pi-maestro-flow 0.2.0 → 0.3.1

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 (235) hide show
  1. package/README.md +44 -72
  2. package/agents/cross-role-reviewer.md +1 -1
  3. package/agents/impeccable-agent.md +1 -1
  4. package/agents/ralph-executor.md +1 -1
  5. package/agents/team-worker.md +1 -1
  6. package/agents/workflow-analyzer.md +1 -1
  7. package/agents/workflow-codebase-mapper.md +1 -1
  8. package/agents/workflow-collab-planner.md +1 -1
  9. package/agents/workflow-debugger.md +1 -1
  10. package/agents/workflow-executor.md +1 -1
  11. package/agents/workflow-integration-checker.md +1 -1
  12. package/agents/workflow-nyquist-auditor.md +1 -1
  13. package/agents/workflow-phase-researcher.md +1 -1
  14. package/agents/workflow-planner.md +1 -1
  15. package/agents/workflow-project-researcher.md +1 -1
  16. package/agents/workflow-reviewer.md +1 -1
  17. package/agents/workflow-verifier.md +1 -1
  18. package/package.json +18 -4
  19. package/skills/codify-to-knowhow/SKILL.md +1 -1
  20. package/skills/delegation-check/SKILL.md +1 -1
  21. package/skills/domain-add/SKILL.md +5 -5
  22. package/skills/insight-challenge/SKILL.md +1 -1
  23. package/skills/learn-decompose/SKILL.md +4 -4
  24. package/skills/learn-follow/SKILL.md +5 -5
  25. package/skills/learn-investigate/SKILL.md +5 -5
  26. package/skills/learn-second-opinion/SKILL.md +5 -5
  27. package/skills/maestro/SKILL.md +8 -8
  28. package/skills/maestro-amend/SKILL.md +4 -4
  29. package/skills/maestro-analyze/SKILL.md +9 -9
  30. package/skills/maestro-blueprint/SKILL.md +7 -7
  31. package/skills/maestro-brainstorm/SKILL.md +10 -10
  32. package/skills/maestro-collab/SKILL.md +4 -4
  33. package/skills/maestro-companion/SKILL.md +3 -3
  34. package/skills/maestro-composer/SKILL.md +10 -10
  35. package/skills/maestro-execute/SKILL.md +8 -8
  36. package/skills/maestro-fork/SKILL.md +7 -7
  37. package/skills/maestro-grill/SKILL.md +12 -12
  38. package/skills/maestro-guard/SKILL.md +5 -5
  39. package/skills/maestro-help/SKILL.md +3 -3
  40. package/skills/maestro-impeccable/SKILL.md +7 -7
  41. package/skills/maestro-init/SKILL.md +8 -8
  42. package/skills/maestro-merge/SKILL.md +6 -6
  43. package/skills/maestro-milestone-audit/SKILL.md +3 -3
  44. package/skills/maestro-milestone-complete/SKILL.md +8 -8
  45. package/skills/maestro-milestone-release/SKILL.md +9 -9
  46. package/skills/maestro-next/SKILL.md +5 -5
  47. package/skills/maestro-overlay/SKILL.md +19 -19
  48. package/skills/maestro-plan/SKILL.md +8 -8
  49. package/skills/maestro-player/SKILL.md +5 -5
  50. package/skills/maestro-quick/SKILL.md +5 -5
  51. package/skills/maestro-ralph/SKILL.md +15 -15
  52. package/skills/maestro-ralph-cli/SKILL.md +6 -6
  53. package/skills/maestro-ralph-cli-execute/SKILL.md +2 -2
  54. package/skills/maestro-ralph-execute/SKILL.md +4 -4
  55. package/skills/maestro-ralph-v2/SKILL.md +17 -17
  56. package/skills/maestro-roadmap/SKILL.md +7 -7
  57. package/skills/maestro-swarm-workflow/SKILL.md +9 -9
  58. package/skills/maestro-tools-execute/SKILL.md +5 -5
