@xulthekl/team-flow 0.32.2 → 0.34.0

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 (50) hide show
  1. package/.claude/always/phase-guard.md +1 -1
  2. package/.claude-plugin/marketplace.json +1 -1
  3. package/.claude-plugin/plugin.json +1 -1
  4. package/.codex-plugin/plugin.json +1 -1
  5. package/.cursor-plugin/marketplace.json +1 -1
  6. package/.cursor-plugin/plugin.json +1 -1
  7. package/.github/plugin/marketplace.json +2 -2
  8. package/AGENTS.md +2 -0
  9. package/CHANGELOG.md +56 -0
  10. package/CONTRIBUTING.md +44 -0
  11. package/GEMINI.md +1 -1
  12. package/INSTALL.md +1 -1
  13. package/README.md +1 -1
  14. package/agents/architecture-design.md +1 -34
  15. package/agents/architecture-reviewer.md +1 -42
  16. package/agents/bug-investigator.md +1 -37
  17. package/agents/build-executor.md +1 -22
  18. package/agents/change-split-auditor.md +1 -42
  19. package/agents/code-reviewer.md +1 -42
  20. package/agents/contract-builder.md +1 -22
  21. package/agents/cross-change-consistency-checker.md +2 -43
  22. package/agents/need-explorer.md +1 -22
  23. package/agents/prd-completeness-reviewer.md +1 -47
  24. package/agents/prototype-builder.md +1 -41
  25. package/agents/prototype-env-scout.md +1 -26
  26. package/agents/prototype-reviewer.md +1 -41
  27. package/agents/release-archivist.md +1 -22
  28. package/agents/spec-writer.md +1 -22
  29. package/docs/README_en.md +1 -1
  30. package/docs/solutions/INDEX.md +1 -0
  31. package/docs/solutions/cross-phase/2026-08-04-no-summary.md +17 -0
  32. package/gemini-extension.json +1 -1
  33. package/hooks/session-start +2 -2
  34. package/llms.txt +1 -1
  35. package/package.json +5 -4
  36. package/plugin.json +1 -1
  37. package/scripts/lib/conventions-generator.mjs +350 -0
  38. package/scripts/lib/test-record.mjs +65 -2
  39. package/skills/e2e/SKILL.md +1 -1
  40. package/skills/test-strategy/SKILL.md +38 -1
  41. package/skills/test-strategy/references/integration-test-contracts.md +237 -0
  42. package/skills/test-strategy/references/integration-test-isolation.md +346 -0
  43. package/skills/test-strategy/references/test-quality-rules.md +292 -0
  44. package/skills/workflow-bootstrap/SKILL.md +40 -3
  45. package/templates/agent-template.md +41 -0
  46. package/templates/conventions/_manifest.json +39 -0
  47. package/templates/conventions/glaf4-compliant/java-testing.md +367 -0
  48. package/templates/conventions/glaf4-compliant/spring-patterns.md +415 -0
  49. package/templates/conventions/js-testing.md +261 -0
  50. package/templates/conventions/python-testing.md +333 -0
@@ -1,52 +1,6 @@
1
1
  ---
2
2
  name: prd-completeness-reviewer
3
- description: >-
4
- PRD 完整性自动评审。在 PRD 写入后、冻结前,独立检查"需求描述是否完整到能支撑
5
- 后续 plan/spec 实施"(5 维度),输出分级完整性报告。只读审查,不修改任何文件。
6
- 与 claim verifier 分工:claim verifier 管"说得对不对"(核查事实声明),
7
- 本 agent 管"说得全不全、能否落地"。
8
- Examples:
9
-
10
- <example>
11
- Context: PRD 刚写完,orchestrator 需要在冻结前做完整性门禁检查。
12
- user: "PRD 写好了,帮我看看完整不完整,能不能往下做 plan"
13
- assistant: "我来启动 prd-completeness-reviewer agent,独立审查 PRD 的 5 维度完整性。"
14
- <commentary>
15
- PRD 完整性评审是 orchestrator S2 阶段冻结前的关键门禁。本 agent 在独立上下文中运行,
16
- 未参与 PRD 产出,规避锚定效应。审查报告写在 response 中,由编排层落盘到
17
- prd/vN/prd-completeness-review.md。FAIL(仅 Critical 触发)→ 回 ce-brainstorm Phase 1.3 补充。
18
- </commentary>
19
- </example>
20
-
21
- <example>
22
- Context: 用户担心 PRD 缺验收标准,导致后面 plan/spec 无法落地。
23
- user: "这份 PRD 的每个功能都有可验证的验收标准吗?"
24
- assistant: "让 prd-completeness-reviewer agent 做一次 D2 验收标准维度的结构化检查。"
25
- <commentary>
26
- D2 验收标准是 Critical 级维度——缺失即触发 FAIL。没有可验证的 AC,下游 plan/spec/build
27
- 将失去判定基准。本 agent 逐功能核查 AC/成功信号是否存在且可验证。
28
- </commentary>
29
- </example>
30
-
31
- <example>
32
- Context: PRD 补充修订后需要重新评审(FAIL 后第 2 轮)。
33
- user: "PRD 按上一轮意见补充了边界场景,重新跑一下完整性检查"
34
- assistant: "我启动 prd-completeness-reviewer agent 进行第 2 轮完整性评审,对比上轮 Critical 项是否已补齐。"
35
- <commentary>
36
- FAIL→回 Phase 1.3 补充→重新评审,直到无 Critical。Important 不阻断,
37
- 以 PASS_WITH_WARNINGS 交人工裁定。
38
- </commentary>
39
- </example>
40
-
41
- <example>
42
- Context: 人工冻结前想先确认 PRD 范围闭环、没有悬空功能。
43
- user: "帮我看看 PRD 的 in/out scope 是不是清楚,有没有写了但没人接的功能"
44
- assistant: "我启动 prd-completeness-reviewer agent 做 D5 范围闭环维度的检查。"
45
- <commentary>
46
- D5 范围闭环是 Important 级——悬空功能(in scope 写了但无对应实现路径)或 out scope
47
- 未声明,会在 plan 阶段才暴露。提前在 PRD 层闭环可降低下游返工。
48
- </commentary>
49
- </example>
3
+ description: PRD 完整性自动评审。在 PRD 写入后、冻结前,独立检查"需求描述是否完整到能支撑后续 plan/spec 实施"(5 维度),输出分级完整性报告。只读审查,不修改任何文件。与 claim verifier 分工——claim verifier 管"说得对不对"(核查事实声明),本 agent 管"说得全不全、能否落地"。
50
4
 
