auriga-cli 1.9.0 → 1.9.3

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.
Files changed (6) hide show
  1. package/README.md +8 -3
  2. package/README.zh-CN.md +8 -3
  3. package/dist/catalog.json +3 -7
  4. package/dist/cli.js +0 -0
  5. package/dist/skills.js +0 -1
  6. package/package.json +13 -2
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, ui-ux-pro-max |
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`) |
@@ -81,7 +81,6 @@ 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 |
@@ -97,7 +96,7 @@ Installs selected plugins via `claude plugins install`, automatically adding req
97
96
  | skill-creator | Create and manage custom skills |
98
97
  | claude-md-management | Audit and improve CLAUDE.md |
99
98
  | codex | Codex cross-model collaboration |
100
- | auriga-go | Workflow autopilot for the auriga workflow. Reminder-based navigation across the 12 `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. |
99
+ | 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
100
 
102
101
  ### Hooks
103
102
 
@@ -123,6 +122,12 @@ Re-running the installer preserves your customized `config.json` and `icon.png`,
123
122
  - [Claude Code](https://docs.anthropic.com/en/docs/claude-code) (required for Plugins and Hooks modules)
124
123
  - [Homebrew](https://brew.sh) (recommended for the `notify` hook to install `alerter`)
125
124
 
125
+ ## Development
126
+
127
+ - `npm test` — unit/integration tests (sub-second)
128
+ - `bash tests/ship-loop.test.sh` — ship-loop Stop hook tests (bash)
129
+ - `npm run test:e2e` — full tarball install e2e suite (~90-120s). Packs the actual npm tarball, installs it into a scratch project, and runs `auriga-cli install` against GitHub content pinned to the current HEAD SHA. The preflight uses `git branch -r --contains HEAD` — purely local, no network — so **HEAD must be reachable from a local remote ref** (a successful `git push` updates local remote refs synchronously; if someone else pushed, run `git fetch` first). The `plugins` and `--all` scenarios additionally require the `claude` CLI on PATH; they skip gracefully otherwise.
130
+
126
131
  ## License
127
132
 
128
133
  MIT
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、ui-ux-pro-max |
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） |
@@ -81,7 +81,6 @@ 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 |
@@ -97,7 +96,7 @@ npx auriga-cli
97
96
  | skill-creator | 创建和管理自定义 skills |
98
97
  | claude-md-management | 审计和改进 CLAUDE.md |
99
98
  | codex | Codex 跨模型协作 |
100
- | auriga-go | auriga 工作流的自动驾驶：在 12 步内做 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。 |
99
+ | 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
100
 
102
101
  ### Hooks
103
102
 
@@ -123,6 +122,12 @@ npx auriga-cli
123
122
  - [Claude Code](https://docs.anthropic.com/en/docs/claude-code)（Plugins 和 Hooks 模块需要）
124
123
  - [Homebrew](https://brew.sh)（`notify` hook 用来安装 `alerter`，可选）
125
124
 
125
+ ## 开发
126
+
127
+ - `npm test` —— 单元/集成测试（亚秒）
128
+ - `bash tests/ship-loop.test.sh` —— ship-loop Stop hook 测试（bash）
129
+ - `npm run test:e2e` —— 完整的 tarball 安装 e2e 套件（~90-120s）。`npm pack` 打出真实 tarball，装到临时项目，对着 GitHub 上当前 HEAD SHA 对应的 content 跑 `auriga-cli install`。预检用 `git branch -r --contains HEAD`，纯本地、不发网络请求，因此 **HEAD 必须能被任何本地 remote ref 追溯到**（`git push` 成功时会同步更新本地 remote ref；如果是别人推的，先 `git fetch`）。`plugins` 和 `--all` 场景还要求 `claude` CLI 已在 PATH，否则这两条会优雅跳过。
130
+
126
131
  ## License
127
132
 
128
133
  MIT
package/dist/catalog.json CHANGED
@@ -1,5 +1,5 @@
1
1
  {
2
- "generatedAt": "2026-04-21T14:49:19.814Z",
2
+ "generatedAt": "2026-05-01T08:36:23.215Z",
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 (correctness, consistency, docs-sync, plus conditional security/edge-cases/UX/performance/structure/maintainability), 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."
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 >5 tool calls. Supports automatic session recovery after /clear."
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"
package/dist/cli.js CHANGED
File without changes
package/dist/skills.js CHANGED
@@ -14,7 +14,6 @@ export const WORKFLOW_SKILLS = [
14
14
  "systematic-debugging",
15
15
  "test-designer",
16
16
  "test-driven-development",
17
- "ui-ux-pro-max",
18
17
  "verification-before-completion",
19
18
  ];
20
19
  // Skill names and npm-style sources are interpolated into the shell
package/package.json CHANGED
@@ -1,7 +1,16 @@
1
1
  {
2
2
  "name": "auriga-cli",
3
- "version": "1.9.0",
3
+ "version": "1.9.3",
4
4
  "description": "Interactive CLI to install Claude Code harness modules (Workflow, Skills, Recommended Skills, Plugins, Hooks)",
5
+ "license": "MIT",
6
+ "repository": {
7
+ "type": "git",
8
+ "url": "git+https://github.com/Ben2pc/auriga-cli.git"
9
+ },
10
+ "homepage": "https://github.com/Ben2pc/auriga-cli#readme",
11
+ "bugs": {
12
+ "url": "https://github.com/Ben2pc/auriga-cli/issues"
13
+ },
5
14
  "type": "module",
6
15
  "bin": {
7
16
  "auriga-cli": "dist/cli.js"
@@ -17,7 +26,9 @@
17
26
  "start": "node dist/cli.js",
18
27
  "pretest": "npm run build",
19
28
  "test": "tsc -p tsconfig.test.json && DEV=1 node --test --experimental-test-module-mocks dist-test/tests/hooks.test.js dist-test/tests/skills.test.js dist-test/tests/catalog.test.js dist-test/tests/cli-parse.test.js dist-test/tests/install-nontty.test.js dist-test/tests/guide.test.js dist-test/tests/validators.test.js dist-test/tests/entrypoint.test.js",
20
- "test:watch": "tsc -p tsconfig.test.json --watch & node --test --watch --experimental-test-module-mocks dist-test/tests/hooks.test.js dist-test/tests/skills.test.js dist-test/tests/catalog.test.js dist-test/tests/cli-parse.test.js dist-test/tests/install-nontty.test.js dist-test/tests/guide.test.js dist-test/tests/validators.test.js dist-test/tests/entrypoint.test.js"
29
+ "test:watch": "tsc -p tsconfig.test.json --watch & node --test --watch --experimental-test-module-mocks dist-test/tests/hooks.test.js dist-test/tests/skills.test.js dist-test/tests/catalog.test.js dist-test/tests/cli-parse.test.js dist-test/tests/install-nontty.test.js dist-test/tests/guide.test.js dist-test/tests/validators.test.js dist-test/tests/entrypoint.test.js",
30
+ "pretest:e2e": "npm run build",
31
+ "test:e2e": "tsc -p tsconfig.test.json && node --test dist-test/tests/e2e-install.test.js"
21
32
  },
22
33
  "engines": {
23
34
  "node": ">=18"