@fitlab-ai/agent-infra 0.4.0 → 0.4.1

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 (270) hide show
  1. package/README.md +1 -3
  2. package/README.zh-CN.md +1 -3
  3. package/lib/defaults.json +2 -0
  4. package/lib/init.js +1 -6
  5. package/lib/update.js +0 -55
  6. package/package.json +1 -1
  7. package/templates/.agents/QUICKSTART.md +10 -0
  8. package/templates/.agents/QUICKSTART.zh-CN.md +10 -0
  9. package/templates/.agents/README.md +18 -11
  10. package/templates/.agents/README.zh-CN.md +18 -11
  11. package/templates/.agents/skills/analyze-task/SKILL.md +1 -4
  12. package/templates/.agents/skills/analyze-task/SKILL.zh-CN.md +1 -3
  13. package/templates/.agents/skills/block-task/SKILL.md +1 -5
  14. package/templates/.agents/skills/block-task/SKILL.zh-CN.md +1 -4
  15. package/templates/.agents/skills/check-task/SKILL.md +1 -5
  16. package/templates/.agents/skills/check-task/SKILL.zh-CN.md +1 -3
  17. package/templates/.agents/skills/close-codescan/SKILL.md +1 -4
  18. package/templates/.agents/skills/close-codescan/SKILL.zh-CN.md +1 -3
  19. package/templates/.agents/skills/close-dependabot/SKILL.md +1 -4
  20. package/templates/.agents/skills/close-dependabot/SKILL.zh-CN.md +1 -3
  21. package/templates/.agents/skills/commit/SKILL.md +26 -198
  22. package/templates/.agents/skills/commit/SKILL.zh-CN.md +26 -197
  23. package/templates/.agents/skills/commit/reference/commit-message.md +60 -0
  24. package/templates/.agents/skills/commit/reference/commit-message.zh-CN.md +60 -0
  25. package/templates/.agents/skills/commit/reference/copyright-check.md +39 -0
  26. package/templates/.agents/skills/commit/reference/copyright-check.zh-CN.md +39 -0
  27. package/templates/.agents/skills/commit/reference/task-status-update.md +88 -0
  28. package/templates/.agents/skills/commit/reference/task-status-update.zh-CN.md +88 -0
  29. package/templates/.agents/skills/complete-task/SKILL.md +1 -6
  30. package/templates/.agents/skills/complete-task/SKILL.zh-CN.md +1 -4
  31. package/templates/.agents/skills/create-issue/SKILL.md +32 -251
  32. package/templates/.agents/skills/create-issue/SKILL.zh-CN.md +33 -252
  33. package/templates/.agents/skills/create-issue/reference/label-and-type.md +77 -0
  34. package/templates/.agents/skills/create-issue/reference/label-and-type.zh-CN.md +77 -0
  35. package/templates/.agents/skills/create-issue/reference/template-matching.md +45 -0
  36. package/templates/.agents/skills/create-issue/reference/template-matching.zh-CN.md +45 -0
  37. package/templates/.agents/skills/create-pr/SKILL.md +33 -224
  38. package/templates/.agents/skills/create-pr/SKILL.zh-CN.md +32 -222
  39. package/templates/.agents/skills/create-pr/reference/branch-strategy.md +29 -0
  40. package/templates/.agents/skills/create-pr/reference/branch-strategy.zh-CN.md +29 -0
  41. package/templates/.agents/skills/create-pr/reference/pr-body-template.md +86 -0
  42. package/templates/.agents/skills/create-pr/reference/pr-body-template.zh-CN.md +86 -0
  43. package/templates/.agents/skills/create-release-note/SKILL.md +10 -13
  44. package/templates/.agents/skills/create-release-note/SKILL.zh-CN.md +10 -12
  45. package/templates/.agents/skills/create-task/SKILL.md +1 -4
  46. package/templates/.agents/skills/create-task/SKILL.zh-CN.md +1 -3
  47. package/templates/.agents/skills/implement-task/SKILL.md +46 -176
  48. package/templates/.agents/skills/implement-task/SKILL.zh-CN.md +42 -170
  49. package/templates/.agents/skills/implement-task/reference/implementation-rules.md +58 -0
  50. package/templates/.agents/skills/implement-task/reference/implementation-rules.zh-CN.md +58 -0
  51. package/templates/.agents/skills/implement-task/reference/report-template.md +63 -0
  52. package/templates/.agents/skills/implement-task/reference/report-template.zh-CN.md +63 -0
  53. package/templates/.agents/skills/import-codescan/SKILL.md +1 -4
  54. package/templates/.agents/skills/import-codescan/SKILL.zh-CN.md +1 -3
  55. package/templates/.agents/skills/import-dependabot/SKILL.md +1 -4
  56. package/templates/.agents/skills/import-dependabot/SKILL.zh-CN.md +1 -3
  57. package/templates/.agents/skills/import-issue/SKILL.md +1 -3
  58. package/templates/.agents/skills/import-issue/SKILL.zh-CN.md +1 -3
  59. package/templates/.agents/skills/init-labels/SKILL.md +1 -4
  60. package/templates/.agents/skills/init-labels/SKILL.zh-CN.md +1 -4
  61. package/templates/.agents/skills/init-milestones/SKILL.md +1 -3
  62. package/templates/.agents/skills/init-milestones/SKILL.zh-CN.md +1 -3
  63. package/templates/.agents/skills/plan-task/SKILL.md +1 -5
  64. package/templates/.agents/skills/plan-task/SKILL.zh-CN.md +1 -3
  65. package/templates/.agents/skills/refine-task/SKILL.md +38 -162
  66. package/templates/.agents/skills/refine-task/SKILL.zh-CN.md +36 -158
  67. package/templates/.agents/skills/refine-task/reference/fix-workflow.md +76 -0
  68. package/templates/.agents/skills/refine-task/reference/fix-workflow.zh-CN.md +76 -0
  69. package/templates/.agents/skills/refine-task/reference/report-template.md +38 -0
  70. package/templates/.agents/skills/refine-task/reference/report-template.zh-CN.md +38 -0
  71. package/templates/.agents/skills/refine-title/SKILL.md +1 -4
  72. package/templates/.agents/skills/refine-title/SKILL.zh-CN.md +1 -3
  73. package/templates/.agents/skills/release/SKILL.md +10 -12
  74. package/templates/.agents/skills/release/SKILL.zh-CN.md +10 -11
  75. package/templates/.agents/skills/review-task/SKILL.md +37 -239
  76. package/templates/.agents/skills/review-task/SKILL.zh-CN.md +37 -238
  77. package/templates/.agents/skills/review-task/reference/output-templates.md +72 -0
  78. package/templates/.agents/skills/review-task/reference/output-templates.zh-CN.md +72 -0
  79. package/templates/.agents/skills/review-task/reference/report-template.md +63 -0
  80. package/templates/.agents/skills/review-task/reference/report-template.zh-CN.md +63 -0
  81. package/templates/.agents/skills/review-task/reference/review-criteria.md +24 -0
  82. package/templates/.agents/skills/review-task/reference/review-criteria.zh-CN.md +24 -0
  83. package/templates/.agents/skills/sync-issue/SKILL.md +29 -487
  84. package/templates/.agents/skills/sync-issue/SKILL.zh-CN.md +30 -487
  85. package/templates/.agents/skills/sync-issue/reference/comment-publish.md +88 -0
  86. package/templates/.agents/skills/sync-issue/reference/comment-publish.zh-CN.md +88 -0
  87. package/templates/.agents/skills/sync-issue/reference/delivery-detection.md +42 -0
  88. package/templates/.agents/skills/sync-issue/reference/delivery-detection.zh-CN.md +42 -0