  59. package/skills/maestro-tools-register/SKILL.md +7 -7
  60. package/skills/maestro-ui-codify/SKILL.md +8 -8
  61. package/skills/maestro-universal-workflow/SKILL.md +15 -15
  62. package/skills/maestro-update/SKILL.md +10 -10
  63. package/skills/manage-codebase-rebuild/SKILL.md +4 -4
  64. package/skills/manage-drift-realign/SKILL.md +7 -7
  65. package/skills/manage-harvest/SKILL.md +5 -5
  66. package/skills/manage-issue/SKILL.md +4 -4
  67. package/skills/manage-issue-discover/SKILL.md +7 -7
  68. package/skills/manage-kg-extractors/SKILL.md +3 -3
  69. package/skills/manage-knowhow/SKILL.md +3 -3
  70. package/skills/manage-knowhow-capture/SKILL.md +4 -4
  71. package/skills/manage-knowledge-audit/SKILL.md +5 -5
  72. package/skills/manage-status/SKILL.md +3 -3
  73. package/skills/manage-wiki/SKILL.md +5 -5
  74. package/skills/odyssey-debug/SKILL.md +13 -13
  75. package/skills/odyssey-improve/SKILL.md +15 -15
  76. package/skills/odyssey-planex/SKILL.md +16 -16
  77. package/skills/odyssey-review-test-fix/SKILL.md +11 -11
  78. package/skills/odyssey-ui/SKILL.md +10 -10
  79. package/skills/prompt-generator/SKILL.md +5 -5
  80. package/skills/quality-auto-test/SKILL.md +3 -3
  81. package/skills/quality-debug/SKILL.md +3 -3
  82. package/skills/quality-refactor/SKILL.md +3 -3
  83. package/skills/quality-retrospective/SKILL.md +9 -9
  84. package/skills/quality-review/SKILL.md +4 -4
  85. package/skills/quality-sync/SKILL.md +3 -3
  86. package/skills/quality-test/SKILL.md +4 -4
  87. package/skills/scholar-anti-ai-writing/SKILL.md +1 -1
  88. package/skills/scholar-citation-verify/SKILL.md +1 -1
  89. package/skills/scholar-experiment/SKILL.md +2 -2
  90. package/skills/scholar-ideation/SKILL.md +7 -7
  91. package/skills/scholar-latex-organizer/SKILL.md +1 -1
  92. package/skills/scholar-publish/SKILL.md +3 -3
  93. package/skills/scholar-rebuttal-pro/SKILL.md +3 -3
  94. package/skills/scholar-review/SKILL.md +1 -1
  95. package/skills/scholar-writing/SKILL.md +1 -1
  96. package/skills/security-audit/SKILL.md +2 -2
  97. package/skills/skill-generator/SKILL.md +3 -3
  98. package/skills/skill-iter-tune/SKILL.md +3 -3
  99. package/skills/skill-simplify/SKILL.md +1 -1
  100. package/skills/skill-tuning/SKILL.md +1 -1
  101. package/skills/spec-add/SKILL.md +5 -5
  102. package/skills/spec-load/SKILL.md +3 -3
  103. package/skills/spec-remove/SKILL.md +4 -4
  104. package/skills/spec-setup/SKILL.md +6 -6
  105. package/skills/team-adversarial-swarm/SKILL.md +5 -5
  106. package/skills/team-arch-opt/SKILL.md +2 -2
  107. package/skills/team-brainstorm/SKILL.md +3 -3
  108. package/skills/team-coordinate/SKILL.md +4 -4
  109. package/skills/team-designer/SKILL.md +1 -1
  110. package/skills/team-executor/SKILL.md +3 -3
  111. package/skills/team-frontend/SKILL.md +2 -2
  112. package/skills/team-frontend-debug/SKILL.md +3 -3
  113. package/skills/team-interactive-craft/SKILL.md +2 -2
  114. package/skills/team-issue/SKILL.md +3 -3
  115. package/skills/team-lifecycle-v4/SKILL.md +4 -4
