universal-dev-standards 6.8.0 → 6.9.0

package/bundled/skills/commands/init.md

@@ -41,7 +41,7 @@ Use AskUserQuestion with multiSelect to ask which AI tools to configure:
 | **OpenCode** | `AGENTS.md` | ✅ | ✅ |
 | **Gemini CLI** | `GEMINI.md` | ✅ | ✅ |
 | **Codex** | `AGENTS.md` | ✅ | ❌ |
-| **Antigravity** | `INSTRUCTIONS.md` | ✅ | ❌ |
+| **Antigravity** | `.agents/AGENTS.md` | ✅ | ❌ |
 
 Pre-select tools detected in the environment. Note: Codex and OpenCode share `AGENTS.md`.
 
@@ -226,7 +226,6 @@ Use AskUserQuestion for integration file content:
 | Option | Description |
 |--------|-------------|
 | **Standard (Recommended)** | Summary + task mapping, AI knows when to read which standard |
-| **Full Embed** | Embed all rules, AI can use immediately but larger file |
 | **Minimal** | File references only, best with Skills |
 
 ### Step 13: Confirm and Execute | 步驟 13：確認並執行
@@ -312,7 +311,7 @@ See `uds init --help` for all options.
 9. **語言擴展** — 偵測到語言時詢問
 10. **框架擴展** — 偵測到框架時詢問
 11. **地區設定** — English / Traditional Chinese
-12. **內容模式** — Standard / Full Embed / Minimal
+12. **內容模式** — Standard / Minimal
 13. **確認並執行** — 展示摘要，確認後一次執行所有安裝
 
 **IMPORTANT**: AskUserQuestion 最多 4 個選項。3+ 工具時必須使用 Smart Grouping 兩階段策略。

package/bundled/skills/commit-standards/SKILL.md

@@ -147,6 +147,8 @@ After `/commit` completes, the AI assistant should suggest:
 
 ## Reference | 參考
 
+- [Conventional Commits Guide](./conventional-commits.md) — Read it when you need the exact type, scope and format rules.
+- [Output Language Options](./language-options.md) — Read it when deciding which language a commit message is written in.
 - Detailed guide: [guide.md](./guide.md)
 - Core standard: [commit-message-guide.md](../../core/commit-message-guide.md)
 

package/bundled/skills/contract-test-assistant/SKILL.md

@@ -111,6 +111,7 @@ After `/contract-test` completes:
 
 ## Reference | 參考
 
+- Detailed guide: [guide.md](./guide.md) — contract testing strategy and setup. Read it when configuring Pact/OpenAPI or wiring contract tests into CI.
 - Detailed guide: [contract-testing.md](../../options/testing/contract-testing.md)
 - Related: [api-design-assistant](../api-design-assistant/SKILL.md)
 

package/bundled/skills/dev-methodology/SKILL.md

@@ -101,6 +101,10 @@ After `/methodology` completes, the AI assistant should suggest based on the sel
 
 ## Reference | 參考
 
+- [Create Custom Methodology Guide](./create-methodology.md) — Read it when building a custom methodology rather than using a shipped one.
+- [Integrated Development Flow Guide](./integrated-flow.md) — Read it when combining several methodologies into one flow.
+- [Workflow Prerequisite Checking / 工作流前置步驟檢查](./prerequisite-check.md) — Read it when a workflow step needs its prerequisites checked first.
+- [Methodology Runtime Guide](./runtime.md) — Read it when you need to know how a methodology behaves while it runs.
 - Detailed guide: [guide.md](./guide.md)
 
 

package/bundled/skills/observability-assistant/SKILL.md

@@ -121,6 +121,7 @@ Before deploying a service to production:
 
 ## Reference | 參考
 
+- Detailed guide: [guide.md](./guide.md) — the three pillars (logs, metrics, traces) in depth. Read it when setting up monitoring, choosing metric types, implementing tracing, or assessing maturity.
 - Core standard: [observability-standards.md](../../core/observability-standards.md)
 - Core standard: [alerting-standards.md](../../core/alerting-standards.md)
 - Core standard: [slo-standards.md](../../core/slo-standards.md)

package/bundled/skills/project-discovery/SKILL.md

@@ -147,6 +147,7 @@ After `/discover` completes, the AI assistant should suggest based on the assess
 
 ## Reference | 參考
 
+- Step-by-step workflow: [workflow.md](./workflow.md) — the discovery steps in order (code health, architecture, documentation inventory, review snapshot, dependency and security). Read it when actually running a discovery rather than deciding whether to.
 - Detailed guide: [guide.md](./guide.md)
 
 

package/bundled/skills/project-structure-guide/SKILL.md

@@ -168,6 +168,7 @@ After `/project-structure` completes, the AI assistant should suggest:
 
