@pigcloud/skills 1.0.5 → 1.0.6

package/CHANGELOG.md

@@ -1,6 +1,6 @@
 # Pig Skills CHANGELOG
 
-> 版本变更记录，遵循 Semantic Versioning
+> 鐗堟湰鍙樻洿璁板綍锛岄伒寰?Semantic Versioning
 
 ---
 
@@ -8,20 +8,20 @@
 
 ### Changed
 - Made postinstall client-aware so it can auto-install into the detected client(s) from `INIT_CWD`.
-- Kept Codex as the only client with a real command pack so `/spec` remains the executable entry instead of a fake alias.
+- Kept Codex as the only client with a real command pack so `/spec-refinement` remains the executable entry instead of a fake alias.
 - Extended `pig-skills auto` to install the matching client folders for Codex, Claude Code, Trae, Cursor, Copilot, and Windsurf.
-- Clarified in the README and usage docs that only Codex gets `/spec`-style command files, while other clients receive skills and rules.
+- Clarified in the README and usage docs that only Codex gets `/spec-refinement`-style command files, while other clients receive skills and rules.
 - Unified the usage guides around the same client-detection and knowledge-capture model.
 
 ## [1.1.0] - 2026-06-18
 
 ### Changed
-- 重构 skill 体系说明，按当前 13 个 skill 重新梳理 README 和使用方式
-- 补充统一校验入口 `validate-skills.js`，并增加 Windows / macOS / Linux 壳
-- 将便携 Python 纳入仓库内，避免依赖系统环境
-- 统一 `spec`、`knowledge-capture`、`workflow-router` 等高频 skill 的识别与门禁表达
-- 收缩 skill frontmatter，按官方 validator 规范保留最小字段
-- 将 `handover` 合并进 `knowledge-capture`，删除独立交接 skill
+- 閲嶆瀯 skill 浣撶郴璇存槑锛屾寜褰撳墠 13 涓?skill 閲嶆柊姊崇悊 README 鍜屼娇鐢ㄦ柟寮?
+- 琛ュ厖缁熶竴鏍￠獙鍏ュ彛 `validate-skills.js`锛屽苟澧炲姞 Windows / macOS / Linux 澹?
+- 灏嗕究鎼?Python 绾冲叆浠撳簱鍐咃紝閬垮厤渚濊禆绯荤粺鐜
+- 缁熶竴 `spec-refinement`銆乣knowledge-capture`銆乣workflow-router` 绛夐珮棰?skill 鐨勮瘑鍒笌闂ㄧ琛ㄨ揪
+- 鏀剁缉 skill frontmatter锛屾寜瀹樻柟 validator 瑙勮寖淇濈暀鏈€灏忓瓧娈?
+- 灏?`handover` 鍚堝苟杩?`knowledge-capture`锛屽垹闄ょ嫭绔嬩氦鎺?skill
 
 ### Added
 - `validate-skills.js`
@@ -33,38 +33,39 @@
 ## [1.0.0] - 2024-01-20
 
 ### Added
-- 初始发布，包含 12 个框架绑定技能
-- OpenSpec 标准化规范
-- 三层渐进式加载机制
-- 跨工具兼容支持（Trae/Cursor/Claude Code/Copilot/Windsurf）
-- CLI 工具（pig-skills 命令）
+- 鍒濆鍙戝竷锛屽寘鍚?12 涓鏋剁粦瀹氭妧鑳?
+- OpenSpec 鏍囧噯鍖栬鑼?
+- 涓夊眰娓愯繘寮忓姞杞芥満鍒?
+- 璺ㄥ伐鍏峰吋瀹规敮鎸侊紙Trae/Cursor/Claude Code/Copilot/Windsurf锛?
+- CLI 宸ュ叿锛坧ig-skills 鍛戒护锛?
 