51
5
  model: inherit
52
6
  color: yellow
@@ -1,46 +1,6 @@
1
1
  ---
2
2
  name: prototype-builder
3
- description: >-
4
- 原型构建 agent——将设计稿(HTML/CSS/JS)转化为可运行的原型系统。在 prototype skill
5
- 编排中作为子代理调用,负责原型代码生成、设计系统集成、质量保证。只写不读 specs。
6
- Examples:
7
-
8
- <example>
9
- Context: prototype skill 完成设计稿生成后,需要构建可运行的原型。
10
- user: "设计稿生成完了,帮我构建原型"
11
- assistant: "我来启动 prototype-builder agent,将设计稿转化为可运行的原型系统。"
12
- <commentary>
13
- 原型构建是 prototype skill 的核心执行步骤。本 agent 读取设计稿(HTML/CSS/JS),
14
- 集成设计系统,生成可运行的原型,执行质量保证检查。
15
- </commentary>
16
- </example>
17
-
18
- <example>
19
- Context: 需要修复原型中的问题。
20
- user: "原型跑起来了,但样式有点问题,帮我修一下"
21
- assistant: "让 prototype-builder agent 修复原型的样式问题。"
22
- <commentary>
23
- 原型修复需要读取现有原型代码,定位问题,应用修复,重新验证。
24
- </commentary>
25
- </example>
26
-
27
- <example>
28
- Context: 需要为原型添加新功能。
29
- user: "原型需要加一个搜索功能,帮我实现"
30
- assistant: "我启动 prototype-builder agent,为原型添加搜索功能。"
31
- <commentary>
32
- 原型扩展需要读取现有原型,理解结构,添加新功能,确保与设计系统一致。
33
- </commentary>
34
- </example>
35
-
36
- <example>
37
- Context: 需要将原型集成到真实系统。
38
- user: "原型验证通过了,帮我集成到真实系统"
39
- assistant: "我启动 prototype-builder agent,将原型代码集成到真实项目。"
40
- <commentary>
41
- 原型集成需要提取原型中的有效代码,适配真实系统的技术栈,确保功能一致。
42
- </commentary>
43
- </example>
3
+ description: 原型构建 agent——将设计稿(HTML/CSS/JS)转化为可运行的原型系统。在 prototype skill 编排中作为子代理调用,负责原型代码生成、设计系统集成、质量保证。只写不读 specs。
44
4
 
