@mison/ling 1.1.0 → 1.1.1

package/.agents/rules/GEMINI.md

@@ -27,6 +27,23 @@ trigger: always_on
 
 ---
 
+## Spec 协议（任务跟踪 CSV 驱动）
+
+当工作区存在 `issues.csv` 时，视其为任务跟踪文件（单一事实源），并遵循：
+
+1. 读取 `issues.csv` 并只锁定一个原子任务。
+2. 将任务状态从“未开始”改为“进行中”，再开始开发。
+3. 修改完成后运行最小充分验证，并记录证据。
+4. 自审通过后将状态改为“已完成”。
+5. 若验证失败，先修复或回退，不得静默降级。
+
+模板参考：
+
+- 优先：`.ling/spec/templates/driver-prompt.md`
+- 其次：`~/.ling/spec/templates/driver-prompt.md`（若已启用全局 Spec Profile）
+
+---
+
 ##  请求分类器（第 1 步）
 
 **在执行任何动作前，先对请求分类：**

package/.agents/skills/clean-code/SKILL.md

@@ -143,24 +143,34 @@ File to edit: UserService.ts
 
 > [CRITICAL]  **核心要求：** 每个代理完成后仅运行所属技能脚本。
 
+### 脚本路径约定
+
+下表中的 `<skills_root>` 代表 Skills 根目录，常见取值：
+
+- Ling 仓库源码：`.agents/skills`
+- Gemini 工作区：`.agent/skills`
+- Codex 全局：`~/.codex/skills`
+- Gemini CLI 全局：`~/.gemini/skills`
+- Antigravity 全局：`~/.gemini/antigravity/skills`
+
 ### 代理 -> 脚本映射
 
 | 代理 | 脚本 | 命令 |
 |-------|--------|---------|
-| **frontend-specialist** | UX Audit | `python .agent/skills/frontend-design/scripts/ux_audit.py .` |
-| **frontend-specialist** | A11y Check | `python .agent/skills/frontend-design/scripts/accessibility_checker.py .` |
-| **backend-specialist** | API Validator | `python .agent/skills/api-patterns/scripts/api_validator.py .` |
-| **mobile-developer** | Mobile Audit | `python .agent/skills/mobile-design/scripts/mobile_audit.py .` |
-| **database-architect** | Schema Validate | `python .agent/skills/database-design/scripts/schema_validator.py .` |
-| **security-auditor** | Security Scan | `python .agent/skills/vulnerability-scanner/scripts/security_scan.py .` |
-| **seo-specialist** | SEO Check | `python .agent/skills/seo-fundamentals/scripts/seo_checker.py .` |
-| **seo-specialist** | GEO Check | `python .agent/skills/geo-fundamentals/scripts/geo_checker.py .` |
-| **performance-optimizer** | Lighthouse | `python .agent/skills/performance-profiling/scripts/lighthouse_audit.py <url>` |
-| **test-engineer** | Test Runner | `python .agent/skills/testing-patterns/scripts/test_runner.py .` |
-| **test-engineer** | Playwright | `python .agent/skills/webapp-testing/scripts/playwright_runner.py <url>` |
-| **Any agent** | Lint Check | `python .agent/skills/lint-and-validate/scripts/lint_runner.py .` |
-| **Any agent** | Type Coverage | `python .agent/skills/lint-and-validate/scripts/type_coverage.py .` |
-| **Any agent** | i18n Check | `python .agent/skills/i18n-localization/scripts/i18n_checker.py .` |
+| **frontend-specialist** | UX Audit | `python <skills_root>/frontend-design/scripts/ux_audit.py .` |
+| **frontend-specialist** | A11y Check | `python <skills_root>/frontend-design/scripts/accessibility_checker.py .` |
+| **backend-specialist** | API Validator | `python <skills_root>/api-patterns/scripts/api_validator.py .` |
+| **mobile-developer** | Mobile Audit | `python <skills_root>/mobile-design/scripts/mobile_audit.py .` |
+| **database-architect** | Schema Validate | `python <skills_root>/database-design/scripts/schema_validator.py .` |
+| **security-auditor** | Security Scan | `python <skills_root>/vulnerability-scanner/scripts/security_scan.py .` |
+| **seo-specialist** | SEO Check | `python <skills_root>/seo-fundamentals/scripts/seo_checker.py .` |
+| **seo-specialist** | GEO Check | `python <skills_root>/geo-fundamentals/scripts/geo_checker.py .` |
+| **performance-optimizer** | Lighthouse | `python <skills_root>/performance-profiling/scripts/lighthouse_audit.py <url>` |
+| **test-engineer** | Test Runner | `python <skills_root>/testing-patterns/scripts/test_runner.py .` |
+| **test-engineer** | Playwright | `python <skills_root>/webapp-testing/scripts/playwright_runner.py <url>` |
+| **Any agent** | Lint Check | `python <skills_root>/lint-and-validate/scripts/lint_runner.py .` |
+| **Any agent** | Type Coverage | `python <skills_root>/lint-and-validate/scripts/type_coverage.py .` |
+| **Any agent** | i18n Check | `python <skills_root>/i18n-localization/scripts/i18n_checker.py .` |
 