 ### Skills
 - **Core**: workflow-router, technical-design, feature-build, code-review
-- **Analysis**: spec, domain-modeling
-- **Integration**: api-docs, test-design
+- **Analysis**: spec-refinement, domain-modeling
+- **Integration**: api-contract-docs, test-design
 - **Collaboration**: knowledge-capture
 - **Infrastructure**: project-bootstrap, environment-deploy
 
 ### Core Bindings
-- Controller → Service → Mapper 分层
-- MpRealDelEntity / MpLogicDelEntity 基类
-- Result<T> 统一返回
-- BizException 异常体系
-- Lambda 查询表达式
+- Controller 鈫?Service 鈫?Mapper 鍒嗗眰
+- MpRealDelEntity / MpLogicDelEntity 鍩虹被
+- Result<T> 缁熶竴杩斿洖
+- BizException 寮傚父浣撶郴
+- Lambda 鏌ヨ琛ㄨ揪寮?
 
 ---
 
-## 计划更新
+## 璁″垝鏇存柊
 
 ### [1.2.0] - TBD
-- 技能模板可视化
-- 技能组合编排器
-- 更多框架特定规则
+- 鎶€鑳芥ā鏉垮彲瑙嗗寲
+- 鎶€鑳界粍鍚堢紪鎺掑櫒
+- 鏇村妗嗘灦鐗瑰畾瑙勫垯
 
 ### [2.0.0] - TBD
-- 技能发布平台
-- 技能订阅机制
-- 多框架支持
+- 鎶€鑳藉彂甯冨钩鍙?
+- 鎶€鑳借闃呮満鍒?
+- 澶氭鏋舵敮鎸?
+
 
 

package/README.en.md

@@ -18,11 +18,11 @@
 
 ## Common Entry Points
 
-- Spec: `spec`
+- Spec: `spec-refinement`
 - Stage routing: `workflow-router`
 - Design and implementation: `technical-design` / `feature-build`
-- Review and validation: `code-review` / `security-review` / `performance-check`
-- Fact extraction: `extract-business-facts`
+- Review and validation: `code-review` / `security-audit` / `performance-audit`
+- Fact extraction: `business-fact-extraction`
 - Knowledge capture: `knowledge-capture`
 
 ## Install
@@ -72,3 +72,4 @@ node self-test-skills.js
 - [skills/references/skill-authoring-standard.md](skills/references/skill-authoring-standard.md)
 - [skills/references/skill-reference-matrix.md](skills/references/skill-reference-matrix.md)
 - [skills/references/rule-loading-map.md](skills/references/rule-loading-map.md)
+

package/README.md

@@ -1,49 +1,49 @@
 # @pigcloud/skills
 
-> 一个面向产品、研发、测试协作的 AI 技能包。`skills/` 负责任务边界与交接，`rules/` 负责规则约束与校验，`workflow-router` 负责阶段路由，`CI / Test / Evidence` 负责交付闭环。
+> 涓€涓潰鍚戜骇鍝併€佺爺鍙戙€佹祴璇曞崗浣滅殑 AI 鎶€鑳藉寘銆俙skills/` 璐熻矗浠诲姟杈圭晫涓庝氦鎺ワ紝`rules/` 璐熻矗瑙勫垯绾︽潫涓庢牎楠岋紝`workflow-router` 璐熻矗闃舵璺敱锛宍CI / Test / Evidence` 璐熻矗浜や粯闂幆銆?
 
-## 这套系统做什么
+## 杩欏绯荤粺鍋氫粈涔?
 
-- 先路由，再执行
-- 先约束，再生成
-- 先复用，再改写
-- 先验证，再结论
+- 鍏堣矾鐢憋紝鍐嶆墽琛?
+- 鍏堢害鏉燂紝鍐嶇敓鎴?
+- 鍏堝鐢紝鍐嶆敼鍐?
+- 鍏堥獙璇侊紝鍐嶇粨璁?
 
-## 核心层
+## 鏍稿績灞?
 
-1. `workflow-router`：识别任务类型并选择下一阶段
-2. `skills/`：可复用的能力模块
-3. `rules/`：项目约束、边界和硬校验
-4. `CI / Test / Evidence`：可验证的交付门禁
+1. `workflow-router`锛氳瘑鍒换鍔＄被鍨嬪苟閫夋嫨涓嬩竴闃舵
+2. `skills/`锛氬彲澶嶇敤鐨勮兘鍔涙ā鍧?
+3. `rules/`锛氶」鐩害鏉熴€佽竟鐣屽拰纭牎楠?
+4. `CI / Test / Evidence`锛氬彲楠岃瘉鐨勪氦浠橀棬绂?
 