  89. package/templates/.agents/skills/sync-issue/reference/label-sync.md +63 -0
  90. package/templates/.agents/skills/sync-issue/reference/label-sync.zh-CN.md +63 -0
  91. package/templates/.agents/skills/sync-issue/reference/milestone-sync.md +37 -0
  92. package/templates/.agents/skills/sync-issue/reference/milestone-sync.zh-CN.md +37 -0
  93. package/templates/.agents/skills/sync-pr/SKILL.md +25 -287
  94. package/templates/.agents/skills/sync-pr/SKILL.zh-CN.md +29 -291
  95. package/templates/.agents/skills/sync-pr/reference/comment-publish.md +82 -0
  96. package/templates/.agents/skills/sync-pr/reference/comment-publish.zh-CN.md +82 -0
  97. package/templates/.agents/skills/sync-pr/reference/delivery-detection.md +54 -0
  98. package/templates/.agents/skills/sync-pr/reference/delivery-detection.zh-CN.md +54 -0
  99. package/templates/.agents/skills/test/SKILL.md +1 -3
  100. package/templates/.agents/skills/test/SKILL.zh-CN.md +1 -3
  101. package/templates/.agents/skills/test-integration/SKILL.md +1 -4
  102. package/templates/.agents/skills/test-integration/SKILL.zh-CN.md +1 -3
  103. package/templates/.agents/skills/update-agent-infra/SKILL.md +2 -6
  104. package/templates/.agents/skills/update-agent-infra/SKILL.zh-CN.md +2 -4
  105. package/templates/.agents/skills/update-agent-infra/scripts/sync-templates.js +42 -46
  106. package/templates/.agents/skills/upgrade-dependency/SKILL.md +1 -4
  107. package/templates/.agents/skills/upgrade-dependency/SKILL.zh-CN.md +1 -3
  108. package/templates/.claude/CLAUDE.md +13 -51
  109. package/templates/.claude/CLAUDE.zh-CN.md +13 -51
  110. package/templates/.claude/commands/analyze-task.md +1 -1
  111. package/templates/.claude/commands/analyze-task.zh-CN.md +1 -1
  112. package/templates/.claude/commands/block-task.md +2 -1
  113. package/templates/.claude/commands/block-task.zh-CN.md +2 -1
  114. package/templates/.claude/commands/check-task.md +2 -1
  115. package/templates/.claude/commands/check-task.zh-CN.md +2 -1
  116. package/templates/.claude/commands/close-codescan.md +2 -1
  117. package/templates/.claude/commands/close-codescan.zh-CN.md +2 -1
  118. package/templates/.claude/commands/close-dependabot.md +2 -1
  119. package/templates/.claude/commands/close-dependabot.zh-CN.md +2 -1
  120. package/templates/.claude/commands/commit.md +1 -1
  121. package/templates/.claude/commands/commit.zh-CN.md +1 -1
  122. package/templates/.claude/commands/complete-task.md +1 -1
  123. package/templates/.claude/commands/complete-task.zh-CN.md +1 -1
  124. package/templates/.claude/commands/create-issue.md +1 -1
  125. package/templates/.claude/commands/create-issue.zh-CN.md +1 -1
  126. package/templates/.claude/commands/create-pr.md +1 -1
  127. package/templates/.claude/commands/create-pr.zh-CN.md +1 -1
  128. package/templates/.claude/commands/create-release-note.md +2 -1
  129. package/templates/.claude/commands/create-release-note.zh-CN.md +2 -1
  130. package/templates/.claude/commands/create-task.md +1 -1
  131. package/templates/.claude/commands/create-task.zh-CN.md +1 -1
  132. package/templates/.claude/commands/implement-task.md +1 -1
  133. package/templates/.claude/commands/implement-task.zh-CN.md +1 -1
  134. package/templates/.claude/commands/import-codescan.md +1 -0
  135. package/templates/.claude/commands/import-codescan.zh-CN.md +2 -1
  136. package/templates/.claude/commands/import-dependabot.md +1 -0
  137. package/templates/.claude/commands/import-dependabot.zh-CN.md +2 -1
  138. package/templates/.claude/commands/import-issue.md +1 -1
  139. package/templates/.claude/commands/import-issue.zh-CN.md +1 -1
  140. package/templates/.claude/commands/init-labels.md +1 -0
  141. package/templates/.claude/commands/init-labels.zh-CN.md +2 -1
  142. package/templates/.claude/commands/init-milestones.md +2 -1
  143. package/templates/.claude/commands/init-milestones.zh-CN.md +2 -1
  144. package/templates/.claude/commands/plan-task.md +1 -1
  145. package/templates/.claude/commands/plan-task.zh-CN.md +1 -1
  146. package/templates/.claude/commands/refine-task.zh-CN.md +1 -1
  147. package/templates/.claude/commands/refine-title.md +2 -1
  148. package/templates/.claude/commands/refine-title.zh-CN.md +2 -1
  149. package/templates/.claude/commands/release.md +2 -1
  150. package/templates/.claude/commands/release.zh-CN.md +2 -1
  151. package/templates/.claude/commands/review-task.md +1 -1
  152. package/templates/.claude/commands/review-task.zh-CN.md +1 -1
  153. package/templates/.claude/commands/sync-issue.md +1 -1
  154. package/templates/.claude/commands/sync-issue.zh-CN.md +1 -1
  155. package/templates/.claude/commands/sync-pr.md +1 -1
  156. package/templates/.claude/commands/sync-pr.zh-CN.md +1 -1
  157. package/templates/.claude/commands/test-integration.md +2 -1
  158. package/templates/.claude/commands/test-integration.zh-CN.md +2 -1
  159. package/templates/.claude/commands/test.md +1 -1
  160. package/templates/.claude/commands/test.zh-CN.md +1 -1
  161. package/templates/.claude/commands/update-agent-infra.md +2 -1
  162. package/templates/.claude/commands/update-agent-infra.zh-CN.md +2 -1
  163. package/templates/.claude/commands/upgrade-dependency.md +2 -1
  164. package/templates/.claude/commands/upgrade-dependency.zh-CN.md +2 -1
  165. package/templates/.gemini/commands/_project_/analyze-task.toml +1 -1
  166. package/templates/.gemini/commands/_project_/analyze-task.zh-CN.toml +1 -1
  167. package/templates/.gemini/commands/_project_/block-task.toml +1 -1
  168. package/templates/.gemini/commands/_project_/block-task.zh-CN.toml +1 -1
  169. package/templates/.gemini/commands/_project_/check-task.toml +1 -1
  170. package/templates/.gemini/commands/_project_/check-task.zh-CN.toml +1 -1
  171. package/templates/.gemini/commands/_project_/close-codescan.toml +1 -1
  172. package/templates/.gemini/commands/_project_/close-codescan.zh-CN.toml +1 -1
  173. package/templates/.gemini/commands/_project_/close-dependabot.toml +1 -1
  174. package/templates/.gemini/commands/_project_/close-dependabot.zh-CN.toml +1 -1
  175. package/templates/.gemini/commands/_project_/commit.toml +1 -1
  176. package/templates/.gemini/commands/_project_/commit.zh-CN.toml +1 -1
  177. package/templates/.gemini/commands/_project_/complete-task.toml +1 -1
  178. package/templates/.gemini/commands/_project_/complete-task.zh-CN.toml +1 -1
  179. package/templates/.gemini/commands/_project_/create-issue.zh-CN.toml +1 -1
  180. package/templates/.gemini/commands/_project_/create-pr.toml +1 -1
  181. package/templates/.gemini/commands/_project_/create-pr.zh-CN.toml +1 -1