  116. package/skills/team-motion-design/SKILL.md +2 -2
  117. package/skills/team-perf-opt/SKILL.md +3 -3
  118. package/skills/team-planex/SKILL.md +2 -2
  119. package/skills/team-quality-assurance/SKILL.md +3 -3
  120. package/skills/team-review/SKILL.md +3 -3
  121. package/skills/team-roadmap-dev/SKILL.md +3 -3
  122. package/skills/team-swarm/SKILL.md +4 -4
  123. package/skills/team-tech-debt/SKILL.md +2 -2
  124. package/skills/team-testing/SKILL.md +3 -3
  125. package/skills/team-ui-polish/SKILL.md +2 -2
  126. package/skills/team-uidesign/SKILL.md +2 -2
  127. package/skills/team-ultra-analyze/SKILL.md +4 -4
  128. package/skills/team-ux-improve/SKILL.md +3 -3
  129. package/skills/team-visual-a11y/SKILL.md +2 -2
  130. package/skills/workflow-skill-designer/SKILL.md +8 -8
  131. package/templates/business-test-report.json +68 -0
  132. package/templates/config.json +48 -0
  133. package/templates/context.md +16 -0
  134. package/templates/doc-index.json +11 -0
  135. package/templates/index.json +68 -0
  136. package/templates/issue.json +36 -0
  137. package/templates/plan.json +38 -0
  138. package/templates/project.md +60 -0
  139. package/templates/reflection-log.md +20 -0
  140. package/templates/roadmap.md +45 -0
  141. package/templates/scratch-index.json +19 -0
  142. package/templates/search-tool.json +1 -0
  143. package/templates/search-tools.md +47 -0
  144. package/templates/state.json +18 -0
  145. package/templates/task-summary.md +21 -0
  146. package/templates/task.json +89 -0
  147. package/templates/terminology-template.json +22 -0
  148. package/templates/uat.md +21 -0
  149. package/templates/validation.json +31 -0
  150. package/templates/verification.json +37 -0
  151. package/templates/workflow.md +14 -0
  152. package/templates/worktree-scope.json +9 -0
  153. package/templates/worktrees.json +26 -0
  154. package/workflows/agy-instructions.md +156 -0
  155. package/workflows/analyze.md +768 -0
  156. package/workflows/auto-test.md +705 -0
  157. package/workflows/blueprint.md +406 -0
  158. package/workflows/boundary-grill.md +50 -0
  159. package/workflows/brainstorm.md +508 -0
  160. package/workflows/business-test.md +574 -0
  161. package/workflows/chinese-response.md +25 -0
  162. package/workflows/claude-instructions.md +167 -0
  163. package/workflows/codebase-rebuild.md +267 -0
  164. package/workflows/codebase-refresh.md +168 -0
  165. package/workflows/codex-instructions.md +156 -0
  166. package/workflows/coding-philosophy.md +70 -0
  167. package/workflows/command-authoring.md +823 -0
  168. package/workflows/debug.md +409 -0
  169. package/workflows/delegate-usage.md +99 -0
  170. package/workflows/domain-add.md +121 -0
  171. package/workflows/drift-realign.md +396 -0
  172. package/workflows/execute.md +631 -0
  173. package/workflows/explore-usage.md +93 -0
  174. package/workflows/finish-work.md +124 -0
  175. package/workflows/fork.md +162 -0
  176. package/workflows/grill.md +494 -0
  177. package/workflows/harvest.md +478 -0
  178. package/workflows/impeccable.md +168 -0
  179. package/workflows/init.md +157 -0