 ## Related Standards
 
+- [Language-specific patterns](./language-patterns.md) — concrete directory layouts per language (Node.js/TypeScript, Python, Go, and others). Read it when laying out a project in a specific language.
 - [Core: Project Structure](../../core/project-structure.md)
 - [Core: Documentation Structure](../../core/documentation-structure.md)
 - [Guide: File Placement Decision Guide](../../core/guides/file-placement-guide.md)

package/bundled/skills/release-standards/SKILL.md

@@ -132,6 +132,9 @@ After `/release` completes, the AI assistant should suggest:
 
 ## Reference | 參考
 
+- [Changelog Format Guide](./changelog-format.md) — Read it when writing or reviewing a changelog entry.
+- [Release Workflow Guide](./release-workflow.md) — Read it when actually cutting a release, step by step.
+- [Semantic Versioning Guide](./semantic-versioning.md) — Read it when deciding whether a change is major, minor or patch.
 - Detailed guide: [guide.md](./guide.md)
 - Core standard: [versioning.md](../../core/versioning.md)
 

package/bundled/skills/requirement-assistant/SKILL.md

@@ -75,6 +75,8 @@ After `/requirement` completes, the AI assistant should suggest:
 
 ## Reference | 參考
 
+- [Requirement Completeness Checklist](./requirement-checklist.md) — Read it when checking a requirement is complete before it is accepted.
+- [Requirement Writing Guide](./requirement-writing.md) — Read it when writing a requirement from scratch.
 - Detailed guide: [guide.md](./guide.md)
 - Core standard: [requirement-engineering.md](../../core/requirement-engineering.md)
 

package/bundled/skills/reverse-engineer/SKILL.md

@@ -147,6 +147,9 @@ After `/reverse` (full or `spec`) completes, the AI assistant should suggest:
 
 ## Reference | 參考
 
+- [BDD Extraction Workflow Guide](./bdd-extraction.md) — Read it when extracting BDD scenarios out of an existing spec.
+- [TDD Analysis Workflow Guide](./tdd-analysis.md) — Read it when analysing test coverage against scenarios and finding the gaps.
+- Step-by-step workflow: [workflow.md](./workflow.md) — the reverse-engineering phases in order (code scanning, data models, configuration, test analysis, coverage). Read it when actually running the process rather than deciding whether to.
 - Detailed guide: [guide.md](./guide.md)
 - Core standard: [reverse-engineering-standards.md](../../core/reverse-engineering-standards.md)
 

package/bundled/skills/runbook-assistant/SKILL.md

@@ -52,6 +52,7 @@ Any deploy runbook that includes a destructive-update pattern (stop → swap →
 
 ## Reference | 參考
 
+- Detailed guide: [guide.md](./guide.md) — runbook creation, organization and validation. Read it when writing runbooks, reviewing operational procedures, planning drills, or assessing coverage.
 - Core standard: [runbook-standards.md](../../core/runbook-standards.md)
 - Related: [alerting-standards.md](../../core/alerting-standards.md)
 - Related: [postmortem-standards.md](../../core/postmortem-standards.md)

package/bundled/skills/slo-assistant/SKILL.md

@@ -46,6 +46,7 @@ Guide SLI selection, SLO setting methodology, and Error Budget management.
 
 ## Reference | 參考
 
+- Detailed guide: [guide.md](./guide.md) — SLI/SLO/error-budget definition and management. Read it when defining SLOs, selecting SLIs, calculating error budgets, or setting reliability targets.
 - Core standard: [slo-standards.md](../../core/slo-standards.md)
 - Related: [observability-standards.md](../../core/observability-standards.md)
 - Related: [alerting-standards.md](../../core/alerting-standards.md)

package/bundled/skills/tdd-assistant/SKILL.md

@@ -87,6 +87,8 @@ After `/tdd` completes, the AI assistant should suggest:
 
 ## Reference | 參考
 
+- [TDD Language Examples](./language-examples.md) — Read it when you need a concrete example in a specific language.
+- [TDD Workflow Guide](./tdd-workflow.md) — Read it when running the red-green-refactor cycle end to end.
 - Detailed guide: [guide.md](./guide.md)
 - Core standard: [test-driven-development.md](../../core/test-driven-development.md)
 

