auriga-cli 1.9.2 → 1.9.4
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +12 -3
- package/README.zh-CN.md +12 -3
- package/dist/catalog.json +15 -7
- package/dist/skills.js +0 -1
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -11,7 +11,7 @@ This repo itself is a fully configured harness project. You can clone it to see
|
|
|
11
11
|
| Module | Description |
|
|
12
12
|
|---|---|
|
|
13
13
|
| **Workflow** | `CLAUDE.md` auriga workflow: requirement clarification -> TDD -> Review, Harness principles, Subagent usage guide |
|
|
14
|
-
| **Skills** | Development process + orchestration skills — brainstorming, systematic-debugging, TDD, verification, planning, playwright, deep-review, test-designer, parallel-implementation
|
|
14
|
+
| **Skills** | Development process + orchestration skills — brainstorming, systematic-debugging, TDD, verification, planning, playwright, deep-review, test-designer, parallel-implementation |
|
|
15
15
|
| **Recommended Skills** | Optional utility skills (e.g. `codex-agent`, `claude-code-agent`) you can add on top of the workflow skills |
|
|
16
16
|
| **Plugins** | Recommended Claude Code plugins — skill-creator, claude-md-management, codex, auriga-go |
|
|
17
17
|
| **Hooks** | Claude Code hooks: `notify` (macOS notification, focus-aware sound-only when terminal is frontmost — **opt-in**: not installed by `install --all`, requires `install hooks --hook notify`), `pr-create-guard` (PostToolUse body snapshot after `gh pr create`), `pr-ready-guard` (PreToolUse block on stray planning docs / active specs in `docs/specs/` / unpushed commits before `gh pr ready`) |
|
|
@@ -81,11 +81,20 @@ Installs selected skills via `npx skills add`, targeting both Claude Code and Co
|
|
|
81
81
|
| verification-before-completion | [obra/superpowers](https://github.com/obra/superpowers) | Pre-completion verification — evidence before assertions |
|
|
82
82
|
| planning-with-files | [OthmanAdi/planning-with-files](https://github.com/OthmanAdi/planning-with-files) | File-based task planning and progress tracking |
|
|
83
83
|
| playwright-cli | [microsoft/playwright-cli](https://github.com/microsoft/playwright-cli) | Browser automation and testing |
|
|
84
|
-
| ui-ux-pro-max | [nextlevelbuilder/ui-ux-pro-max-skill](https://github.com/nextlevelbuilder/ui-ux-pro-max-skill) | UI/UX design and development enhancement |
|
|
85
84
|
| deep-review | [Ben2pc/g-claude-code-plugins](https://github.com/Ben2pc/g-claude-code-plugins) | Multi-dimensional PR review orchestrator (required + conditional reviewers + punch list) |
|
|
86
85
|
| test-designer | [Ben2pc/g-claude-code-plugins](https://github.com/Ben2pc/g-claude-code-plugins) | Independent-Evaluation test designer for TDD red phase |
|
|
87
86
|
| parallel-implementation | [Ben2pc/g-claude-code-plugins](https://github.com/Ben2pc/g-claude-code-plugins) | Slice planner for parallel multi-subagent code writing |
|
|
88
87
|
|
|
88
|
+
**Recommended Skills (opt-in, not installed by `--all`):**
|
|
89
|
+
|
|
90
|
+
| Skill | Source | Description |
|
|
91
|
+
|---|---|---|
|
|
92
|
+
| claude-code-agent | [Ben2pc/g-claude-code-plugins](https://github.com/Ben2pc/g-claude-code-plugins) | Delegate coding, review, diagnosis, and planning to standalone Claude Code sessions |
|
|
93
|
+
| codex-agent | [Ben2pc/g-claude-code-plugins](https://github.com/Ben2pc/g-claude-code-plugins) | Delegate to Codex sessions for cross-model coverage |
|
|
94
|
+
| design-taste-frontend | [Leonxlnx/taste-skill](https://github.com/Leonxlnx/taste-skill) | Senior UI/UX engineer with metric-based design rules and strict component architecture |
|
|
95
|
+
| frontend-design | [anthropics/skills](https://github.com/anthropics/skills) | Distinctive, production-grade frontend UI generation that avoids generic AI aesthetics |
|
|
96
|
+
| make-interfaces-feel-better | [jakubkrehel/make-interfaces-feel-better](https://github.com/jakubkrehel/make-interfaces-feel-better) | Polish principles — animations, surfaces, typography, performance |
|
|
97
|
+
|
|
89
98
|
Supports both project and global installation scopes.