-## 常用入口
+## 甯哥敤鍏ュ彛
 
-- 规格澄清：`spec`
-- 阶段路由：`workflow-router`
-- 设计与实现：`technical-design` / `feature-build`
-- 审查与验证：`code-review` / `security-review` / `performance-check`
-- 事实抽取：`extract-business-facts`
-- 知识沉淀：`knowledge-capture`
+- 瑙勬牸婢勬竻锛歚spec-refinement`
+- 闃舵璺敱锛歚workflow-router`
+- 璁捐涓庡疄鐜帮細`technical-design` / `feature-build`
+- 瀹℃煡涓庨獙璇侊細`code-review` / `security-audit` / `performance-audit`
+- 浜嬪疄鎶藉彇锛歚business-fact-extraction`
+- 鐭ヨ瘑娌夋穩锛歚knowledge-capture`
 
-## 安装
+## 瀹夎
 
 ```bash
 npm install -g @pigcloud/skills
 ```
 
-## 客户端接入
+## 瀹㈡埛绔帴鍏?
 
-- Codex：见 [docs/CODEX-APP-GUIDE.md](docs/CODEX-APP-GUIDE.md)
-- Trae：见 [docs/TRAE-GUIDE.md](docs/TRAE-GUIDE.md)
-- Claude Code：见 [docs/CLAUDE-CODE-GUIDE.md](docs/CLAUDE-CODE-GUIDE.md)
-- 统一安装指南：见 [docs/client-installation-guide.md](docs/client-installation-guide.md)
+- Codex锛氳 [docs/CODEX-APP-GUIDE.md](docs/CODEX-APP-GUIDE.md)
+- Trae锛氳 [docs/TRAE-GUIDE.md](docs/TRAE-GUIDE.md)
+- Claude Code锛氳 [docs/CLAUDE-CODE-GUIDE.md](docs/CLAUDE-CODE-GUIDE.md)
+- 缁熶竴瀹夎鎸囧崡锛氳 [docs/client-installation-guide.md](docs/client-installation-guide.md)
 
-## 治理概览
+## 娌荤悊姒傝
 
-- 系统总览：见 [docs/agent-governance-overview.md](docs/agent-governance-overview.md)
-- 技能扩展指南：见 [docs/skills-extension-guide.md](docs/skills-extension-guide.md)
+- 绯荤粺鎬昏锛氳 [docs/agent-governance-overview.md](docs/agent-governance-overview.md)
+- 鎶€鑳芥墿灞曟寚鍗楋細瑙?[docs/skills-extension-guide.md](docs/skills-extension-guide.md)
 
-## 校验
+## 鏍￠獙
 
 ```bash
 node validate-skills.js
@@ -54,15 +54,15 @@ node scripts/validate-skill-replay-signals.js
 node self-test-skills.js
 ```
 
-## 目录说明
+## 鐩綍璇存槑
 
-- `skills/`：技能正文
-- `skills/references/`：编写标准、参考矩阵、加载映射
-- `rules/`：规则入口与规则包
-- `docs/`：安装、治理和工作流说明
-- `bin/`：CLI、自动安装、postinstall
+- `skills/`锛氭妧鑳芥鏂?
+- `skills/references/`锛氱紪鍐欐爣鍑嗐€佸弬鑰冪煩闃点€佸姞杞芥槧灏?
+- `rules/`锛氳鍒欏叆鍙ｄ笌瑙勫垯鍖?
+- `docs/`锛氬畨瑁呫€佹不鐞嗗拰宸ヤ綔娴佽鏄?
+- `bin/`锛欳LI銆佽嚜鍔ㄥ畨瑁呫€乸ostinstall
 
-## 入口文档
+## 鍏ュ彛鏂囨。
 
 - [AGENTS.md](AGENTS.md)
 - [docs/README.md](docs/README.md)
@@ -72,3 +72,5 @@ node self-test-skills.js
 - [skills/references/skill-authoring-standard.md](skills/references/skill-authoring-standard.md)
 - [skills/references/skill-reference-matrix.md](skills/references/skill-reference-matrix.md)
 - [skills/references/rule-loading-map.md](skills/references/rule-loading-map.md)
+
+

package/bin/cli.js

@@ -43,20 +43,20 @@ const chalk = {
 };
 