  180. package/workflows/instruction-authoring-guide.md +97 -0
  181. package/workflows/integration-test.md +186 -0
  182. package/workflows/interview-mechanics.md +8 -0
  183. package/workflows/issue-analyze.md +20 -0
  184. package/workflows/issue-discover.md +238 -0
  185. package/workflows/issue-execute.md +110 -0
  186. package/workflows/issue-gaps-analyze.codex.md +256 -0
  187. package/workflows/issue-gaps-analyze.md +215 -0
  188. package/workflows/issue-plan.md +110 -0
  189. package/workflows/issue.md +338 -0
  190. package/workflows/knowhow.md +429 -0
  191. package/workflows/knowledge-audit.md +355 -0
  192. package/workflows/learn.md +271 -0
  193. package/workflows/maestro-chain-execute.md +20 -0
  194. package/workflows/maestro-link-coordinate.md +114 -0
  195. package/workflows/maestro-super.md +120 -0
  196. package/workflows/maestro.md +501 -0
  197. package/workflows/map.md +74 -0
  198. package/workflows/merge.md +122 -0
  199. package/workflows/milestone-audit.md +155 -0
  200. package/workflows/milestone-complete.md +167 -0
  201. package/workflows/milestone-release.md +82 -0
  202. package/workflows/odyssey-base-codex.md +305 -0
  203. package/workflows/odyssey-base.md +256 -0
  204. package/workflows/overlays.md +109 -0
  205. package/workflows/plan.md +520 -0
  206. package/workflows/quick.md +350 -0
  207. package/workflows/ralph-amend-goal.md +177 -0
  208. package/workflows/refactor.md +87 -0
  209. package/workflows/retrospective.md +471 -0
  210. package/workflows/review.md +448 -0
  211. package/workflows/roadmap-common.md +193 -0
  212. package/workflows/roadmap.md +106 -0
  213. package/workflows/shell-exec-protocol.md +30 -0
  214. package/workflows/skill-authoring.md +265 -0
  215. package/workflows/spec-generate.md +475 -0
  216. package/workflows/specs-add.md +123 -0
  217. package/workflows/specs-load.md +76 -0
  218. package/workflows/specs-remove.md +104 -0
  219. package/workflows/specs-setup.md +316 -0
  220. package/workflows/status.md +149 -0
  221. package/workflows/sync.md +116 -0
  222. package/workflows/tdd.md +255 -0
  223. package/workflows/test-gen.md +226 -0
  224. package/workflows/test.md +385 -0
  225. package/workflows/tools-spec.md +70 -0
  226. package/workflows/ui-codify-extract.md +372 -0
  227. package/workflows/ui-codify-knowhow.md +258 -0
  228. package/workflows/ui-codify-package.md +159 -0
  229. package/workflows/ui-codify.md +227 -0
  230. package/workflows/ui-design.md +393 -0
  231. package/workflows/ui-style.md +201 -0
  232. package/workflows/verify.md +557 -0
  233. package/workflows/wiki-connect.md +153 -0
  234. package/workflows/wiki-digest.md +180 -0
  235. package/workflows/wiki-manage.md +113 -0
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  name: maestro
3
3
  description: "Auto-route intent to optimal command chain Arguments: <intent> [-y] [-c] [--dry-run] [--super]"
4
- allowed-tools: Read Write Edit Bash Glob Grep Agent AskUserQuestion TodoWrite
4
+ allowed-tools: Read Write Edit Bash Glob Grep teammate maestro
5
5
  ---
6
6
 