|
|
90
99
|
|
|
91
100
|
### Plugins
|
|
@@ -97,7 +106,7 @@ Installs selected plugins via `claude plugins install`, automatically adding req
|
|
|
97
106
|
| skill-creator | Create and manage custom skills |
|
|
98
107
|
| claude-md-management | Audit and improve CLAUDE.md |
|
|
99
108
|
| codex | Codex cross-model collaboration |
|
|
100
|
-
| auriga-go | Workflow autopilot for the auriga workflow. Reminder-based navigation across the
|
|
109
|
+
| auriga-go | Workflow autopilot for the auriga workflow. Reminder-based navigation across the `CLAUDE.md` phases with an Experimental hook-backed `ship` mode. Bundles a skill (description-based NL trigger + `/auriga-go`) plus a plugin-level Stop hook for ship mode. |
|
|
101
110
|
|
|
102
111
|
### Hooks
|
|
103
112
|
|
package/README.zh-CN.md
CHANGED
|
@@ -11,7 +11,7 @@
|
|
|
11
11
|
| 模块 | 说明 |
|
|
12
12
|
|---|---|
|
|
13
13
|
| **Workflow** | `CLAUDE.md` 里的 auriga 工作流:需求澄清 → TDD → Review,Harness 原则,Subagent 使用指南 |
|
|
14
|
-
| **Skills** | 开发流程 + 编排类 skills —— brainstorming、systematic-debugging、TDD、verification、planning、playwright、deep-review、test-designer、parallel-implementation
|
|
14
|
+
| **Skills** | 开发流程 + 编排类 skills —— brainstorming、systematic-debugging、TDD、verification、planning、playwright、deep-review、test-designer、parallel-implementation |
|
|
15
15
|
| **Recommended Skills** | 可选的工具类 skills(如 `codex-agent`、`claude-code-agent`),在 workflow skills 之外按需追加 |
|
|
16
16
|
| **Plugins** | 推荐的 Claude Code 插件 —— skill-creator、claude-md-management、codex、auriga-go |
|
|
17
17
|
| **Hooks** | Claude Code hooks:`notify`(macOS 通知,终端在焦点时仅放声不弹横幅 —— **opt-in**:`install --all` 不装,需要 `install hooks --hook notify`)、`pr-create-guard`(`gh pr create` 后注入 PR body 快照的 PostToolUse)、`pr-ready-guard`(`gh pr ready` 前按游离 planning 文档 / `docs/specs/` 内未清理的 spec / 未 push commits 拦截的 PreToolUse) |
|
|
@@ -81,11 +81,20 @@ npx auriga-cli
|
|
|
81
81
|
| verification-before-completion | [obra/superpowers](https://github.com/obra/superpowers) | 完成前验证,用证据说话 |
|
|
82
82
|
| planning-with-files | [OthmanAdi/planning-with-files](https://github.com/OthmanAdi/planning-with-files) | 文件化任务计划与进度跟踪 |
|
|
83
83
|
| playwright-cli | [microsoft/playwright-cli](https://github.com/microsoft/playwright-cli) | 浏览器自动化与测试 |
|
|
84
|
-
| ui-ux-pro-max | [nextlevelbuilder/ui-ux-pro-max-skill](https://github.com/nextlevelbuilder/ui-ux-pro-max-skill) | UI/UX 设计与开发增强 |
|
|
85
84
|
| deep-review | [Ben2pc/g-claude-code-plugins](https://github.com/Ben2pc/g-claude-code-plugins) | 多维度 PR review 编排器(必选 + 条件 + punch list 汇总) |
|
|
86
85
|
| test-designer | [Ben2pc/g-claude-code-plugins](https://github.com/Ben2pc/g-claude-code-plugins) | TDD 红灯阶段的 Independent Evaluation 测试设计器 |
|
|
87
86
|
| parallel-implementation | [Ben2pc/g-claude-code-plugins](https://github.com/Ben2pc/g-claude-code-plugins) | 多 subagent 并行写代码时的切片计划器 |
|
|
88
87
|
|
|
88
|
+
**Recommended Skills(可选,不在 `--all` 内):**
|
|
89
|
+
|
|
90
|
+
| Skill | 来源 | 说明 |
|
|
91
|
+
|---|---|---|
|
|
92
|
+
| claude-code-agent | [Ben2pc/g-claude-code-plugins](https://github.com/Ben2pc/g-claude-code-plugins) | 通过 Claude Code Agent SDK 把任务委派给独立 Claude Code 会话 |
|
|
93
|
+
| codex-agent | [Ben2pc/g-claude-code-plugins](https://github.com/Ben2pc/g-claude-code-plugins) | 委派给 Codex 会话,做跨模型覆盖 |
|
|
94
|
+
| design-taste-frontend | [Leonxlnx/taste-skill](https://github.com/Leonxlnx/taste-skill) | 高阶 UI/UX 工程师 —— 度量化设计规则与严格的组件架构约束 |
|
|
95
|
+
| frontend-design | [anthropics/skills](https://github.com/anthropics/skills) | 生成有辨识度、production 级的前端界面,避开常见 AI 同质化美学 |
|
|
96
|
+
| make-interfaces-feel-better | [jakubkrehel/make-interfaces-feel-better](https://github.com/jakubkrehel/make-interfaces-feel-better) | 界面打磨原则 —— 动画、表面、排版、性能 |
|
|
97
|
+
|
|
89
98
|
支持 project 和 global 两种安装范围。
|
|
90
99
|
|
|
91
100
|
### Plugins
|
|
@@ -97,7 +106,7 @@ npx auriga-cli
|
|
|
97
106
|
| skill-creator | 创建和管理自定义 skills |
|
|
98
107
|
| claude-md-management | 审计和改进 CLAUDE.md |
|
|
99
108
|
| codex | Codex 跨模型协作 |
|
|
100
|
-
| auriga-go | auriga
|
|
109
|
+
| auriga-go | auriga 工作流的自动驾驶:按 `CLAUDE.md` 的 phase 做 reminder-based 导航;包含 Experimental 的 hook-backed `ship` 模式。内置一个 skill(按 description 的自然语言触发 + `/auriga-go` slash command)和一个 plugin 层面的 Stop hook。 |