  182. package/templates/.gemini/commands/_project_/create-release-note.toml +1 -1
  183. package/templates/.gemini/commands/_project_/create-release-note.zh-CN.toml +1 -1
  184. package/templates/.gemini/commands/_project_/create-task.toml +1 -1
  185. package/templates/.gemini/commands/_project_/create-task.zh-CN.toml +1 -1
  186. package/templates/.gemini/commands/_project_/implement-task.toml +1 -1
  187. package/templates/.gemini/commands/_project_/implement-task.zh-CN.toml +1 -1
  188. package/templates/.gemini/commands/_project_/import-codescan.zh-CN.toml +1 -1
  189. package/templates/.gemini/commands/_project_/import-dependabot.zh-CN.toml +1 -1
  190. package/templates/.gemini/commands/_project_/import-issue.toml +1 -1
  191. package/templates/.gemini/commands/_project_/import-issue.zh-CN.toml +1 -1
  192. package/templates/.gemini/commands/_project_/init-labels.zh-CN.toml +1 -1
  193. package/templates/.gemini/commands/_project_/init-milestones.toml +1 -1
  194. package/templates/.gemini/commands/_project_/init-milestones.zh-CN.toml +1 -1
  195. package/templates/.gemini/commands/_project_/plan-task.toml +1 -1
  196. package/templates/.gemini/commands/_project_/plan-task.zh-CN.toml +1 -1
  197. package/templates/.gemini/commands/_project_/refine-task.zh-CN.toml +1 -1
  198. package/templates/.gemini/commands/_project_/refine-title.toml +1 -1
  199. package/templates/.gemini/commands/_project_/refine-title.zh-CN.toml +1 -1
  200. package/templates/.gemini/commands/_project_/release.toml +1 -1
  201. package/templates/.gemini/commands/_project_/release.zh-CN.toml +1 -1
  202. package/templates/.gemini/commands/_project_/review-task.toml +1 -1
  203. package/templates/.gemini/commands/_project_/review-task.zh-CN.toml +1 -1
  204. package/templates/.gemini/commands/_project_/sync-issue.toml +1 -1
  205. package/templates/.gemini/commands/_project_/sync-issue.zh-CN.toml +1 -1
  206. package/templates/.gemini/commands/_project_/sync-pr.toml +1 -1
  207. package/templates/.gemini/commands/_project_/sync-pr.zh-CN.toml +1 -1
  208. package/templates/.gemini/commands/_project_/test-integration.toml +1 -1
  209. package/templates/.gemini/commands/_project_/test-integration.zh-CN.toml +1 -1
  210. package/templates/.gemini/commands/_project_/test.toml +1 -1
  211. package/templates/.gemini/commands/_project_/test.zh-CN.toml +1 -1
  212. package/templates/.gemini/commands/_project_/update-agent-infra.toml +1 -1
  213. package/templates/.gemini/commands/_project_/update-agent-infra.zh-CN.toml +1 -1
  214. package/templates/.gemini/commands/_project_/upgrade-dependency.toml +1 -1
  215. package/templates/.gemini/commands/_project_/upgrade-dependency.zh-CN.toml +1 -1
  216. package/templates/.github/hooks/check-version-format.sh +29 -0
  217. package/templates/.github/hooks/pre-commit +8 -0
  218. package/templates/.opencode/commands/analyze-task.md +1 -1
  219. package/templates/.opencode/commands/analyze-task.zh-CN.md +1 -1
  220. package/templates/.opencode/commands/block-task.md +1 -1
  221. package/templates/.opencode/commands/block-task.zh-CN.md +1 -1
  222. package/templates/.opencode/commands/check-task.md +1 -1
  223. package/templates/.opencode/commands/check-task.zh-CN.md +1 -1
  224. package/templates/.opencode/commands/close-codescan.md +1 -1
  225. package/templates/.opencode/commands/close-codescan.zh-CN.md +1 -1
  226. package/templates/.opencode/commands/close-dependabot.md +1 -1
  227. package/templates/.opencode/commands/close-dependabot.zh-CN.md +1 -1
  228. package/templates/.opencode/commands/commit.md +1 -1
  229. package/templates/.opencode/commands/commit.zh-CN.md +1 -1
  230. package/templates/.opencode/commands/complete-task.md +1 -1
  231. package/templates/.opencode/commands/complete-task.zh-CN.md +1 -1
  232. package/templates/.opencode/commands/create-issue.zh-CN.md +1 -1
  233. package/templates/.opencode/commands/create-pr.md +1 -1
  234. package/templates/.opencode/commands/create-pr.zh-CN.md +1 -1
  235. package/templates/.opencode/commands/create-release-note.md +1 -1
  236. package/templates/.opencode/commands/create-release-note.zh-CN.md +1 -1
  237. package/templates/.opencode/commands/create-task.md +1 -1
  238. package/templates/.opencode/commands/create-task.zh-CN.md +1 -1
  239. package/templates/.opencode/commands/implement-task.md +1 -1
  240. package/templates/.opencode/commands/implement-task.zh-CN.md +1 -1
  241. package/templates/.opencode/commands/import-codescan.zh-CN.md +1 -1
  242. package/templates/.opencode/commands/import-dependabot.zh-CN.md +1 -1
  243. package/templates/.opencode/commands/import-issue.md +1 -1
  244. package/templates/.opencode/commands/import-issue.zh-CN.md +1 -1
  245. package/templates/.opencode/commands/init-labels.zh-CN.md +1 -1
  246. package/templates/.opencode/commands/init-milestones.md +1 -1
  247. package/templates/.opencode/commands/init-milestones.zh-CN.md +1 -1
  248. package/templates/.opencode/commands/plan-task.md +1 -1
  249. package/templates/.opencode/commands/plan-task.zh-CN.md +1 -1
  250. package/templates/.opencode/commands/refine-task.zh-CN.md +1 -1
  251. package/templates/.opencode/commands/refine-title.md +1 -1
  252. package/templates/.opencode/commands/refine-title.zh-CN.md +1 -1
  253. package/templates/.opencode/commands/release.md +1 -1
  254. package/templates/.opencode/commands/release.zh-CN.md +1 -1
  255. package/templates/.opencode/commands/review-task.md +1 -1
  256. package/templates/.opencode/commands/review-task.zh-CN.md +1 -1
  257. package/templates/.opencode/commands/sync-issue.md +1 -1
  258. package/templates/.opencode/commands/sync-issue.zh-CN.md +1 -1
  259. package/templates/.opencode/commands/sync-pr.md +1 -1
  260. package/templates/.opencode/commands/sync-pr.zh-CN.md +1 -1
  261. package/templates/.opencode/commands/test-integration.md +1 -1
  262. package/templates/.opencode/commands/test-integration.zh-CN.md +1 -1
  263. package/templates/.opencode/commands/test.md +1 -1
  264. package/templates/.opencode/commands/test.zh-CN.md +1 -1
  265. package/templates/.opencode/commands/update-agent-infra.md +1 -1
  266. package/templates/.opencode/commands/update-agent-infra.zh-CN.md +1 -1
  267. package/templates/.opencode/commands/upgrade-dependency.md +1 -1
  268. package/templates/.opencode/commands/upgrade-dependency.zh-CN.md +1 -1
  269. package/templates/AGENTS.md +10 -2
  270. package/templates/AGENTS.zh-CN.md +10 -2
@@ -1,8 +1,6 @@
1
1
  ---
2
2
  name: create-release-note
3
- description: >
4
- 从 PR 和 commit 生成版本发布说明。
5
- 当用户要求生成发布说明时触发。参数:版本号,可选的上一版本号。
3
+ description: "从 PR 和 commit 生成版本发布说明"
6
4
  ---
7
5
 
