@boyingliu01/xp-gate 0.7.0 → 0.8.0

package/plugins/claude-code/skills/ralph-loop/references/components/tool-descriptions.md

@@ -0,0 +1,32 @@
+# tool-descriptions.md — Ralph Loop 各步骤工具链（AHE 组件分解）
+
+> **本文是 `skills/ralph-loop/SKILL.md` 中构建步骤的 AHE 对齐展开。**
+
+## 组件职责
+
+描述 Ralph Loop 中每个 REQ 执行的具体工具链：TDD 流、回归测试、成本监控。
+
+## 构建步骤
+
+| 步骤 | 动作 | 说明 |
+|------|------|------|
+| 1 | 加载当前 REQ | 从 specification.yaml 获取下一个 READY REQ |
+| 2 | 加载 learnings | 从 progress.log 加载 permanent + contextual learnings |
+| 3 | 测试基础设施检查 | 检查 test-utils.ts 是否存在且导出 createTestApp()、withTestDb()。不存在 → dispatch test-infra subagent，retry max 2，失败 → BLOCK/fallback |
+| 4 | TDD (RED→GREEN→REFACTOR) | test-driven-development skill（含 TDD 铁律 + Mock 边界注入）|
+| 5 | 全量回归测试 | 运行全部现有测试 |
+| 6 | 测试先行比率检查 (L1b) | 新增测试行数 / (新增测试 + 新增实现) ≥ 40% |
+| 7 | 记录 progress.log | 将 learnings 分类存储 (permanent/contextual) |
+| 8 | 成本检查 | token 使用量是否超阈值 |
+| 9 | 完成/继续 | 所有 REQ 完成 → 结束；否则 → 下一个 REQ |
+
+## 语言特定
+
+通过 `--lang` 注入对应 TDD skill: `springboot-tdd`, `django-tdd`, `golang-testing`
+
+## AHE 分类
+
+| 字段 | 值 |
+|------|---|
+| 组件类型 | Tool Description |
+| 修改频率预期 | 高 |

package/plugins/claude-code/skills/ralph-loop/references/phase-2-build-ralph.md

@@ -0,0 +1,89 @@
+# Ralph Loop — Phase 2 BUILD 默认模式
+
+> ralph-loop 是 Sprint-Flow Phase 2 BUILD 的默认执行模式。token-constraint 优先：每次只处理一个 REQ，干净上下文，全量回归。
+
+## 模式切换
+
+### 默认行为
+
+```bash
+/sprint-flow "需求描述"
+# → Phase 2 自动使用 ralph-loop 模式
+```
+
+### 可选并行模式
+
+```bash
+/sprint-flow "需求描述" --mode parallel
+# → 旧有行为：一次性并行 dispatch 所有需求
+```
+
+## 核心差异
+
+| 维度 | ralph-loop (默认) | --mode parallel (可选) |
+|------|-------------------|----------------------|
+| 需求源 | specification.yaml | specification.yaml |
+| 执行方式 | 逐 REQ 串行迭代 | 一次性并行 dispatch |
+| 上下文 | 每个 REQ 独立 dispatch，干净上下文 | 共享 session，线性增长 |
+| 验证范围 | **全量测试**（含跨 REQ 回归） | 关联测试 |
+| AGENTS.md 更新 | **orchestrator 统一写** | subagent 写 |
+| 依赖排序 | 拓扑排序 + 同层 priority | 无 |
+
+## 流程
+
+```
+默认模式:                          ralph-loop 模式:
+┌──────────────────────┐           ┌──────────────────────────┐
+│ dispatching-parallel │           │ 读取 specification.yaml  │
+│ -agents              │           │ 构建依赖图                │
+│                      │           │ 拓扑排序 (Kahn's algo)    │
+│ 一次性 dispatch 所有  │           └──────────┬───────────────┘
+│ 共享同一 session      │                      ▼
+└──────────┬───────────┘           ┌──────────────────────────┐
+           │                       │ 迭代循环:                │
+           ▼                       │  取 next READY REQ       │
+┌──────────────────────┐           │  dispatch 独立 subagent  │
+│ verification +       │           │  (clean context)         │
+│   commit             │           │  L1: typecheck+lint      │
+└──────────────────────┘           │  L2: 全量测试 ← 回归检测 │
+                                   │  L3: coverage ≥ 80%      │
+                                   │  PASS → commit + learn   │
+                                   │  FAIL → retry max 3      │
+                                   └──────────┬───────────────┘
+                                              ▼
+                                         Phase 3 REVIEW
+```
+
+## 与 Sprint-Flow 参数交互
+
+| 参数 | 行为 (默认=ralph-loop) |
+|------|----------------------|
+| `--stop-at build` | 执行完 ralph-loop 后停止 |
+| `--resume-from build` | 从 checkpoint 恢复，跳过已 done REQs |
+| `--phase build-only` | 只执行 ralph-loop |
+| `--mode parallel` | 切换回旧有并行模式 |
+
+## Token 对比
+
+| REQ 数量 | 默认模式 | ralph-loop | 节约 |
+|---------|---------|-----------|------|
+| 3 | ~15k | ~9k | 40% |
+| 5 | ~50k | ~25k | 50% |
+| 10 | ~150k | ~50k | 67% |
+
+## 集成检查点
+
+Ralph Loop 完成后返回：
+
+```json
+{
+  "mode": "ralph-loop",
+  "specification_source": "specification.yaml",
+  "topology_order": ["REQ-001", "REQ-002", "REQ-003"],
+  "requirements": { "total": 6, "done": 6, "pending": 0, "blocked": 0 },
+  "learnings": { "permanent": ["..."], "contextual": ["..."] },
+  "status": "completed"
+}
+```
+
+Phase 3 REVIEW 正常执行（delphi code-walkthrough + test-specification-alignment）。PARTIAL 状态时仅检查 done REQs。