package/bundled/templates/.ai-context.yaml.template

@@ -0,0 +1,194 @@
+# ============================================================
+# .ai-context.yaml - AI Context Configuration Template
+# ============================================================
+#
+# This file helps AI assistants understand your project structure
+# and optimize their analysis and code generation.
+#
+# Usage:
+# 1. Copy this file to your project root as `.ai-context.yaml`
+# 2. Customize the values for your project
+# 3. AI tools will use this for better context management
+#
+# Reference: core/ai-friendly-architecture.md
+# ============================================================
+
+version: 1.0.0
+
+# ============================================================
+# PROJECT INFORMATION
+# ============================================================
+project:
+  # Project name (should match package.json or pyproject.toml)
+  name: my-project
+
+  # Project type affects analysis strategy
+  # Options: web-app | library | cli | api | monorepo | mobile
+  type: web-app
+
+  # Primary programming language
+  # Options: typescript | javascript | python | go | rust | java | other
+  primary-language: typescript
+
+  # Brief description for AI context
+  description: |
+    A brief description of what this project does.
+    Include key features and architectural decisions.
+
+# ============================================================
+# MODULE DEFINITIONS
+# ============================================================
+# Define logical modules in your codebase for structured analysis.
+# AI will use these boundaries to chunk large codebases efficiently.
+
+modules:
+  # Example: Authentication module
+  - name: auth
+    path: src/auth/
+    entry: index.ts
+    description: User authentication and session management
+    dependencies:
+      - database
+      - crypto
+    # Priority affects analysis order (high | medium | low)
+    priority: high
+
+  # Example: API module
+  - name: api
+    path: src/api/
+    entry: routes.ts
+    description: REST API endpoints and handlers
+    dependencies:
+      - auth
+      - database
+    priority: high
+
+  # Example: Database module
+  - name: database
+    path: src/db/
+    entry: index.ts
+    description: Database connection and models
+    dependencies: []
+    priority: high
+
+  # Example: Utilities module
+  - name: utils
+    path: src/utils/
+    entry: index.ts
+    description: Shared utility functions
+    dependencies: []
+    priority: low
+
+# ============================================================
+# ANALYSIS HINTS
+# ============================================================
+# Guide AI tools on how to analyze this project
+
+analysis-hints:
+  # Main entry points - AI starts analysis here
+  entry-points:
+    - src/main.ts
+    - src/index.ts
+
+  # Patterns to ignore during analysis
+  ignore-patterns:
+    - node_modules
+    - dist
+    - build
+    - coverage
+    - "*.test.ts"
+    - "*.spec.ts"
+    - __pycache__
+    - .venv
+
+  # Architecture type affects analysis approach
+  # Options: layered | microservices | modular | monolith | event-driven
+  architecture-type: layered
+
+  # Key configuration files to understand project setup
+  config-files:
+    - package.json
+    - tsconfig.json
+    - .env.example
+
+# ============================================================
+# DOCUMENTATION REFERENCES
+# ============================================================
+# Point AI to different documentation layers
+
+documentation:
+  # Level 1: Quick reference (< 500 tokens)
+  quick-ref: docs/QUICK-REF.md
+
+  # Level 2: Detailed architecture (< 5000 tokens)
+  detailed: docs/ARCHITECTURE.md
+
+  # Level 3: Full examples
+  examples: docs/examples/
+
+  # API documentation
+  api-docs: docs/api/
+
+  # Changelog for understanding recent changes
+  changelog: CHANGELOG.md
+
+# ============================================================
+# RLM CONTEXT STRATEGY
+# ============================================================
+# Configuration for handling large codebases with AI
+
+context-strategy:
+  # Maximum tokens per analysis chunk
+  max-chunk-size: 50000
+
+  # Token overlap between chunks for context continuity
+  overlap: 500
+
+  # Analysis pattern
+  # Options: hierarchical | parallel | sequential
+  analysis-pattern: hierarchical
+
+  # Enable RLM-aware processing
+  enable-rlm: true
+
+# ============================================================
+# CUSTOM ANNOTATIONS
+# ============================================================
+# Define project-specific code annotation patterns
+
+annotations:
+  # Security-related code markers
+  security:
+    - "@ai-security"
+    - "@security-critical"
+
+  # Performance-critical code markers
+  performance:
+    - "@ai-performance"
+    - "@perf-critical"
+
+  # Complexity hints
+  complexity:
+    - "@ai-complexity"
+
+# ============================================================
+# TEAM CONVENTIONS
+# ============================================================
+# Help AI understand your team's conventions
+
+conventions:
+  # Naming conventions
+  naming:
+    files: kebab-case        # kebab-case | camelCase | snake_case | PascalCase
+    functions: camelCase
+    classes: PascalCase
+    constants: UPPER_SNAKE
+
+  # Code style
+  style:
+    indent: 2
+    quotes: single
+    semicolons: true
+
+  # Commit message format
+  commits: conventional      # conventional | angular | custom