8
6
  # 创建发布说明
@@ -11,13 +9,13 @@ description: >
11
9
 
12
10
  ## 执行流程
13
11
 
14
- ### 步骤 1:解析参数
12
+ ### 1. 解析参数
15
13
 
16
14
  从参数中提取:
17
15
  - `<version>`:当前发布版本(必需),格式 `X.Y.Z`
18
16
  - `<prev-version>`:上一版本(可选),如未提供则自动检测
19
17
 
20
- ### 步骤 2:确定版本范围
18
+ ### 2. 确定版本范围
21
19
 
22
20
  **当前标签**:`v<version>`
23
21
 
@@ -33,7 +31,7 @@ git rev-parse v<version>
33
31
  git rev-parse v<prev-version>
34
32
  ```
35
33
 
36
- ### 步骤 3:参考历史发布说明格式与分类
34
+ ### 3. 参考历史发布说明格式与分类
37
35
 
38
36
  获取最近多条已发布的 Release Note 作为格式参考,并参考预定义的完整分类清单:
39
37
 
@@ -58,7 +56,7 @@ done
58
56
  - 后续步骤 7 生成发布说明时,**必须**同时参考步骤 3 的历史格式风格和完整分类清单,保持版本间的一致性
59
57
  - 如果没有历史发布说明,则使用步骤 7 中定义的默认格式
60
58
 
61
- ### 步骤 4:收集已合并的 PR
59
+ ### 4. 收集已合并的 PR
62
60
 
63
61
  获取标签之间的日期范围,然后查询已合并的 PR:
64
62
 
@@ -78,7 +76,7 @@ gh pr list --state merged --base <branch> \
78
76
  git log v<prev-version>..v<version> --format="%H %s" --no-merges
79
77
  ```
80
78
 
81
- ### 步骤 5:收集关联 Issue
79
+ ### 5. 收集关联 Issue
82
80
 
83
81
  从每个 PR body 中提取关联的 Issue:
84
82
  - 匹配模式:`Closes #N`、`Fixes #N`、`Resolves #N`(不区分大小写)
@@ -87,7 +85,7 @@ git log v<prev-version>..v<version> --format="%H %s" --no-merges
87
85
  gh issue view <N> --json number,title,labels,url
88
86
  ```
89
87
 
90
- ### 步骤 6:分类变更
88
+ ### 6. 分类变更
91
89
 
92
90
  **按类型**(从 PR 标题的 Conventional Commit 前缀):
93
91
  - `feat`、`perf`、`refactor`、依赖升级 -> Enhancement
@@ -98,7 +96,7 @@ gh issue view <N> --json number,title,labels,url
98
96
  - 从 PR 标题中的方括号 `[module]` 或 Conventional scope `feat(module):` 推断模块
99
97
  - 兜底:分析变更的文件
100
98
 
101
- ### 步骤 7:生成发布说明
99
+ ### 7. 生成发布说明
102
100
 
103
101
  **优先使用步骤 3 中获取的历史格式风格,并确保覆盖步骤 3 列出的所有分类。** 如果存在历史发布说明,严格沿用其章节结构、标题风格(含 emoji)、条目格式和双语布局。
104
102
 
@@ -127,7 +125,7 @@ gh issue view <N> --json number,title,labels,url
127
125
  4. 贡献者:去重,按贡献数量降序排列
128
126
  5. 空部分:省略没有条目的部分
129
127
 
130
- ### 步骤 8:展示并确认
128
+ ### 8. 展示并确认
131
129
 
132
130
  向用户展示生成的发布说明。
133
131
 
@@ -135,7 +133,7 @@ gh issue view <N> --json number,title,labels,url
135
133
  1. 需要调整吗?
136
134
  2. 是否创建 GitHub Draft Release?
137
135
 
138
- ### 步骤 9:创建 Draft Release(如确认)
136
+ ### 9. 创建 Draft Release(如确认)
139
137
 
140
138
  ```bash
141
139
  gh release create v<version> \
@@ -1,9 +1,6 @@
1
1
  ---
2
2
  name: create-task
3
- description: >
4
- Create a task skeleton from the user's natural-language description.
5
- Triggered when the user describes a new feature, bug, or improvement request.
6
- The only output is task.md; do not write any business code. Argument: task description text.
3
+ description: "Create a task from a natural-language description"
7
4
  ---
8
5
 
9
6
  # Create Task
@@ -1,8 +1,6 @@
1
1
  ---
2
2
  name: create-task
3
- description: >
4
- 根据用户的自然语言描述创建任务骨架。当用户描述一个新功能、Bug 或改进需求时触发。
5
- 唯一的产出是 task.md —— 不编写任何业务代码。参数:任务描述文本。
3
+ description: "根据自然语言描述创建任务"
6
4
  ---
7
5
 