7
7
  <purpose>
@@ -10,8 +10,8 @@ Session: `.workflow/.maestro/{session_id}/status.json`.
10
10
  </purpose>
11
11
 
12
12
  <deferred_reading>
13
- - [maestro.md](~/.maestro/workflows/maestro.md) — read at execution start for intent analysis + chain selection
14
- - [maestro-super.md](~/.maestro/workflows/maestro-super.md) — read when `--super` flag active
13
+ - [maestro.md](~/.pi/agent/packages/pi-maestro-flow/workflows/maestro.md) — read at execution start for intent analysis + chain selection
14
+ - [maestro-super.md](~/.pi/agent/packages/pi-maestro-flow/workflows/maestro-super.md) — read when `--super` flag active
15
15
  </deferred_reading>
16
16
 
17
17
  <context>
@@ -95,10 +95,10 @@ S_CONFIRM:
95
95
  → END WHEN: user cancels
96
96
 
97
97
  S_DISPATCH:
98
- → END DO: Skill({ skill: "maestro-ralph-execute" })
98
+ → END DO: invoke /skill: "maestro-ralph-execute" })
99
99
 
100
100
  S_FALLBACK:
101
- → S_CLASSIFY WHEN: user provides new intent DO: AskUserQuestion
101
+ → S_CLASSIFY WHEN: user provides new intent DO: user prompt
102
102
  → END WHEN: user cancels
103
103
 
104
104
  </transitions>
@@ -117,7 +117,7 @@ S_FALLBACK:
117
117
 
118
118
  ### A_CLASSIFY_INTENT
119
119
 
120
- 1. Read `~/.maestro/workflows/maestro.md` from deferred_reading
120
+ 1. Read `~/.pi/agent/packages/pi-maestro-flow/workflows/maestro.md` from deferred_reading
121
121
  2. Match intent to task_type via chain catalog (semantic)
122
122
  3. Select chain from chainMap,遵循拓扑约束:
123
123
  - 压力测试/拷问/验证假设/grill/stress-test → `grill`(**-y 模式透传 `-y` 到 grill,grill 以 Auto mode 执行,不跳过**)
@@ -133,7 +133,7 @@ S_FALLBACK:
133
133
 
134
134
  ### A_CLARIFY
135
135
 
136
- 1. `AskUserQuestion` with parsed intent + available chain options
136
+ 1. `user prompt` with parsed intent + available chain options
137
137
  2. Re-classify with user response
138
138
 
139
139
  ### A_DECOMPOSE_TASKS
@@ -141,7 +141,7 @@ S_FALLBACK:
141
141
  设 `session.decomposition_owner = "maestro"`。下游 ralph 只消费不二次提问(invariant 4)。Condensed:
142
142
 
143
143
  1. 分类意图广度。narrow / 单步 / `{status,init,quick}` 链跳过
144
- 2. broad/medium → `AskUserQuestion` ≤3 轮:Scope / Constraints / Definition of Done
144
+ 2. broad/medium → `user prompt` ≤3 轮:Scope / Constraints / Definition of Done
145
145
  3. 派生 `execution_criteria` + `task_decomposition`(每个 sub-goal 含 `done_when` + `evidence` + `lifecycle` + `completion_confirmed: false`)
146
146
  4. **status.json 唯一真源**:写入 `boundary_contract` / `execution_criteria` / `task_decomposition`;不生成 markdown 清单
147
147
  5. 在最后一个 evidence-producing stage(execute/review/test)之后、`milestone-complete` 之前追加 `decision:post-goal-audit`。ralph-execute 在该节点按需动态生长 `steps[]`
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  name: maestro-amend
3
3
  description: "Generate overlays to fix workflow command deficiencies Arguments: [description] [--from-verify <dir>] [--from-review <dir>] [--from-session <id>] [--from-issues ISS-xxx,...] [--scan] [--dry-run] [-y]"
4
- allowed-tools: Read Write Bash Glob Grep AskUserQuestion
4
+ allowed-tools: Read Write Bash Glob Grep maestro
5
5
  ---
6
6
 
7
7
  <purpose>
@@ -9,8 +9,8 @@ Signal-driven overlay generator — collect workflow deficiency signals from mul
9
9
  </purpose>
10
10
 
11
11
  <required_reading>
12
- @~/.maestro/workflows/overlays.md
13
- @~/.maestro/cli-tools.json
12
+ ~/.pi/agent/packages/pi-maestro-flow/workflows/overlays.md
13
+ ~/.maestro/cli-tools.json
14
14
  </required_reading>
15
15
 
16
16
  <context>
@@ -27,7 +27,7 @@ $ARGUMENTS — optional description and/or source flags.
27
27
  | `--scan` | Auto-scan .workflow/ | Discover all workflow-related signals |
28
28
  | _(positional text)_ | User description | Direct observation |
29
29
 