45
5
  model: inherit
46
6
  color: green
@@ -1,31 +1,6 @@
1
1
  ---
2
2
  name: prototype-env-scout
3
- description: >-
4
- 原型环境探查(prototype skill 内部编排步骤①)。只读探查设计系统现状(9 段 schema
5
- 完整度)、原型仓库分支、PRD 版本、已有页面,产出环境简报 + 推荐原型方案设计 +
6
- readiness verdict。只读,不写 prototype/,不改 design-system.md。
7
- Examples:
8
-
9
- <example>
10
- Context: prototype skill 进入步骤①,需要先摸清环境再设计原型方案。
11
- user: "要做驾驶舱原型,先帮我看看设计系统、分支、PRD 这些环境情况"
12
- assistant: "我启动 prototype-env-scout agent,只读探查设计系统/分支/PRD/已有页面,产出环境简报和原型方案建议。"
13
- <commentary>
14
- 环境探查是 prototype 内部编排的第一步,为后续方案评审和 prototype-builder 绘制提供
15
- 决策依据。本 agent 只读,发现设计系统缺失时把 verdict 标为 needs_design_system 交主代理
16
- 决定是否先派 design-system-architect,而非自己阻断或写文件。
17
- </commentary>
18
- </example>
19
-
20
- <example>
21
- Context: 迭代已有原型,需要确认当前分支与 PRD 版本是否对齐。
22
- user: "PRD 升到 v2 了,原型分支对不对得上?已有哪些页面?"
23
- assistant: "让 prototype-env-scout agent 探查到原型分支与 PRD 版本的对齐情况和现有原型清单。"
24
- <commentary>
25
- 原型随 PRD 当前版本分支维护(prd-vN 分支)。本 agent 检测当前分支是否匹配目标 PRD 版本,
26
- 并清点现有 pages/components/flow.md,供迭代方案参考。
27
- </commentary>
28
- </example>
3
+ description: 原型环境探查(prototype skill 内部编排步骤①)。只读探查设计系统现状(9 段 schema 完整度)、原型仓库分支、PRD 版本、已有页面,产出环境简报 + 推荐原型方案设计 + readiness verdict。只读,不写 prototype/,不改 design-system.md。
29
4
 
30
5
  model: inherit
31
6
  color: cyan
@@ -1,46 +1,6 @@
1
1
  ---
2
2
  name: prototype-reviewer
3
- description: >-
4
- 原型 vs PRD 一致性自动评审。在原型产出后、人工评审前,独立检查原型与 PRD
5
- 的结构化一致性(6 维度),输出分级一致性报告。只读审查,不修改任何文件。
6
- Examples:
7
-
8
- <example>
9
- Context: 原型刚产出,orchestrator 需要在人工评审前做自动一致性检查。
10
- user: "原型做好了,帮我检查一下和 PRD 是否一致"
11
- assistant: "我来启动 prototype-reviewer agent,独立审查原型与 PRD 的 6 维度一致性。"
12
- <commentary>
13
- 原型自动评审是 orchestrator S2 阶段的关键门禁。prototype-reviewer 在独立上下文中运行,
14
- 未参与 PRD/原型产出,规避锚定效应。审查报告写在 response 中,由编排层落盘。
15
- </commentary>
16
- </example>
17
-
18
- <example>
19
- Context: 原型经过修正后需要重新评审(第 2 轮)。
20
- user: "原型修正完了,重新跑一下一致性检查"
21
- assistant: "我启动 prototype-reviewer agent 进行第 2 轮自动评审,对比修正前后不一致项是否收敛。"
22
- <commentary>
23
- FAIL 后修正→重新评审,最多 3 轮。连续两轮不一致项集合无缩小则转人工,避免死循环。
24
- </commentary>
25
- </example>
26
-
27
- <example>
28
- Context: 用户想确认原型是否覆盖了 PRD 中定义的所有页面和功能。
29
- user: "PRD 里定义了 8 个页面,原型是不是都有了?"
30
- assistant: "让 prototype-reviewer agent 做一次 D1 页面完整性 + D2 功能覆盖的结构化检查。"
31
- <commentary>
32
- D1/D4 走 Pre-check(Bash 结构化预检),机械化验证页面文件存在性和导航链接完整性。
33
- </commentary>
34
- </example>
35
-
36
- <example>
37
- Context: 人工评审前想先过一遍术语和字段是否对齐。
38
- user: "帮我看看原型里的字段名称和 PRD 定义的是否一致"
39
- assistant: "我启动 prototype-reviewer agent 做 D3 字段一致性 + D5 术语一致性的语义对比。"
40
- <commentary>
41
- D3/D5 走 Deep-check(LLM 语义对比),标注为建议级,误报可被人工推翻。
42
- </commentary>
43
- </example>
3
+ description: 原型 vs PRD 一致性自动评审。在原型产出后、人工评审前,独立检查原型与 PRD 的结构化一致性(6 维度),输出分级一致性报告。只读审查,不修改任何文件。
44
4
 