8
6
  # 创建任务
@@ -1,104 +1,63 @@
1
1
  ---
2
2
  name: implement-task
3
- description: >
4
- Implement a task based on the technical plan, write code and tests, and
5
- output an implementation report. Triggered when the user requests task
6
- implementation or coding after the technical plan has been reviewed and
7
- approved. Argument: task-id.
3
+ description: "Implement a task from its technical plan and output a report"
8
4
  ---
9
5
 
10
6
  # Implement Task
11
7
 
8
+ Implement the approved task and produce `implementation.md` or `implementation-r{N}.md`.
9
+
12
10
  ## Boundary / Critical Rules
13
11
 
14
- - Strictly follow the latest technical plan artifact (`plan.md` or `plan-r{N}.md`) -- do not deviate without documenting the reason
15
- - Do NOT auto-commit. Never execute `git commit` or `git add` automatically
16
- - This skill outputs an implementation report (`implementation.md` or `implementation-r{N}.md`) and must never overwrite an existing round artifact
17
- - After executing this skill, you **must** immediately update task status in task.md
12
+ - Follow the latest approved plan artifact: `plan.md` or `plan-r{N}.md`
13
+ - Never auto-run `git add` or `git commit`
14
+ - Create a new implementation artifact for each round and never overwrite an older one
15
+ - After executing this skill, you **must** immediately update task.md
18
16
 
19
17
  ## Steps
20
18
 
21
19
  ### 1. Verify Prerequisites
22
20
 
23
- Check required files:
24
- - `.agents/workspace/active/{task-id}/task.md` - Task file
21
+ Check these files first:
22
+ - `.agents/workspace/active/{task-id}/task.md`
25
23
  - At least one technical plan artifact: `plan.md` or `plan-r{N}.md`
26
24
 
27
- Note: `{task-id}` format is `TASK-{yyyyMMdd-HHmmss}`, e.g. `TASK-20260306-143022`
28
-
29
- If either file is missing, prompt the user to complete the prerequisite step first.
25
+ If either file is missing, stop and ask the user to complete the prerequisite step.
30
26
 
31
27
  ### 2. Determine the Input Plan and Implementation Round
32
28
 
33
- Scan `.agents/workspace/active/{task-id}/` for technical plan files (`plan.md`, `plan-r{N}.md`):
34
- - Read the highest-round plan file and record it as `{plan-artifact}`
35
-
36
- Scan `.agents/workspace/active/{task-id}/` for implementation report files:
37
- - If neither `implementation.md` nor `implementation-r*.md` exists -> this is Round 1 and must create `implementation.md`
38
- - If `implementation.md` exists and no `implementation-r*.md` exists -> this is Round 2 and must create `implementation-r2.md`
39
- - If `implementation-r{N}.md` exists -> this is Round N+1 and must create `implementation-r{N+1}.md`
40
-
41
- Record:
42
- - `{plan-artifact}`: the technical plan file used for this implementation
43
- - `{implementation-round}`: the current implementation round
44
- - `{implementation-artifact}`: the implementation report filename for this round
45
-
46
- Note: multi-round implementation should only happen after a review verdict of Rejected. A normal first implementation always creates `implementation.md`.
29
+ Scan `.agents/workspace/active/{task-id}/` and record:
30
+ - the highest-round plan file as `{plan-artifact}`
31
+ - the next implementation artifact as `implementation.md` or `implementation-r{N}.md`
32
+ - `{implementation-round}` and `{implementation-artifact}`
47
33
 
48
- ### 3. Read Technical Plan
34
+ If any `plan-r{N}.md` exists, read the highest-round plan file. Otherwise read `plan.md`.
49
35
 
50
- Carefully read `{plan-artifact}` to understand:
51
- - Technical approach and solution strategy
52
- - Detailed implementation steps
53
- - Files to create/modify
54
- - Test strategy
55
- - Any constraints or risks
36
+ ### 3. Read the Technical Plan
56
37
 
57
- ### 4. Execute Code Implementation
38
+ Read `{plan-artifact}` carefully and extract:
39
+ - implementation steps
40
+ - files to create or modify
41
+ - test strategy
42
+ - constraints, risks, and any approved tradeoffs
58
43
 
59
- Follow the `implementation` step in `.agents/workflows/feature-development.yaml`:
44
+ ### 4. Implement the Code
60
45
 
61
- **Required tasks**:
62
- - [ ] Implement functionality code following the plan
63
- - [ ] Write comprehensive unit tests
64
- - [ ] Run tests locally to verify functionality
65
- - [ ] Update related documentation and comments
66
- - [ ] Follow project coding standards (see project instructions)
46
+ Follow `.agents/workflows/feature-development.yaml` and the plan in order.
67
47
 
68
- **Implementation principles**:
69
- 1. **Strictly follow the plan**: Do not deviate from the technical plan
70
- 2. **Step by step**: Execute plan steps in order
71
- 3. **Test continuously**: Run tests after completing each step
72
- 4. **Keep it simple**: Do not over-engineer or add unplanned features
48
+ > Detailed implementation rules, testing discipline, and deviation handling live in `reference/implementation-rules.md`. Read `reference/implementation-rules.md` before executing this step.
73
49
 
74
50
  ### 5. Run Test Verification
75
51
 
76
- Execute the project's test command. Reference the `test` skill for the project-specific test command:
52
+ Use the project test command from the `test` skill and keep iterating until all required tests pass.
77
53
 
78
- ```bash
79
- # Check .agents/skills/test/SKILL.md for the project's test command
80
- # Common patterns:
81
- # npm test (Node.js)
82
- # mvn test (Maven)
83
- # pytest (Python)
84
- # go test ./... (Go)
85
- ```
86
-
87
- If tests fail:
88
- - Analyze the failure first, and prioritize fixing problems introduced by the current implementation, plus any test or documentation updates required to match the approved plan
89
- - Re-run the tests after each fix until they pass, or until you confirm the remaining issue is an external blocker outside the current task scope
90
- - Only stop when the failure is blocked by external dependencies, missing environment, or unclear requirements that cannot be resolved within the task; in that case, report the blocker and do not create the implementation report, update task.md as implementation-complete, or output the Step 8 completion template
54
+ If tests fail, Attempt to fix the issue and re-run tests first. Only stop when you confirm an external blocker, missing environment, or unclear requirement that is out of scope for the task.
91
55
 
92
- Proceed to Steps 6, 7, and 8 only after the full test suite passes.
93
-
94
- ### 6. Output Implementation Report
56
+ ### 6. Write the Implementation Report
95
57
 
96
58
  Create `.agents/workspace/active/{task-id}/{implementation-artifact}`.
97
59
 