30
- Multiple combinable. No flags + no description → interactive (scan + AskUserQuestion).
30
+ Multiple combinable. No flags + no description → interactive (scan + user prompt).
31
31
 
32
32
  **Control**: `--dry-run` (preview, don't install), `-y` (skip confirmations)
33
33
 
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  name: maestro-analyze
3
3
  description: "Use when a topic needs structured multi-dimensional investigation before planning or decision-making Arguments: [milestone|topic] [-y] [-c] [-q] [--gaps [ISS-ID]]"
4
- allowed-tools: Read Write Edit Bash Glob Grep Agent AskUserQuestion
4
+ allowed-tools: Read Write Edit Bash Glob Grep teammate maestro
5
5
  ---
6
6
 
7
7
  <purpose>
@@ -9,13 +9,13 @@ Multi-dimensional analysis of a proposal, decision, or architecture choice via C
9
9
  </purpose>
10
10
 
11
11
  <required_reading>
12
- @~/.maestro/workflows/analyze.md
12
+ ~/.pi/agent/packages/pi-maestro-flow/workflows/analyze.md
13
13
  </required_reading>
14
14
 
15
15
  <deferred_reading>
16
- - [state.json](~/.maestro/templates/state.json) — read when registering artifact
17
- - [issue-gaps-analyze.md](~/.maestro/workflows/issue-gaps-analyze.md) — read when --gaps is triggered
18
- - [boundary-grill.md](~/.maestro/workflows/boundary-grill.md) — read when boundary conflicts detected (between Phase 4 and Phase 5)
16
+ - [state.json](~/.pi/agent/packages/pi-maestro-flow/templates/state.json) — read when registering artifact
17
+ - [issue-gaps-analyze.md](~/.pi/agent/packages/pi-maestro-flow/workflows/issue-gaps-analyze.md) — read when --gaps is triggered
18
+ - [boundary-grill.md](~/.pi/agent/packages/pi-maestro-flow/workflows/boundary-grill.md) — read when boundary conflicts detected (between Phase 4 and Phase 5)
19
19
  </deferred_reading>
20
20
 
21
21
  <context>
@@ -64,7 +64,7 @@ Output directory format, artifact registration schema, and output artifact listi
64
64
  </context>
65
65
 
66
66
  <interview_protocol>
67
- Follows @~/.maestro/workflows/interview-mechanics.md standard.
67
+ Follows ~/.pi/agent/packages/pi-maestro-flow/workflows/interview-mechanics.md standard.
68
68
 
69
69
  **Interaction mode**: convergent menu-driven
70
70
  **Decision tree** (strict order): scope (phase / topic / milestone-wide / adhoc / --gaps) → depth (quick / standard / deep) → dimensions (which of the 6 to keep) → Go/No-Go threshold
@@ -76,11 +76,11 @@ Follows @~/.maestro/workflows/interview-mechanics.md standard.
76
76
  </interview_protocol>
77
77
 
78
78
  <execution>
79
- Follow '~/.maestro/workflows/analyze.md' completely.
79
+ Follow '~/.pi/agent/packages/pi-maestro-flow/workflows/analyze.md' completely.
80
80
 
81
81
  ### --gaps Mode
82
82
 
83
- When `--gaps` is present, follow `~/.maestro/workflows/issue-gaps-analyze.md` instead of the standard pipeline.
83
+ When `--gaps` is present, follow `~/.pi/agent/packages/pi-maestro-flow/workflows/issue-gaps-analyze.md` instead of the standard pipeline.
84
84
  </execution>
85
85
 
86
86
  <completion>
@@ -125,7 +125,7 @@ Status verdicts:
125
125
 
126
126
  ### Session seal
127
127
 
128
- @~/.maestro/workflows/finish-work.md — SESSION_DIR=OUTPUT_DIR, SESSION_TYPE=analyze, SESSION_ID={artifact_id}, LINKED_MILESTONE={target_milestone or null}
128
+ ~/.pi/agent/packages/pi-maestro-flow/workflows/finish-work.md — SESSION_DIR=OUTPUT_DIR, SESSION_TYPE=analyze, SESSION_ID={artifact_id}, LINKED_MILESTONE={target_milestone or null}
129
129
  </completion>
130
130
 