|
|
101
110
|
|
|
102
111
|
### Hooks
|
|
103
112
|
|
package/dist/catalog.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
{
|
|
2
|
-
"generatedAt": "2026-
|
|
2
|
+
"generatedAt": "2026-05-06T14:58:34.641Z",
|
|
3
3
|
"workflowSkills": [
|
|
4
4
|
{
|
|
5
5
|
"name": "brainstorming",
|
|
@@ -7,7 +7,7 @@
|
|
|
7
7
|
},
|
|
8
8
|
{
|
|
9
9
|
"name": "deep-review",
|
|
10
|
-
"description": "Run a formal, multi-dimensional code review of a pull request. Reads the PR diff, classifies change types, dispatches parallel reviewers by dimension (
|
|
10
|
+
"description": "Run a formal, multi-dimensional code review of a pull request. Reads the PR diff, classifies change types, dispatches parallel reviewers by dimension (spec-conformance, correctness incl. test quality, docs-sync, plus conditional robustness/UX/performance/structure and code-quality for non-trivial changes), and synthesizes findings into an actionable punch list. Use when the user asks to review a PR, run /deep-review, mark a PR as ready for review, or requests a formal/thorough code review."
|
|
11
11
|
},
|
|
12
12
|
{
|
|
13
13
|
"name": "parallel-implementation",
|
|
@@ -15,7 +15,7 @@
|
|
|
15
15
|
},
|
|
16
16
|
{
|
|
17
17
|
"name": "planning-with-files",
|
|
18
|
-
"description": "Implements Manus-style file-based planning to organize and track progress on complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when asked to plan out, break down, or organize a multi-step project, research task, or any work requiring
|
|
18
|
+
"description": "Implements Manus-style file-based planning to organize and track progress on complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when asked to plan out, break down, or organize a multi-step project, research task, or any work requiring 5+ tool calls. Supports automatic session recovery after /clear."
|
|
19
19
|
},
|
|
20
20
|
{
|
|
21
21
|
"name": "playwright-cli",
|
|
@@ -33,10 +33,6 @@
|
|
|
33
33
|
"name": "test-driven-development",
|
|
34
34
|
"description": "Use when implementing any feature or bugfix, before writing implementation code"
|
|
35
35
|
},
|
|
36
|
-
{
|
|
37
|
-
"name": "ui-ux-pro-max",
|
|
38
|
-
"description": "UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and HTML/CSS). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, and check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, and mobile app. Elements: button, modal, navbar, sidebar, card, table, form, and chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, and flat design. Topics: color systems, accessibility, animation, layout, typography, font pairing, spacing, interaction states, shadow, and gradient. Integrations: shadcn/ui MCP for component search and examples."
|
|
39
|
-
},
|
|
40
36
|
{
|
|
41
37
|
"name": "verification-before-completion",
|
|
42
38
|
"description": "Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always"
|
|
@@ -50,6 +46,18 @@
|
|
|
50
46
|
{
|
|
51
47
|
"name": "codex-agent",
|
|
52
48
|
"description": "Delegate coding, review, diagnosis, planning, and browser tasks to an independent Codex session via `codex exec` / resume / review."
|
|
49
|
+
},
|
|
50
|
+
{
|
|
51
|
+
"name": "design-taste-frontend",
|
|
52
|
+
"description": "Senior UI/UX Engineer. Architect digital interfaces overriding default LLM biases. Enforces metric-based rules, strict component architecture, CSS hardware acceleration, and balanced design engineering."
|
|
53
|
+
},
|
|
54
|
+
{
|
|
55
|
+
"name": "frontend-design",
|
|
56
|
+
"description": "Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics."
|
|
57
|
+
},
|
|
58
|
+
{
|
|
59
|
+
"name": "make-interfaces-feel-better",
|
|
60
|
+
"description": "Design engineering principles for making interfaces feel polished. Use when building UI components, reviewing frontend code, implementing animations, hover states, shadows, borders, typography, micro-interactions, enter/exit animations, or any visual detail work. Triggers on UI polish, design details, \"make it feel better\", \"feels off\", stagger animations, border radius, optical alignment, font smoothing, tabular numbers, image outlines, box shadows."
|
|
53
61
|
}
|
|
54
62
|
],
|
|
55
63
|
"plugins": [
|
package/dist/skills.js
CHANGED