98
- Requirements:
99
- - Do not overwrite any existing implementation report
100
- - Record the actual round number and artifact filename in the report
101
- - If this is a re-implementation round, explain what triggered it
60
+ > Report structure, required sections, and the full template live in `reference/report-template.md`. Read `reference/report-template.md` before writing the report.
102
61
 
103
62
  ### 7. Update Task Status
104
63
 
@@ -110,125 +69,36 @@ date "+%Y-%m-%d %H:%M:%S"
110
69
 
111
70
  Update `.agents/workspace/active/{task-id}/task.md`:
112
71
  - `current_step`: implementation
113
- - `assigned_to`: {current AI agent}
72
+ - `assigned_to`: {current agent}
114
73
  - `updated_at`: {current time}
115
- - Record the implementation artifact for this round: `{implementation-artifact}` (Round `{implementation-round}`)
116
- - Mark implementation as complete in workflow progress and include the actual round when the task template supports it
117
- - **Append** to `## Activity Log` (do NOT overwrite previous entries):
118
- ```
119
- - {yyyy-MM-dd HH:mm:ss} — **Implementation (Round {N})** by {agent} — Code implemented, {n} files modified, {n} tests passed → {artifact-filename}
120
- ```
121
-
122
- ### 8. Inform User
123
-
124
- > **IMPORTANT**: All TUI command formats listed below must be output in full. Do not show only the format for the current AI agent.
125
-
126
- Output format:
127
- ```
128
- Implementation complete for task {task-id}.
129
-
130
- Summary:
131
- - Modified files: {count}
132
- - New files: {count}
133
- - Tests passed: {count}/{total}
134
-
135
- Output file:
136
- - Implementation report: .agents/workspace/active/{task-id}/{implementation-artifact} (Round {implementation-round})
137
-
138
- Next step - code review:
139
- - Claude Code / OpenCode: /review-task {task-id}
140
- - Gemini CLI: /{{project}}:review-task {task-id}
141
- - Codex CLI: $review-task {task-id}
142
- ```
143
-
144
- ## Output Template
145
-
146
- ```markdown
147
- # Implementation Report
148
-
149
- - **Implementation round**: Round {implementation-round}
150
- - **Artifact file**: `{implementation-artifact}`
74
+ - record `{implementation-artifact}` for Round `{implementation-round}`
75
+ - append:
76
+ `- {yyyy-MM-dd HH:mm:ss} — **Implementation (Round {N})** by {agent} Code implemented, {n} files modified, {n} tests passed → {implementation-artifact}`
151
77
 
152
- ## Modified Files
78
+ ### 8. Inform the User
153
79
 
154
- ### New Files
155
- - `{file-path}` - {Description}
156
-
157
- ### Modified Files
158
- - `{file-path}` - {Summary of changes}
159
-
160
- ## Key Code Explanation
161
-
162
- ### {Module/Feature Name}
163
- **File**: `{file-path}:{line-number}`
164
-
165
- **Implementation logic**:
166
- {Explanation of important logic}
167
-
168
- **Key code**:
169
- ```{language}
170
- {Key code snippet}
171
- ```
172
-
173
- ## Test Results
174
-
175
- ### Unit Tests
176
- - Test file: `{test-file-path}`
177
- - Test cases: {count}
178
- - Pass rate: {percentage}
179
-
180
- **Test output**:
181
- ```
182
- {Test run results}
183
- ```
184
-
185
- ## Differences from Plan
186
-
187
- {If implementation differs from plan, explain why}
188
-
189
- ## Items for Review
190
-
191
- **Points that need reviewer attention**:
192
- - {Attention point 1}
193
- - {Attention point 2}
194
-
195
- ## Known Issues
196
-
197
- {Issues discovered during implementation or items to optimize later}
198
-
199
- ## Next Steps
200
-
201
- {Suggestions for code review or follow-up work}
202
- ```
80
+ Output the implementation summary and include all TUI command variants for the next review step.
203
81
 
204
82
  ## Completion Checklist
205
83
 
206
- - [ ] Completed all code implementation
207
- - [ ] Created implementation report `.agents/workspace/active/{task-id}/{implementation-artifact}`
208
- - [ ] All tests pass
209
- - [ ] Updated `current_step` to implementation in task.md
210
- - [ ] Updated `updated_at` to current time in task.md
211
- - [ ] Updated `assigned_to` in task.md
212
- - [ ] Appended entry to Activity Log in task.md
213
- - [ ] Marked implementation as complete in workflow progress
214
- - [ ] Informed user of next step (must include all TUI command formats — do not filter)
84
+ - [ ] Implemented the approved code changes
85
+ - [ ] Created `{implementation-artifact}`
86
+ - [ ] All required tests passed
87
+ - [ ] Updated task.md and appended the Activity Log entry
88
+ - [ ] Included every TUI command format in the user-facing next step
215
89
 
216
90
  ## STOP
217
91
 
218
- After completing the checklist, **stop**. Do not auto-commit. Wait for code review before submission.
92
+ Stop after the checklist is complete. Do not auto-commit.
219
93
 
220
94
  ## Notes
221
95
 
222
- 1. **Prerequisites**: Must have a reviewed technical plan (`plan.md` or `plan-r{N}.md` exists and is approved)
223
- 2. **No auto-commit**: Do NOT execute `git commit` or `git add` automatically. Remind the user to commit manually
224
- 3. **Test requirement**: All new code must have unit tests; test coverage must not decrease. When removing a feature, delete the test fixtures and assertions that existed solely for that feature — do not mechanically flip assertions; every assertion must verify meaningful business logic, not merely confirm that data passes through unchanged
225
- 4. **Code quality**: Follow project coding standards
226
- 5. **Plan deviation**: If you need to deviate from the plan, document the reason in the implementation report
227
- 6. **Versioning rule**: First-round implementation uses `implementation.md`; later re-implementations use `implementation-r{N}.md`
96
+ - Round 1 uses `implementation.md`; later rounds use `implementation-r{N}.md`
97
+ - Record any deviation from `{plan-artifact}` in the report
98
+ - New tests must validate meaningful business behavior, not just passthrough data
228
99
 
229
100
  ## Error Handling
230
101
 
231
- - Task not found: Prompt "Task {task-id} not found"
232
- - Missing plan: Prompt "Technical plan not found, please run the plan-task skill first"
233
- - Test failure: Attempt to fix the issue and re-run tests first; stop only when an external blocker, missing environment, or unclear requirement prevents completion, and report that blocker
234
- - Build failure: Output build errors, stop implementation
102
+ - Task not found: `Task {task-id} not found`
103
+ - Missing plan: `Technical plan not found, please run the plan-task skill first`
104
+ - Test failure after local fixes: explain the external blocker and stop without creating the implementation artifact
@@ -1,102 +1,63 @@
1
1
  ---
2
2
  name: implement-task
3
- description: >
4
- 根据技术方案实施任务,编写代码和测试,输出实现报告。当用户在技术方案审查通过后要求实施任务或编码时触发。
5
- 参数:task-id。
3
+ description: "根据技术方案实施任务并输出报告"
6
4
  ---
7
5
 