package/bundled/templates/CLAUDE.md.template

@@ -0,0 +1,145 @@
+# CLAUDE.md Template
+# CLAUDE.md 範本
+
+> Copy this file to your project root as `CLAUDE.md` or `.cursorrules`.
+>
+> 將此檔案複製到專案根目錄，命名為 `CLAUDE.md` 或 `.cursorrules`。
+
+---
+
+# Project AI Collaboration Guidelines
+# 專案 AI 協作規範
+
+## 1. Certainty Labels | 確定性標籤
+
+When analyzing code or making statements, use these tags:
+
+分析程式碼或陳述事實時，使用以下標籤：
+
+| Tag | Use When | 使用時機 |
+|-----|----------|---------|
+| `[Confirmed]` / `[已確認]` | Direct evidence from code/docs | 直接來自程式碼/文件的證據 |
+| `[Inferred]` / `[推測]` | Logical deduction from evidence | 基於證據的邏輯推論 |
+| `[Assumption]` / `[假設]` | Based on common patterns | 基於常見模式（需驗證） |
+| `[Unknown]` / `[未知]` | Information not available | 資訊不可得 |
+
+**Rules | 規則**:
+- Always cite sources: `[Source: Code] file.ts:42`
+- Never fabricate APIs, configs, or requirements
+- Ask for clarification when unsure
+
+---
+
+## 2. Recommendations | 建議原則
+
+When presenting multiple options, **always include a recommendation**:
+
+提供多個選項時，**必須包含推薦選項**：
+
+```
+Options:
+1. Option A - description
+2. Option B - description
+3. Option C - description
+
+**Recommended: Option A** because [reasoning]
+```
+
+---
+
+## 3. Quality Gates | 質量關卡
+
+Before suggesting a commit, verify:
+
+建議 commit 前，驗證：
+
+- [ ] Build passes (zero errors, zero warnings)
+- [ ] All tests pass
+- [ ] Code follows project standards
+- [ ] New code has tests
+
+**Never auto-execute git commands.** Show commands and wait for user confirmation.
+
+**不要自動執行 git 指令。** 顯示指令並等待使用者確認。
+
+---
+
+## 4. Project Structure | 專案結構
+
+<!-- Customize this section for your project -->
+<!-- 依專案需求自訂此區塊 -->
+
+### Directories | 目錄
+
+| Directory | Purpose | gitignore? |
+|-----------|---------|------------|
+| `src/` | Source code | No |
+| `tests/` | Test files | No |
+| `dist/` | Build output | **Yes** |
+
+<!-- Common build artifacts — uncomment relevant lines in your .gitignore: -->
+<!-- node_modules/       # Node.js -->
+<!-- __pycache__/        # Python -->
+<!-- .venv/              # Python virtualenv -->
+<!-- target/             # Java Maven / Rust -->
+<!-- dist/               # General -->
+<!-- build/              # General -->
+
+### Conventions | 慣例
+
+- Source files: `src/`
+- Test files: `tests/` or colocated with source
+- Build output: `dist/` (gitignored)
+
+---
+
+## 5. Project-Specific Rules | 專案特定規則
+
+<!-- Add your project-specific rules here -->
+<!-- 在此新增專案特定規則 -->
+
+### Build Commands | 建置指令
+
+<!-- Commands vary by ecosystem. Uncomment and adjust for your project: -->
+<!-- Node.js:   npm run build && npm test -->
+<!-- Python:    python -m build && python -m pytest -->
+<!-- Go:        go build ./... && go test ./... -->
+<!-- Java (Maven): mvn package && mvn test -->
+<!-- Rust:      cargo build && cargo test -->
+
+```bash
+# Development build
+{{BUILD_COMMAND}}
+
+# Run tests
+{{TEST_COMMAND}}
+
+# Lint check
+{{LINT_COMMAND}}
+```
+
+### Output Language | 產出語言
+
+This project uses **English** commit messages.
+<!-- Options: English | Traditional Chinese | Bilingual -->
+
+### Conversation Language | 對話語言
+
+AI should respond in **Traditional Chinese**.
+<!-- Options: English | Traditional Chinese -->
+
+---
+
+## Reference | 參考
+
+This template is based on [universal-dev-standards](https://github.com/AsiaOstrich/universal-dev-standards):
+
+- [Anti-Hallucination Standards](https://github.com/AsiaOstrich/universal-dev-standards/blob/main/core/anti-hallucination.md)
+- [Check-in Standards](https://github.com/AsiaOstrich/universal-dev-standards/blob/main/core/checkin-standards.md)
+- [Project Structure](https://github.com/AsiaOstrich/universal-dev-standards/blob/main/core/project-structure.md)
+
+---
+
+## License | 授權
+
+This template is released under [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/).