131
131
  <error_codes>
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  name: maestro-blueprint
3
3
  description: "Generate formal specification package (Product Brief, PRD, Architecture, Epics) through 6-phase document chain Arguments: <idea or @file> [-y] [-c] [--from <source>]"
4
- allowed-tools: Read Write Edit Bash Glob Grep Agent AskUserQuestion
4
+ allowed-tools: Read Write Edit Bash Glob Grep teammate maestro
5
5
  ---
6
6
 
7
7
  <purpose>
@@ -11,11 +11,11 @@ Pipeline: brainstorm (optional) → **blueprint** → analyze / roadmap / plan.
11
11
  </purpose>
12
12
 
13
13
  <required_reading>
14
- @~/.maestro/workflows/blueprint.md
14
+ ~/.pi/agent/packages/pi-maestro-flow/workflows/blueprint.md
15
15
  </required_reading>
16
16
 
17
17
  <deferred_reading>
18
- - [blueprint-config.json](~/.maestro/templates/blueprint-config.json) — read when initializing blueprint configuration
18
+ - [blueprint-config.json](~/.pi/agent/packages/pi-maestro-flow/templates/blueprint-config.json) — read when initializing blueprint configuration
19
19
  </deferred_reading>
20
20
 
21
21
  <context>
@@ -46,7 +46,7 @@ $ARGUMENTS -- idea text, @file reference, or upstream context source.
46
46
  </context>
47
47
 
48
48
  <interview_protocol>
49
- Follows @~/.maestro/workflows/interview-mechanics.md standard.
49
+ Follows ~/.pi/agent/packages/pi-maestro-flow/workflows/interview-mechanics.md standard.
50
50
 
51
51
  **Interaction mode**: convergent menu-driven, depth-first
52
52
  **Decision tree** (strict depth-first): scope (full product / feature set / single feature) → spec type (service / api / library / platform) → focus areas → whether to run codebase exploration → requirement priorities
@@ -57,7 +57,7 @@ Follows @~/.maestro/workflows/interview-mechanics.md standard.
57
57
  </interview_protocol>
58
58
 
59
59
  <execution>
60
- Follow `~/.maestro/workflows/blueprint.md` completely.
60
+ Follow `~/.pi/agent/packages/pi-maestro-flow/workflows/blueprint.md` completely.
61
61
 
62
62
  ### Phase chain
63
63
 
@@ -151,9 +151,9 @@ Status verdicts:
151
151
  - [ ] Readiness gate: Pass (>=80%) or Review (>=60%) with documented caveats
152
152
  - [ ] Artifact registered in state.json (type=blueprint)
153
153
  - [ ] context-package.json generated for downstream consumption
154
- - [ ] On gate Pass/Review: session sealed via finish-work (finish-work.md includes AskUserQuestion confirmation before state.json artifact registration and optional spec/knowhow extraction). On Fail: skip — session stays active, excluded from wiki search.
154
+ - [ ] On gate Pass/Review: session sealed via finish-work (finish-work.md includes user prompt confirmation before state.json artifact registration and optional spec/knowhow extraction). On Fail: skip — session stays active, excluded from wiki search.
155
155
  </success_criteria>
156
156
 