8
6
  # 实施任务
9
7
 
8
+ 根据已批准的技术方案实施任务,并产出 `implementation.md` 或 `implementation-r{N}.md`。
9
+
10
10
  ## 行为边界 / 关键规则
11
11
 
12
- - 严格遵循最新技术方案产物(`plan.md` 或 `plan-r{N}.md`)—— 不要偏离,除非记录了偏离原因
13
- - 不要自动提交。绝不自动执行 `git commit` 或 `git add`
14
- - 本技能产出实现报告(`implementation.md` 或 `implementation-r{N}.md`)—— 不覆盖已有轮次产物
15
- - 执行本技能后,你**必须**立即更新 task.md 中的任务状态
12
+ - 严格遵循最新方案产物:`plan.md` 或 `plan-r{N}.md`
13
+ - 绝不自动执行 `git add` 或 `git commit`
14
+ - 每轮实现都创建新的实现产物,不覆盖旧文件
15
+ - 执行本技能后,你**必须**立即更新 task.md
16
16
 
17
17
  ## 执行步骤
18
18
 
19
19
  ### 1. 验证前置条件
20
20
 
21
- 检查必要文件:
22
- - `.agents/workspace/active/{task-id}/task.md` - 任务文件
21
+ 先检查:
22
+ - `.agents/workspace/active/{task-id}/task.md`
23
23
  - 至少一个技术方案产物:`plan.md` 或 `plan-r{N}.md`
24
24
 
25
- 注意:`{task-id}` 格式为 `TASK-{yyyyMMdd-HHmmss}`,例如 `TASK-20260306-143022`
26
-
27
- 如果任一文件缺失,提示用户先完成前置步骤。
25
+ 如果缺少任一文件,立即停止并提示用户先完成前置步骤。
28
26
 
29
27
  ### 2. 确定输入方案与实现轮次
30
28
 
31
- 扫描 `.agents/workspace/active/{task-id}/` 目录中的技术方案文件(`plan.md`、`plan-r{N}.md`):
32
- - 读取最高轮次的方案文件,记为 `{plan-artifact}`
33
-
34
- 扫描 `.agents/workspace/active/{task-id}/` 目录中的实现报告文件:
35
- - 如果不存在 `implementation.md` 且不存在 `implementation-r*.md` → 本轮为第 1 轮,产出 `implementation.md`
36
- - 如果存在 `implementation.md` 且不存在 `implementation-r*.md` → 本轮为第 2 轮,产出 `implementation-r2.md`
37
- - 如果存在 `implementation-r{N}.md` → 本轮为第 N+1 轮,产出 `implementation-r{N+1}.md`
29
+ 扫描 `.agents/workspace/active/{task-id}/` 并记录:
30
+ - 最高轮次的方案文件为 `{plan-artifact}`
31
+ - 本轮实现产物为 `implementation.md` 或 `implementation-r{N}.md`
32
+ - `{implementation-round}` 与 `{implementation-artifact}`
38
33
 
39
- 记录:
40
- - `{plan-artifact}`:本次实现遵循的技术方案文件
41
- - `{implementation-round}`:本轮实现轮次
42
- - `{implementation-artifact}`:本轮实现报告文件名
43
-
44
- 注意:仅在审查结论为“拒绝”后重新执行时才会进入多轮。正常首次实现始终产出 `implementation.md`。
34
+ 如果存在 `plan-r{N}.md`,读取最高轮次的方案文件;否则读取 `plan.md`。
45
35
 
46
36
  ### 3. 阅读技术方案
47
37
 
48
- 仔细阅读 `{plan-artifact}` 以理解:
49
- - 技术方法和解决策略
50
- - 详细实施步骤
51
- - 需要创建/修改的文件
38
+ 仔细阅读 `{plan-artifact}`,提取:
39
+ - 实施步骤
40
+ - 需要创建或修改的文件
52
41
  - 测试策略
53
- - 任何约束或风险
42
+ - 约束、风险与已批准的取舍
54
43
 
55
44
  ### 4. 执行代码实现
56
45
 
57
- 遵循 `.agents/workflows/feature-development.yaml` 中的 `implementation` 步骤:
58
-
59
- **必要任务**:
60
- - [ ] 按照计划实现功能代码
61
- - [ ] 编写全面的单元测试
62
- - [ ] 在本地运行测试以验证功能
63
- - [ ] 更新相关文档和注释
64
- - [ ] 遵循项目编码规范(参见项目指南)
46
+ 按照 `.agents/workflows/feature-development.yaml` 和方案顺序实施。
65
47
 
66
- **实现原则**:
67
- 1. **严格遵循计划**:不偏离技术方案
68
- 2. **逐步执行**:按顺序执行计划步骤
69
- 3. **持续测试**:每完成一个步骤后运行测试
70
- 4. **保持简单**:不过度设计,不添加计划外的功能
48
+ > 详细实现规则、测试纪律和偏离处理见 `reference/implementation-rules.md`。执行此步骤前,先读取 `reference/implementation-rules.md`。
71
49
 
72
50
  ### 5. 运行测试验证
73
51
 
74
- 执行项目的测试命令。参考 `test` 技能获取项目特定的测试命令:
52
+ 使用 `test` 技能中的项目测试命令,直到所有必需测试通过。
75
53
 
76
- ```bash
77
- # 查看 .agents/skills/test/SKILL.md 获取项目测试命令
78
- # 常见模式:
79
- # npm test (Node.js)
80
- # mvn test (Maven)
81
- # pytest (Python)
82
- # go test ./... (Go)
83
- ```
84
-
85
- 如果测试失败:
86
- - 先分析失败原因,优先修复由本次实现引入的问题,以及为匹配已批准方案而需要同步调整的测试或文档
87
- - 修复后重新运行测试,直到测试通过,或明确确认存在超出当前任务范围的外部阻塞
88
- - 仅当问题属于外部阻塞、环境缺失或需求不明确且无法在当前任务内解决时,才向用户报告阻塞并停止;此时不要创建实现报告,不要更新 task.md 为实现完成,也不要输出步骤 8 的完成模板
54
+ 如果测试失败,先尝试修复并重新运行测试。只有在确认存在外部阻塞、环境缺失或需求不明确且超出任务范围时,才可以停止。
89
55
 
90
- 只有全部测试通过后,才可以继续步骤 6、7 和 8。
91
-
92
- ### 6. 输出实现报告
56
+ ### 6. 编写实现报告
93
57
 
94
58
  创建 `.agents/workspace/active/{task-id}/{implementation-artifact}`。
95
59
 
96
- 要求:
97
- - 不要覆盖已有的实现报告
98
- - 在报告中明确记录本轮轮次编号和实际产物文件名
99
- - 如果本轮是重实现,说明其触发原因(例如上一轮审查结论为 Rejected)
60
+ > 报告结构、必填章节和完整模板见 `reference/report-template.md`。写报告前先读取 `reference/report-template.md`。
100
61
 