package/plugins/claude-code/skills/ralph-loop/templates/progress-log.md

@@ -0,0 +1,36 @@
+# Ralph Loop — Progress Log
+
+Feature: [feature name]
+Started: [ISO 8601]
+Source: specification.yaml
+Topology Order: [REQ-001, REQ-002, ...]
+
+---
+
+## REQ-001 — [title]
+
+**Status**: PASS / FAIL / TIMEOUT / BLOCKED
+**Retry count**: 0
+**Test infra**: generated / existing / skipped
+**Files changed**: [file1, file2, ...]
+**Learnings**:
+- `[permanent]` migration files must be in src/migrations/
+- `[contextual]` off-by-one at line 42 in utils.ts
+**Timestamp**: [ISO 8601]
+
+---
+
+## REQ-002 — [title]
+
+**Status**: PASS
+**Retry count**: 1
+**Failure injected**: Linter: unused-var at line 42
+**Test infra**: existing (createTestApp, withTestDb)
+**Files changed**: [file1, file2, ...]
+**Learnings**:
+- `[permanent]` Auth middleware must run before validation
+**Timestamp**: [ISO 8601]
+
+---
+
+<!-- Append new REQs below. Tag: permanent / contextual -->

package/plugins/claude-code/skills/sprint-flow/AGENTS.md

@@ -0,0 +1,68 @@
+# SKILLS/SPRINT-FLOW KNOWLEDGE BASE
+
+**Generated:** 2026-05-30
+**Version:** v0.5.1
+
+## OVERVIEW
+7-phase development pipeline: THINK→PLAN→BUILD→REVIEW→USER ACCEPT→FEEDBACK→SHIP, with ralph-loop default build mode.
+
+## STRUCTURE
+```
+skills/sprint-flow/
+├── SKILL.md              # 7-phase pipeline definition
+├── evals/                # Evaluation test cases
+├── evolution-history.json # Skill evolution tracking
+├── evolution-log.md      # Change history
+├── references/           # Phase reference docs
+│   ├── phase-0-think.md  # THINK phase guidelines
+│   └── ...               # Other phase docs
+└── templates/            # Sprint templates
+```
+
+## WHERE TO LOOK
+| Task | Location | Notes |
+|------|----------|-------|
+| Pipeline def | SKILL.md | 7 phases with hard gates |
+| THINK phase | references/phase-0-think.md | brainstorming → CONTEXT.md + ADR |
+| Build mode | SKILL.md | ralph-loop (default) vs parallel |
+
+## 7 PHASES
+| Phase | Name | Key Action | Hard Gate |
+|-------|------|-----------|-----------|
+| 0 | THINK | brainstorming, CONTEXT.md, ADR | — |
+| 1 | PLAN | autoplan → delphi-review → specification.yaml | HARD-GATE: design must pass |
+| 2 | BUILD | ralph-loop (REQ-level iteration) + TDD + test-align | — |
+| 3 | REVIEW | code-walkthrough + QA + benchmark | — |
+| 4 | USER ACCEPT | Manual verification | — |
+| 5 | FEEDBACK | Retro + debugging + learn | — |
+| 6 | SHIP | finishing-dev-branch + PR/merge | — |
+
+## CONVENTIONS
+- ralph-loop is Phase 2 **default** mode (saves 40-67% tokens vs parallel)
+- delphi-review HARD-GATE in Phase 1: design unapproved → BLOCK coding
+- Each REQ in ralph-loop gets clean context (no linear accumulation)
+- `learn` called at Phase 5 + each REQ completion
+
+## ANTI-PATTERNS (THIS PROJECT)
+- Do NOT skip delphi-review in Phase 1 — HARD-GATE blocks implementation
+- Do NOT use parallel build mode unless explicitly requested
+- Do NOT enter Phase 1 (PLAN) without completing THINK phase
+- DO NOT implement before design approval
+
+## UNIQUE STYLES
+- Auto-detects UI framework (ui-detector.ts in npm-package/lib/)
+- Supports --type and --lang flags for tech stack selection
+- Phase isolation: each phase has specific entry/exit criteria
+- Emergent Requirements acknowledged: user acceptance phase built in
+
+## COMMANDS
+```bash
+/delphi-review "开发用户登录" --type web-nextjs --lang typescript
+/sprint-flow "开发用户登录" --phase build-only
+/sprint-flow "开发用户登录" --mode parallel  # Legacy all-at-once
+```
+
+## NOTES
+- Integrates brainstorming, autoplan, delphi-review, TDD, test-specification-alignment
+- ralph-loop internal learnings via progress.log (permanent/contextual classification)
+- Phase 5 calls gstack/learn for Sprint-level retrospective