/変更直後 - **code-reviewer** agent を使用
|
||||
3. バグ修正または新機能 - **tdd-guide** agent を使用
|
||||
4. アーキテクチャの意思決定 - **architect** agent を使用
|
||||
1. 複雑な機能リクエスト - **ecc:planner** agent を使用
|
||||
2. コード作成/変更直後 - **ecc:code-reviewer** agent を使用
|
||||
3. バグ修正または新機能 - **ecc:tdd-guide** agent を使用
|
||||
4. アーキテクチャの意思決定 - **ecc:architect** agent を使用
|
||||
|
||||
## 並列タスク実行
|
||||
|
||||
|
||||
+8
-8
@@ -47,14 +47,14 @@ Bu, yazılım geliştirme için 68 özel agent, 293 skill, 94 command ve otomati
|
||||
## Agent Orkestrasyonu
|
||||
|
||||
Agentları kullanıcı istemi olmadan proaktif olarak kullanın:
|
||||
- Karmaşık özellik istekleri → **planner**
|
||||
- Yeni yazılan/değiştirilen kod → **code-reviewer**
|
||||
- Hata düzeltme veya yeni özellik → **tdd-guide**
|
||||
- Mimari karar → **architect**
|
||||
- Güvenlik açısından hassas kod → **security-reviewer**
|
||||
- Çok kanallı iletişim önceliklendirme → **chief-of-staff**
|
||||
- Otonom döngüler / döngü izleme → **loop-operator**
|
||||
- Harness yapılandırma güvenilirliği ve maliyeti → **harness-optimizer**
|
||||
- Karmaşık özellik istekleri → **ecc:planner**
|
||||
- Yeni yazılan/değiştirilen kod → **ecc:code-reviewer**
|
||||
- Hata düzeltme veya yeni özellik → **ecc:tdd-guide**
|
||||
- Mimari karar → **ecc:architect**
|
||||
- Güvenlik açısından hassas kod → **ecc:security-reviewer**
|
||||
- Çok kanallı iletişim önceliklendirme → **ecc:chief-of-staff**
|
||||
- Otonom döngüler / döngü izleme → **ecc:loop-operator**
|
||||
- Harness yapılandırma güvenilirliği ve maliyeti → **ecc:harness-optimizer**
|
||||
|
||||
Bağımsız işlemler için paralel yürütme kullanın — birden fazla agenti aynı anda başlatın.
|
||||
|
||||
|
||||
@@ -2,28 +2,35 @@
|
||||
|
||||
## Mevcut Agent'lar
|
||||
|
||||
`~/.claude/agents/` dizininde bulunur:
|
||||
ECC agent'ları `ecc@ecc` eklentisiyle birlikte gelir, `~/.claude/agents/` dizininde bulunmaz.
|
||||
Agent aracıyla eklenti kapsamlı bir `subagent_type` ile çağrılır:
|
||||
|
||||
```text
|
||||
Agent(subagent_type: "ecc:planner", prompt: "...")
|
||||
```
|
||||
|
||||
| Agent | Amaç | Ne Zaman Kullanılır |
|
||||
|-------|---------|-------------|
|
||||
| planner | Uygulama planlaması | Karmaşık özellikler, refactoring |
|
||||
| architect | Sistem tasarımı | Mimari kararlar |
|
||||
| tdd-guide | Test odaklı geliştirme | Yeni özellikler, hata düzeltmeleri |
|
||||
| code-reviewer | Kod incelemesi | Kod yazdıktan sonra |
|
||||
| security-reviewer | Güvenlik analizi | Commit'lerden önce |
|
||||
| build-error-resolver | Build hatalarını düzeltme | Build başarısız olduğunda |
|
||||
| e2e-runner | E2E testleri | Kritik kullanıcı akışları |
|
||||
| refactor-cleaner | Ölü kod temizliği | Kod bakımı |
|
||||
| doc-updater | Dokümantasyon | Dokümanları güncelleme |
|
||||
| rust-reviewer | Rust kod incelemesi | Rust projeleri |
|
||||
| ecc:planner | Uygulama planlaması | Karmaşık özellikler, refactoring |
|
||||
| ecc:architect | Sistem tasarımı | Mimari kararlar |
|
||||
| ecc:tdd-guide | Test odaklı geliştirme | Yeni özellikler, hata düzeltmeleri |
|
||||
| ecc:code-reviewer | Kod incelemesi | Kod yazdıktan sonra |
|
||||
| ecc:security-reviewer | Güvenlik analizi | Commit'lerden önce |
|
||||
| ecc:build-error-resolver | Build hatalarını düzeltme | Build başarısız olduğunda |
|
||||
| ecc:e2e-runner | E2E testleri | Kritik kullanıcı akışları |
|
||||
| ecc:refactor-cleaner | Ölü kod temizliği | Kod bakımı |
|
||||
| ecc:doc-updater | Dokümantasyon | Dokümanları güncelleme |
|
||||
| ecc:rust-reviewer | Rust kod incelemesi | Rust projeleri |
|
||||
|
||||
68 agent'ın tam listesi için `/ecc:ecc-guide` bölümüne bakın.