 > [FAIL]  **错误做法：** `test-engineer` 运行 `ux_audit.py`
 > [OK]  **正确做法：** `frontend-specialist` 运行 `ux_audit.py`

package/.agents/skills/doc.md

@@ -18,7 +18,11 @@
 
 | 范围 | 路径 | 说明 |
 |---------|-----------|-------|
-| **Workspace（工作区）** | `<workspace-root>/.agent/skills/` | 仅作用于当前项目 |
+| **Ling 仓库源码（Canonical）** | `<ling-repo>/.agents/skills/` | 模板源，用于构建与分发 |
+| **Workspace（工作区）** | `<workspace-root>/.agent/skills/` | 仅作用于当前项目（Gemini/Antigravity） |
+| **Global（全局）** | `~/.codex/skills/`、`~/.gemini/skills/`、`~/.gemini/antigravity/skills/` | 跨项目复用（按目标工具读取） |
+
+> 约定：下文示例使用 `<skills_root>` 表示 Skills 根目录；请按你的安装方式替换为上表路径。
 
 ### 技能目录结构
 
@@ -39,7 +43,7 @@ my-skill/
 ### 步骤 1：创建目录
 
 ```bash
-mkdir -p .agent/skills/code-review
+mkdir -p <skills_root>/code-review
 ```
 
 ### 步骤 2：创建 SKILL.md
@@ -119,12 +123,12 @@ Agent（智能体）会自动识别 `code-review` 技能，加载信息并按指
 ### 步骤 1：创建目录
 
 ```bash
-mkdir -p .agent/skills/license-header-adder/resources
+mkdir -p <skills_root>/license-header-adder/resources
 ```
 
 ### 步骤 2：创建模板文件
 
-**`.agent/skills/license-header-adder/resources/HEADER.txt`**：
+**`<skills_root>/license-header-adder/resources/HEADER.txt`**：
 
 ```
 /*
@@ -136,7 +140,7 @@ mkdir -p .agent/skills/license-header-adder/resources
 
 ### 步骤 3：创建 SKILL.md
 
-**`.agent/skills/license-header-adder/SKILL.md`**：
+**`<skills_root>/license-header-adder/SKILL.md`**：
 
 ```markdown
 ---

package/CHANGELOG.md

@@ -7,6 +7,19 @@
 
 ## [Unreleased]
 
+## [ling-1.1.1] - 2026-03-14
+
+### 新增
+
+- Spec 项目级工作区初始化与诊断：新增 `ling spec init` / `ling spec doctor`，在工作区落盘 `.ling/spec` 资产与 `issues.csv` 校验。
+- Spec Profiles 资产：全局与项目级均包含 `profiles/`，并纳入完整性校验与回退语义。
+- Spec 资产分支拉取：`ling spec init --branch <name>` 支持从指定分支的 `.spec/` 拉取 templates/references/profiles。
+
+### 变更
+
+- Spec 状态判定强化：`ling spec status` 增加文件级完整性校验，且在 `state.json` 缺失但检测到残留 artifacts 时返回 `broken` 并给出修复提示。
+- CI 改为 npm：CI 矩阵不再依赖 bun，统一使用 `npm ci/test/run` 执行验证。
+
 ## [ling-1.1.0] - 2026-03-13
 
 ### 新增
@@ -67,7 +80,8 @@
 
 本项目在 Ling 重启前的 2.x/3.x 版本记录已冻结，不再维护。
 
-[Unreleased]: https://github.com/MisonL/Ling/compare/ling-1.1.0...HEAD
+[Unreleased]: https://github.com/MisonL/Ling/compare/ling-1.1.1...HEAD
+[ling-1.1.1]: https://github.com/MisonL/Ling/releases/tag/ling-1.1.1
 [ling-1.1.0]: https://github.com/MisonL/Ling/releases/tag/ling-1.1.0
 [ling-1.0.2]: https://github.com/MisonL/Ling/releases/tag/ling-1.0.2
 [ling-1.0.1]: https://github.com/MisonL/Ling/releases/tag/ling-1.0.1

package/bin/core/generator.js

@@ -37,6 +37,7 @@ class RuleGenerator {
         agentsMd += `1. Managed resources are synchronized under \`.agents/skills\`.\n`;
         agentsMd += `2. Do not rename managed skill folders manually.\n`;
         agentsMd += `3. Use \`ling doctor --target codex --fix\` to recover missing managed artifacts.\n`;
+        agentsMd += `4. If \`issues.csv\` exists, treat it as the task tracking source of truth and keep at most one task in \`进行中\`.\n`;
 
         // 3. Generate risk controls
         let lingRules = `# Ling Risk Controls (Codex Managed)\n\n`;