 const SKILLS = [
-  { name: 'workflow-router', category: 'core', description: 'route workflow stages' },
-  { name: 'spec', category: 'analysis', description: 'turn product input into an executable spec' },
-  { name: 'technical-design', category: 'core', description: 'shape implementation design' },
-  { name: 'feature-build', category: 'core', description: 'implement features safely' },
-  { name: 'code-review', category: 'core', description: 'review code changes' },
-  { name: 'domain-modeling', category: 'analysis', description: 'extract domain knowledge' },
-  { name: 'extract-business-facts', category: 'analysis', description: 'extract business facts from code' },
-  { name: 'api-docs', category: 'integration', description: 'document API contracts' },
-  { name: 'test-design', category: 'integration', description: 'design test coverage' },
-  { name: 'security-review', category: 'review', description: 'review security risks' },
-  { name: 'performance-check', category: 'review', description: 'review performance risks' },
-  { name: 'knowledge-capture', category: 'collaboration', description: 'capture reusable knowledge' },
-  { name: 'project-bootstrap', category: 'infrastructure', description: 'bootstrap project scaffolds' },
-  { name: 'environment-deploy', category: 'infrastructure', description: 'deploy supporting environments' }
+  { name: 'workflow-router', category: 'core', description: '路由工作阶段' },
+  { name: 'spec-refinement', category: 'analysis', description: '将需求输入整理为可执行规格' },
+  { name: 'technical-design', category: 'core', description: '梳理实现设计' },
+  { name: 'feature-build', category: 'core', description: '安全实现功能变更' },
+  { name: 'code-review', category: 'core', description: '审查代码变更' },
+  { name: 'domain-modeling', category: 'analysis', description: '提炼领域知识' },
+  { name: 'business-fact-extraction', category: 'analysis', description: '从代码中提取业务事实' },
+  { name: 'api-contract-docs', category: 'integration', description: '整理 API 契约文档' },
+  { name: 'test-design', category: 'integration', description: '设计测试覆盖' },
+  { name: 'security-audit', category: 'review', description: '审查安全风险' },
+  { name: 'performance-audit', category: 'review', description: '审查性能风险' },
+  { name: 'knowledge-capture', category: 'collaboration', description: '沉淀可复用知识' },
+  { name: 'project-bootstrap', category: 'infrastructure', description: '初始化项目骨架' },
+  { name: 'environment-deploy', category: 'infrastructure', description: '部署支撑环境' }
 ];
 
 const TOOL_CONFIGS = {
@@ -568,7 +568,7 @@ async function run() {
   if (command === 'list') {
     console.log(chalk.blue('Installed skills:'));
     SKILLS.forEach(skill => {
-      console.log(chalk.green(`  鉁?${skill.name}`) + chalk.gray(` - ${skill.description}`));
+      console.log(chalk.green(`  - ${skill.name}`) + chalk.gray(` - ${skill.description}`));
     });
     console.log(chalk.gray(`\nTotal: ${SKILLS.length} skills`));
     return;
@@ -686,3 +686,4 @@ run().catch(error => {
   process.exitCode = 1;
 });
 