101
62
  ### 7. 更新任务状态
102
63
 
@@ -108,125 +69,36 @@ date "+%Y-%m-%d %H:%M:%S"
108
69
 
109
70
  更新 `.agents/workspace/active/{task-id}/task.md`:
110
71
  - `current_step`:implementation
111
- - `assigned_to`:{当前 AI 代理}
72
+ - `assigned_to`:{当前代理}
112
73
  - `updated_at`:{当前时间}
113
- - 记录本轮实现产物:`{implementation-artifact}`(Round `{implementation-round}`)
114
- - 在工作流进度中标记 implementation 为已完成,并注明实际轮次(如果任务模板支持)
115
- - **追加**到 `## Activity Log`(不要覆盖之前的记录):
116
- ```
117
- - {yyyy-MM-dd HH:mm:ss} — **Implementation (Round {N})** by {agent} — Code implemented, {n} files modified, {n} tests passed → {artifact-filename}
118
- ```
74
+ - 记录 Round `{implementation-round}` `{implementation-artifact}`
75
+ - 追加:
76
+ `- {yyyy-MM-dd HH:mm:ss} **Implementation (Round {N})** by {agent} — Code implemented, {n} files modified, {n} tests passed → {implementation-artifact}`
119
77
 
120
78
  ### 8. 告知用户
121
79
 
122
- > **重要**:以下「下一步」中列出的所有 TUI 命令格式必须完整输出,不要只展示当前 AI 代理对应的格式。
123
-
124
- 输出格式:
125
- ```
126
- 任务 {task-id} 实现完成。
127
-
128
- 摘要:
129
- - 修改文件:{数量}
130
- - 新建文件:{数量}
131
- - 测试通过:{数量}/{总数}
132
-
133
- 产出文件:
134
- - 实现报告:.agents/workspace/active/{task-id}/{implementation-artifact}(Round {implementation-round})
135
-
136
- 下一步 - 代码审查:
137
- - Claude Code / OpenCode:/review-task {task-id}
138
- - Gemini CLI:/{{project}}:review-task {task-id}
139
- - Codex CLI:$review-task {task-id}
140
- ```
141
-
142
- ## 输出模板
143
-
144
- ```markdown
145
- # 实现报告
146
-
147
- - **实现轮次**:Round {implementation-round}
148
- - **产物文件**:`{implementation-artifact}`
149
-
150
- ## 修改文件
151
-
152
- ### 新建文件
153
- - `{file-path}` - {描述}
154
-
155
- ### 修改文件
156
- - `{file-path}` - {变更摘要}
157
-
158
- ## 关键代码说明
159
-
160
- ### {模块/功能名称}
161
- **文件**:`{file-path}:{line-number}`
162
-
163
- **实现逻辑**:
164
- {重要逻辑的说明}
165
-
166
- **关键代码**:
167
- ```{language}
168
- {关键代码片段}
169
- ```
170
-
171
- ## 测试结果
172
-
173
- ### 单元测试
174
- - 测试文件:`{test-file-path}`
175
- - 测试用例数:{数量}
176
- - 通过率:{百分比}
177
-
178
- **测试输出**:
179
- ```
180
- {测试运行结果}
181
- ```
182
-
183
- ## 与计划的差异
184
-
185
- {如果实现与计划有差异,说明原因}
186
-
187
- ## 审查关注点
188
-
189
- **需要审查者注意的要点**:
190
- - {关注点 1}
191
- - {关注点 2}
192
-
193
- ## 已知问题
194
-
195
- {实现过程中发现的问题或后续需要优化的事项}
196
-
197
- ## 后续步骤
198
-
199
- {代码审查或后续工作的建议}
200
- ```
80
+ 输出实现摘要,并完整展示下一步代码审查的所有 TUI 命令格式。
201
81
 
202
82
  ## 完成检查清单
203
83
 
204
- - [ ] 完成了所有代码实现
205
- - [ ] 创建了实现报告 `.agents/workspace/active/{task-id}/{implementation-artifact}`
206
- - [ ] 所有测试通过
207
- - [ ] 更新了 task.md 中的 `current_step` 为 implementation
208
- - [ ] 更新了 task.md 中的 `updated_at` 为当前时间
209
- - [ ] 更新了 task.md 中的 `assigned_to`
210
- - [ ] 追加了 Activity Log 条目到 task.md
211
- - [ ] 在工作流进度中标记了 implementation 为已完成
212
- - [ ] 告知了用户下一步(必须展示所有 TUI 的命令格式,不要筛选)
84
+ - [ ] 已完成批准范围内的代码实现
85
+ - [ ] 已创建 `{implementation-artifact}`
86
+ - [ ] 所有必需测试通过
87
+ - [ ] 已更新 task.md 并追加 Activity Log
88
+ - [ ] 已向用户展示所有 TUI 格式的下一步命令
213
89
 
214
90
  ## 停止
215
91
 
216
- 完成检查清单后,**停止**。不要自动提交。等待代码审查后再提交。
92
+ 完成检查清单后立即停止。不要自动提交。
217
93
 
218
94
  ## 注意事项
219
95
 
220
- 1. **前置条件**:必须有已审查的技术方案(`plan.md` `plan-r{N}.md` 存在且已获批准)
221
- 2. **禁止自动提交**:不要自动执行 `git commit` 或 `git add`。提醒用户手动提交
222
- 3. **测试要求**:所有新代码必须有单元测试;测试覆盖率不得下降。删除功能时,必须同时删除为该功能而存在的测试 fixture 和断言,不要机械地翻转断言方向;每条断言都应验证有意义的业务逻辑,仅确认数据原样通过的断言不构成有效测试
223
- 4. **代码质量**:遵循项目编码规范
224
- 5. **计划偏离**:如果需要偏离计划,在实现报告中记录原因
225
- 6. **版本化规则**:首轮实现使用 `implementation.md`;后续重实现使用 `implementation-r{N}.md`
96
+ - 首轮实现使用 `implementation.md`,后续轮次使用 `implementation-r{N}.md`
97
+ - 如偏离 `{plan-artifact}`,必须在报告中记录原因
98
+ - 新测试必须验证有意义的业务行为,而不是机械透传
226
99
 
227
100
  ## 错误处理
228
101
 
229
- - 任务未找到:提示 "Task {task-id} not found"
230
- - 缺少计划:提示 "Technical plan not found, please run the plan-task skill first"
231
- - 测试失败:先尝试修复并重新运行测试;只有在存在外部阻塞、环境缺失或需求不明确时才停止,并输出阻塞原因
232
- - 构建失败:输出构建错误,停止实现
102
+ - 任务未找到:`Task {task-id} not found`
103
+ - 缺少方案:`Technical plan not found, please run the plan-task skill first`
104
+ - 本地修复后仍无法通过测试:说明外部阻塞并停止,且不要创建实现产物