|
||||
|
||||
## Anlık Agent Kullanımı
|
||||
|
||||
Kullanıcı istemi gerekmez:
|
||||
1. Karmaşık özellik istekleri - **planner** agent kullan
|
||||
2. Kod yeni yazıldı/değiştirildi - **code-reviewer** agent kullan
|
||||
3. Hata düzeltmesi veya yeni özellik - **tdd-guide** agent kullan
|
||||
4. Mimari karar - **architect** agent kullan
|
||||
1. Karmaşık özellik istekleri - **ecc:planner** agent kullan
|
||||
2. Kod yeni yazıldı/değiştirildi - **ecc:code-reviewer** agent kullan
|
||||
3. Hata düzeltmesi veya yeni özellik - **ecc:tdd-guide** agent kullan
|
||||
4. Mimari karar - **ecc:architect** agent kullan
|
||||
|
||||
## Paralel Görev Yürütme
|
||||
|
||||
|
||||
@@ -27,8 +27,8 @@
|
||||
</p>
|
||||
|
||||
<p align="center">
|
||||
<a href="https://github.com/affaan-m/ECC/stargazers"><img src="https://img.shields.io/endpoint?url=https%3A%2F%2Fapi.ecc.tools%2Fbadge%2Fstars&style=flat" alt="Stars" /></a>
|
||||
<a href="https://github.com/affaan-m/ECC/network/members"><img src="https://img.shields.io/endpoint?url=https%3A%2F%2Fapi.ecc.tools%2Fbadge%2Fforks&style=flat" alt="Forks" /></a>
|
||||
<a href="https://github.com/affaan-m/ECC"><img src="https://img.shields.io/github/stars/affaan-m/ECC?style=flat" alt="GitHub stars" /></a>
|
||||
<a href="https://github.com/affaan-m/ECC/forks"><img src="https://img.shields.io/github/forks/affaan-m/ECC?style=flat" alt="GitHub forks" /></a>
|
||||
<a href="https://github.com/affaan-m/ECC/graphs/contributors"><img src="https://img.shields.io/github/contributors/affaan-m/ECC?style=flat" alt="Contributors" /></a>
|
||||
<a href="https://github.com/marketplace/ecc-tools"><img src="https://img.shields.io/endpoint?url=https%3A%2F%2Fapi.ecc.tools%2Fbadge%2Finstalls&logo=github" alt="GitHub App installs" /></a>
|
||||
</p>
|
||||
|
||||
+2
-2
@@ -4,8 +4,8 @@
|
||||
|
||||
|
||||
|
||||
[](https://github.com/affaan-m/ECC/stargazers)
|
||||
[](https://github.com/affaan-m/ECC/network/members)
|
||||
[](https://github.com/affaan-m/ECC)
|
||||
[](https://github.com/affaan-m/ECC/forks)
|
||||
[](https://github.com/affaan-m/ECC/graphs/contributors)
|
||||
[](https://www.npmjs.com/package/ecc-universal)
|
||||
[](https://www.npmjs.com/package/ecc-agentshield)
|
||||
|
||||
@@ -48,14 +48,14 @@
|
||||
|
||||
主动使用智能体，无需用户提示：
|
||||
|
||||
* 复杂功能请求 → **planner**
|
||||
* 刚编写/修改的代码 → **code-reviewer**