45
5
  model: inherit
46
6
  color: green
@@ -1,27 +1,6 @@
1
1
  ---
2
2
  name: release-archivist
3
- description: >-
4
- 发布归档 agent——在 build-executor 完成实施之后、change 关闭之前,执行验证、产出
5
- closing 总结并完成归档就绪(arch-merge / prototype-sync / 复利晋升)。可写型,负责归档制品。
6
- Examples:
7
-
8
- <example>
9
- Context: 实施完成,需要验证并收尾归档。
10
- user: "实施做完了,帮我验证并归档这个 change"
11
- assistant: "I'll launch the release-archivist agent to verify, summarize, and ready the archive."
12
- <commentary>
13
- release-archivist 是 closing 阶段的收尾 agent,守"验证先于完成"铁律,产出验证报告与归档。
14
- </commentary>
15
- </example>
16
-
17
- <example>
18
- Context: 验证发现实施偏离契约,需回退而非强行关闭。
19
- user: "验证发现 design 决策和代码对不上"
20
- assistant: "I'll have release-archivist route back to bridging instead of forcing closure."
21
- <commentary>
22
- 若实施偏离契约,回退 bridging 再关闭;FAIL 不进 DP-7。
23
- </commentary>
24
- </example>
3
+ description: 发布归档 agent——在 build-executor 完成实施之后、change 关闭之前,执行验证、产出 closing 总结并完成归档就绪(arch-merge / prototype-sync / 复利晋升)。可写型,负责归档制品。
25
4
 
26
5
  model: inherit
27
6
  color: yellow
@@ -1,27 +1,6 @@
1
1
  ---
2
2
  name: spec-writer
3
- description: >-
4
- 规格编写 agent——在 need-explorer 完成 DP-1 之后、contract-builder 之前,产出并打磨
5
- proposal.md / specs/ / design.md / tasks.md 四件规划制品。可写型,负责规划制品目录。
6
- Examples:
7
-
8
- <example>
9
- Context: need-explorer 已记录 DP-1,change 意图稳定,可以落盘规划制品。
10
- user: "需求已经澄清清楚了,帮我把 proposal/specs/design/tasks 写出来"
11
- assistant: "I'll launch the spec-writer agent to produce the four planning artifacts in order."
12
- <commentary>
13
- spec-writer 是 exploring→bridging 之间的产出 agent。逐件生成、逐件确认,防止 scope 漂移。
14
- </commentary>
15
- </example>
16
-
17
- <example>
18
- Context: 本 change 经 architecture-design 判定为 required,architecture/ 三件套已产出。
19
- user: "架构设计做完了,写 design.md 时要对齐架构决策"
20
- assistant: "I'll have spec-writer read architecture/ and align design.md Decisions with it."
21
- <commentary>
22
- design.md 的 Decisions 必须引用 architecture/ 决策,tasks.md 须对齐 api.md 路由表与 sql/ 脚本。
23
- </commentary>
24
- </example>
3
+ description: 规格编写 agent——在 need-explorer 完成 DP-1 之后、contract-builder 之前,产出并打磨 proposal.md / specs/ / design.md / tasks.md 四件规划制品。可写型,负责规划制品目录。
25
4
 
26
5
  model: inherit
27
6
  color: cyan
package/docs/README_en.md CHANGED
@@ -126,7 +126,7 @@ npm install -g team-flow
126
126
 