+

package/package.json

@@ -1,70 +1,70 @@
-{
+{
   "name": "@pigcloud/skills",
-  "version": "1.0.5",
-  "description": "AI skills pack with client-aware installation, shared skills and rules, Codex command entries, and Pig Cloud-specific overlays for requirements, implementation, and knowledge curation.",
-  "author": "Pig Skills Maintainers",
-  "license": "MIT",
-  "keywords": [
-    "ai",
-    "skills",
-    "openspec",
-    "pig-cloud",
-    "coding",
-    "distillation",
-    "agent",
-    "claude",
-    "cursor",
-    "copilot",
-    "trae"
-  ],
-  "repository": {
-    "type": "git",
-    "url": "https://gitee.com/rebys/pig-skills.git"
-  },
-  "bugs": {
-    "url": "https://gitee.com/rebys/pig-skills/issues"
-  },
-  "homepage": "https://gitee.com/rebys/pig-skills",
-  "bin": {
-    "pig-skills": "./bin/cli.js"
-  },
-  "main": "./index.js",
-  "files": [
-    "bin/",
-    "install.cmd",
-    "install.ps1",
-    "install.sh",
-    "pig-cloud-skills-commands/",
-    "rules/",
-    "skills/",
-    "scripts/",
-    "templates/",
-    "index.js",
-    "README.md",
-    "CHANGELOG.md"
-  ],
-  "scripts": {
-    "test": "node validate-skills.js && node scripts/validate-skill-shapes.js && node scripts/validate-rules.js && node scripts/validate-skill-stop-rules.js && node scripts/validate-skill-replay-signals.js && node self-test-skills.js",
-    "test:self": "node self-test-skills.js",
-    "replay:golden": "node scripts/run-golden-replays.js",
-    "replay:golden:mock": "node scripts/run-golden-replays.js --provider mock",
-    "postinstall": "node bin/postinstall.js",
-    "validate:skills": "node validate-skills.js",
-    "validate:shapes": "node scripts/validate-skill-shapes.js",
-    "validate:rules": "node scripts/validate-rules.js",
-    "validate:stop-rules": "node scripts/validate-skill-stop-rules.js",
-    "validate:replay-signals": "node scripts/validate-skill-replay-signals.js"
-  },
-  "engines": {
-    "node": ">=14.0.0"
-  },
-  "dependencies": {
-    "commander": "^11.0.0",
-    "fs-extra": "^11.0.0",
-    "chalk": "^4.1.0",
-    "inquirer": "^8.0.0"
-  },
-  "devDependencies": {
-    "jest": "^29.0.0"
-  }
-}
+  "version": "1.0.6",
+  "description": "面向 Codex、Trae 和 Claude Code 的 AI 技能包，提供共享技能、规则约束、工作流路由和 Pig Cloud 专属覆盖层。",
+  "author": "Pig Skills Maintainers",
+  "license": "MIT",
+  "keywords": [
+    "ai",
+    "skills",
+    "openspec",
+    "pig-cloud",
+    "coding",
+    "distillation",
+    "agent",
+    "claude",
+    "cursor",
+    "copilot",
+    "trae"
+  ],
+  "repository": {
+    "type": "git",
+    "url": "https://gitee.com/rebys/pig-skills.git"
+  },
+  "bugs": {
+    "url": "https://gitee.com/rebys/pig-skills/issues"
+  },
+  "homepage": "https://gitee.com/rebys/pig-skills",
+  "bin": {
+    "pig-skills": "./bin/cli.js"
+  },
+  "main": "./index.js",
+  "files": [
+    "bin/",
+    "install.cmd",
+    "install.ps1",
+    "install.sh",
+    "pig-cloud-skills-commands/",
+    "rules/",
+    "skills/",
+    "scripts/",
+    "templates/",
+    "index.js",
+    "README.md",
+    "CHANGELOG.md"
+  ],
+  "scripts": {
+    "test": "node validate-skills.js && node scripts/validate-skill-shapes.js && node scripts/validate-rules.js && node scripts/validate-skill-stop-rules.js && node scripts/validate-skill-replay-signals.js && node self-test-skills.js",
+    "test:self": "node self-test-skills.js",
+    "replay:golden": "node scripts/run-golden-replays.js",
+    "replay:golden:mock": "node scripts/run-golden-replays.js --provider mock",
+    "postinstall": "node bin/postinstall.js",
+    "validate:skills": "node validate-skills.js",
+    "validate:shapes": "node scripts/validate-skill-shapes.js",
+    "validate:rules": "node scripts/validate-rules.js",
+    "validate:stop-rules": "node scripts/validate-skill-stop-rules.js",
+    "validate:replay-signals": "node scripts/validate-skill-replay-signals.js"
+  },
+  "engines": {
+    "node": ">=14.0.0"
+  },
+  "dependencies": {
+    "commander": "^11.0.0",
+    "fs-extra": "^11.0.0",
+    "chalk": "^4.1.0",
+    "inquirer": "^8.0.0"
+  },
+  "devDependencies": {
+    "jest": "^29.0.0"
+  }
+}

package/rules/coding/implementation.md

@@ -1,30 +1,31 @@
 # Coding Implementation Rules
 
-## 默认做法
+## 榛樿鍋氭硶
 
 - Implement only the confirmed scope.
 - Keep the change small, reviewable, and verifiable.
 - Preserve the agreed boundary while coding.
 - Prefer one implementation path over speculative alternatives unless the task explicitly asks for options.
 