|
||||
* 错误修复或新功能 → **tdd-guide**
|
||||
* 架构决策 → **architect**
|
||||
* 安全敏感代码 → **security-reviewer**
|
||||
* 多渠道沟通分流 → **chief-of-staff**
|
||||
* 自主循环 / 循环监控 → **loop-operator**
|
||||
* 线束配置可靠性及成本 → **harness-optimizer**
|
||||
* 复杂功能请求 → **ecc:planner**
|
||||
* 刚编写/修改的代码 → **ecc:code-reviewer**
|
||||
* 错误修复或新功能 → **ecc:tdd-guide**
|
||||
* 架构决策 → **ecc:architect**
|
||||
* 安全敏感代码 → **ecc:security-reviewer**
|
||||
* 多渠道沟通分流 → **ecc:chief-of-staff**
|
||||
* 自主循环 / 循环监控 → **ecc:loop-operator**
|
||||
* 线束配置可靠性及成本 → **ecc:harness-optimizer**
|
||||
|
||||
对于独立操作使用并行执行 — 同时启动多个智能体。
|
||||
|
||||
|
||||
@@ -2,29 +2,36 @@
|
||||
|
||||
## 可用智能体
|
||||
|
||||
位于 `~/.claude/agents/` 中：
|
||||
ECC 智能体随 `ecc@ecc` 插件一起分发，不在 `~/.claude/agents/` 目录中。
|
||||
它们通过 Agent 工具以插件作用域的 `subagent_type` 调用：
|
||||
|
||||
```text
|
||||
Agent(subagent_type: "ecc:planner", prompt: "...")
|
||||
```
|
||||
|
||||
| 代理 | 用途 | 使用时机 |
|
||||
|-------|---------|-------------|
|
||||
| planner | 实现规划 | 复杂功能、重构 |
|
||||
| architect | 系统设计 | 架构决策 |
|
||||
| tdd-guide | 测试驱动开发 | 新功能、错误修复 |
|
||||
| code-reviewer | 代码审查 | 编写代码后 |
|
||||
| security-reviewer | 安全分析 | 提交前 |
|
||||
| build-error-resolver | 修复构建错误 | 构建失败时 |
|
||||
| e2e-runner | 端到端测试 | 关键用户流程 |
|
||||
| refactor-cleaner | 清理死代码 | 代码维护 |
|
||||
| doc-updater | 文档 | 更新文档 |
|
||||
| rust-reviewer | Rust 代码审查 | Rust 项目 |
|
||||
| ecc:planner | 实现规划 | 复杂功能、重构 |
|
||||
| ecc:architect | 系统设计 | 架构决策 |
|
||||
| ecc:tdd-guide | 测试驱动开发 | 新功能、错误修复 |
|
||||
| ecc:code-reviewer | 代码审查 | 编写代码后 |
|
||||
| ecc:security-reviewer | 安全分析 | 提交前 |
|
||||
| ecc:build-error-resolver | 修复构建错误 | 构建失败时 |
|
||||
| ecc:e2e-runner | 端到端测试 | 关键用户流程 |
|
||||
| ecc:refactor-cleaner | 清理死代码 | 代码维护 |
|
||||
| ecc:doc-updater | 文档 | 更新文档 |
|
||||
| ecc:rust-reviewer | Rust 代码审查 | Rust 项目 |
|
||||
|
||||
完整 68 个智能体的清单参见 `/ecc:ecc-guide`。
|
||||
|
||||
## 即时智能体使用
|
||||
|
||||
无需用户提示：
|
||||
|
||||
1. 复杂的功能请求 - 使用 **planner** 智能体
|
||||
2. 刚编写/修改的代码 - 使用 **code-reviewer** 智能体
|
||||
3. 错误修复或新功能 - 使用 **tdd-guide** 智能体
|
||||
4. 架构决策 - 使用 **architect** 智能体
|
||||
1. 复杂的功能请求 - 使用 **ecc:planner** 智能体
|
||||
2. 刚编写/修改的代码 - 使用 **ecc:code-reviewer** 智能体
|
||||
3. 错误修复或新功能 - 使用 **ecc:tdd-guide** 智能体
|
||||
4. 架构决策 - 使用 **ecc:architect** 智能体
|
||||
|
||||
## 并行任务执行
|
||||
|
||||
|
||||
Reference in New Issue
Block a user