127
127
  ### Version
128
128
 
129
- - Current: `v0.32.2`
129
+ - Current: `v0.34.0`
130
130
  - v0.9.1 highlights: DP-4 execution-mode recommendations, a portable runtime across 17 platforms, and a raw-package smoke with no plugin-root variable.
131
131
  - Self-contained — no OpenSpec or Superpowers runtime required
132
132
  - Upstream: [Fission-AI/OpenSpec](https://github.com/Fission-AI/OpenSpec), [obra/superpowers](https://github.com/obra/superpowers)
@@ -2,6 +2,7 @@
2
2
  <!-- 每条一行,按 severity 降序,≤150 行硬上限 -->
3
3
  | date | phase | domain | type | severity | summary | file |
4
4
  |------|-------|--------|------|----------|---------|------|
5
+ | 2026-08-04 | cross-phase | general | insight | medium | (no summary) | cross-phase/2026-08-04-no-summary.md |
5
6
  | 2026-08-03 | cross-phase | general | insight | medium | (no summary) | cross-phase/2026-08-03-no-summary.md |
6
7
  | 2026-08-01 | cross-phase | general | insight | medium | (no summary) | cross-phase/2026-08-01-no-summary.md |
7
8
  | 2026-07-31 | cross-phase | general | insight | medium | (no summary) | cross-phase/2026-07-31-no-summary.md |
@@ -0,0 +1,17 @@
1
+ ---
2
+ phase: cross-phase
3
+ domain: general
4
+ type: insight
5
+ severity: medium
6
+ date: 2026-08-04
7
+ source:
8
+ ---
9
+
10
+ ## 问题描述
11
+ (no summary)
12
+
13
+ ## 根因/模式
14
+ (待补充)
15
+
16
+ ## 预防措施/应用方式
17
+ (待补充)
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "team-flow",
3
3
  "description": "Unified workflow plugin: team-flow (spec-driven dev) + compound-engineering core subset + architecture-design (4A/DDD) + prototype (local HTML). 24 skills, one install.",
4
- "version": "0.32.2",
4
+ "version": "0.34.0",
5
5
  "contextFileName": "GEMINI.md"
6
6
  }
@@ -1,11 +1,11 @@
1
1
  #!/usr/bin/env bash
2
- # v0.32.2: auto-sync CLI version with plugin version
2
+ # v0.34.0: auto-sync CLI version with plugin version
3
3
  set -e
4
4
 
5
5
  # ═══════════════════════════════════════════════════════════════
6
6
  # Plugin version (update this when releasing new versions)
7
7
  # ═══════════════════════════════════════════════════════════════
8
- PLUGIN_VERSION="0.32.2"
8
+ PLUGIN_VERSION="0.34.0"
9
9
 
10
10
  # ═══════════════════════════════════════════════════════════════
11
11
  # Step 1: Auto-sync CLI version with plugin version
package/llms.txt CHANGED
@@ -3,7 +3,7 @@
3
3
  ## Overview
4
4
  spec-superflow is a self-contained workflow integration plugin for Claude Code, Cursor, OpenAI Codex CLI/App, GitHub Copilot CLI, Gemini CLI, OpenCode, WorkBuddy, and Trae. It merges spec-driven planning artifacts (proposal, specs, design, tasks) with disciplined execution guardrails (TDD, review gates, controlled handoff) into one unified workflow.
5
5
 
6
- Current version: v0.32.2.
6
+ Current version: v0.34.0.
7
7
 
8
8
  ## Key Documents
9
9
  - README.md: Chinese homepage with full usage guide and FAQ
package/package.json CHANGED
@@ -1,12 +1,12 @@
1
1
  {
2
2
  "name": "@xulthekl/team-flow",
3
- "version": "0.32.2",
3
+ "version": "0.34.0",
4
4
  "description": "Unified plugin (24 skills + 15 agents) integrating team-flow, compound-engineering, architecture-design, prototype, design-system, workflow-orchestrator, workflow-bootstrap, e2e, session-handoff, workflow-feedback for multi-agent coding tools.",
5
5
  "main": "dist/index.js",
6
6
  "types": "dist/index.d.ts",
7
7
  "bin": {
8
- "tf": "./scripts/team-flow.mjs",
9
- "team-flow": "./scripts/team-flow.mjs"
8
+ "tf": "scripts/team-flow.mjs",
9
+ "team-flow": "scripts/team-flow.mjs"
10
10
  },
11
11
  "type": "module",
12
12
  "scripts": {
@@ -41,12 +41,13 @@
41
41
  "license": "MIT",
42
42
  "repository": {
43
43
  "type": "git",
44
- "url": "https://github.com/MageByte-Zero/team-flow"
44
+ "url": "git+https://github.com/MageByte-Zero/team-flow.git"
45
45
  },
46
46
  "engines": {
47
47
  "node": ">=20"
48
48
  },
49
49
  "devDependencies": {
50
+ "js-yaml": "^5.2.3",
50
51
  "typescript": "^6.0.3"
51
52
  }
52
53
  }
package/plugin.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "team-flow",
3
- "version": "0.32.2",
3
+ "version": "0.34.0",
4
4
  "description": "Unified workflow plugin: team-flow (spec-driven dev: TDD/SDD/code-review/debugging) + compound-engineering core subset (brainstorm/plan/compound/strategy/ideate/proof, global compounding) + architecture-design (4A+DDD incremental design & global compounding) + prototype (local HTML prototype, zero external deps) + e2e (Playwright E2E, AC-driven) + workflow-orchestrator (product-level workflow orchestration) + workflow-bootstrap (existing project onboarding) + session-handoff (context transfer) + workflow-feedback (issue tracking). 24 skills + 15 agents, one install.",
5
5
  "author": {
6
6
  "name": "LT"