-## 禁区
+## 绂佸尯
 
-- Do not rewrite the spec while implementing.
+- Do not rewrite the spec-refinement while implementing.
 - Do not widen the scope because implementation is difficult.
 - Do not skip validation.
 - Do not bundle unrelated cleanup into the same change unless it reduces risk.
 
-## 检查
+## 妫€鏌?
 
 - Does the code stay within scope?
 - Can the result be validated locally?
 - Is the implementation easy to review in one pass?
 - Would the diff still make sense if the task title were removed?
 
-## 回放信号
+## 鍥炴斁淇″彿
 
 - Trigger when the request is about delivery, refactor, or code changes.
 
 ## References
 
 - `coding/index.md`
+

package/rules/product/project-context.md

@@ -1,29 +1,30 @@
 # Project Context Rules
 
-## 默认做法
+## 榛樿鍋氭硶
 
 - Capture what the current project already guarantees before rewriting the requirement.
 - Separate product intent, existing project facts, and assumptions.
 - Prefer current repo docs, release notes, and existing behavior over memory.
 - Record conflicts when product demand does not match current project facts.
 
-## 禁区
+## 绂佸尯
 
 - Do not turn implementation details into product requirements.
 - Do not ignore existing project facts when they are available.
 - Do not hide conflicts behind vague wording.
 
-## 检查
+## 妫€鏌?
 
 - Are product intent and project facts separated?
 - Are conflicts and open questions explicit?
-- Does the output still work for spec refinement?
+- Does the output still work for spec-refinement?
 - Is the project context based on current evidence?
 
-## 回放信号
+## 鍥炴斁淇″彿
 
 - Trigger when the task needs product understanding aligned with the current project state.
 
 ## References
 
 - `product/index.md`
+

package/rules/skill-profile-map.json

@@ -3,7 +3,7 @@
     "bundle": "workflow",
     "profile": "router"
   },
-  "spec": {
+  "spec-refinement": {
     "bundle": "workflow",
     "profile": "refinement"
   },
@@ -27,19 +27,19 @@
     "bundle": "product",
     "profile": "modeling"
   },
-  "extract-business-facts": {
+  "business-fact-extraction": {
     "bundle": "product",
     "profile": "modeling"
   },
-  "api-docs": {
+  "api-contract-docs": {
     "bundle": "docs",
     "profile": "api"
   },
-  "security-review": {
+  "security-audit": {
     "bundle": "review",
     "profile": "security"
   },
-  "performance-check": {
+  "performance-audit": {
     "bundle": "review",
     "profile": "performance"
   },
@@ -56,3 +56,4 @@
     "profile": "scaffold"
   }
 }
+

package/rules/skill-profile-map.md

@@ -7,16 +7,16 @@ This file explains which canonical skill loads which rules bundle and profile.
 | Skill | Bundle | Profile |
 |---|---|---|
 | `workflow-router` | `workflow` | `router` |
-| `spec` | `workflow` | `refinement` |
+| `spec-refinement` | `workflow` | `refinement` |
 | `technical-design` | `coding` | `analysis` |
 | `feature-build` | `coding` | `implementation` |
 | `test-design` | `coding` | `testing` |
 | `code-review` | `review` | `code` |
 | `domain-modeling` | `product` | `modeling` |
-| `extract-business-facts` | `product` | `modeling` |
-| `api-docs` | `docs` | `api` |
-| `security-review` | `review` | `security` |
-| `performance-check` | `review` | `performance` |
+| `business-fact-extraction` | `product` | `modeling` |
+| `api-contract-docs` | `docs` | `api` |
+| `security-audit` | `review` | `security` |
+| `performance-audit` | `review` | `performance` |
 | `knowledge-capture` | `docs` | `capture` |
 | `project-bootstrap` | `coding` | `scaffold` |
 | `environment-deploy` | `coding` | `scaffold` |
@@ -26,3 +26,4 @@ This file explains which canonical skill loads which rules bundle and profile.
 - `rule_profile` in skill frontmatter is the source of truth.
 - `skill-profile-map.json` is kept as a validation and routing fallback.
 - `code-review` intentionally uses the generic `code` profile in this repository. Stack-specific review behavior is added by overlays.
+