157
157
  <on_complete>
158
- @~/.maestro/workflows/finish-work.md — SESSION_DIR={session_dir}, SESSION_TYPE=blueprint, SESSION_ID={session_id}, LINKED_MILESTONE=null
158
+ ~/.pi/agent/packages/pi-maestro-flow/workflows/finish-work.md — SESSION_DIR={session_dir}, SESSION_TYPE=blueprint, SESSION_ID={session_id}, LINKED_MILESTONE=null
159
159
  </on_complete>
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  name: maestro-brainstorm
3
3
  description: "Use when exploring ideas, evaluating approaches, or needing multi-perspective analysis before implementation Arguments: [topic|role-name] [--yes] [--count N] [--session ID] [--update] [--skip-questions] [--include-questions] [--style-skill PKG] [--review-only] [--from <source>]"
4
- allowed-tools: Read Write Edit Bash Glob Grep Agent AskUserQuestion
4
+ allowed-tools: Read Write Edit Bash Glob Grep teammate maestro
5
5
  ---
6
6
 
7
7
  <purpose>
@@ -11,14 +11,14 @@ Pipeline: grill (optional) → **brainstorm** → roadmap / analyze / blueprint.
11
11
  </purpose>
12
12
 
13
13
  <required_reading>
14
- @~/.maestro/workflows/brainstorm.md
14
+ ~/.pi/agent/packages/pi-maestro-flow/workflows/brainstorm.md
15
15
  </required_reading>
16
16
 
17
17
  <deferred_reading>
18
- - [scratch-index.json](~/.maestro/templates/scratch-index.json) — read when operating in scratch mode
19
- - [index.json](~/.maestro/templates/index.json) — read when operating in phase mode
20
- - [brainstorm-visualize.md](~/.maestro/workflows/brainstorm-visualize.md) — read when html-prototypes/ produced and user wants to browse them
21
- - [boundary-grill.md](~/.maestro/workflows/boundary-grill.md) — read when boundary conflicts detected (in cross-role review)
18
+ - [scratch-index.json](~/.pi/agent/packages/pi-maestro-flow/templates/scratch-index.json) — read when operating in scratch mode
19
+ - [index.json](~/.pi/agent/packages/pi-maestro-flow/templates/index.json) — read when operating in phase mode
20
+ - [brainstorm-visualize.md](~/.pi/agent/packages/pi-maestro-flow/workflows/brainstorm-visualize.md) — read when html-prototypes/ produced and user wants to browse them
21
+ - [boundary-grill.md](~/.pi/agent/packages/pi-maestro-flow/workflows/boundary-grill.md) — read when boundary conflicts detected (in cross-role review)
22
22
  </deferred_reading>
23
23
 
24
24
  <context>
@@ -57,7 +57,7 @@ $ARGUMENTS -- topic text for auto mode, or role name for single role mode.
57
57
  </context>
58
58
 
59
59
  <interview_protocol>
60
- Follows @~/.maestro/workflows/interview-mechanics.md standard.
60
+ Follows ~/.pi/agent/packages/pi-maestro-flow/workflows/interview-mechanics.md standard.
61
61
 
62
62
  **Interaction mode**: convergent menu-driven
63
63
  **Decision tree** (flexible order — user may jump between branches): mode (auto / single-role / review-only) → role selection and --count → --from upstream source (grill:ID, blueprint:ID, @file, path) → whether to enable design-research and DESIGN.md sub-pipeline
@@ -68,7 +68,7 @@ Follows @~/.maestro/workflows/interview-mechanics.md standard.
68
68
  </interview_protocol>
69
69
 
70
70
  <execution>
71
- Follow '~/.maestro/workflows/brainstorm.md' completely.
71
+ Follow '~/.pi/agent/packages/pi-maestro-flow/workflows/brainstorm.md' completely.
72
72
 
73
73
  ### Phase Gates (MANDATORY, BLOCKING)
74
74
 
@@ -134,7 +134,7 @@ Status verdicts:
134
134
  | Quick roadmap needed | `/maestro-roadmap --from brainstorm:{artifact_id}` |
135
135
  | Need deeper analysis first | `/maestro-analyze {topic} --from brainstorm:{artifact_id}` |
136
136
  | Need stress-testing first | `/maestro-grill {topic}` |
137
- | `html-prototypes/` produced with 2+ files and user wants to browse | Load `~/.maestro/workflows/brainstorm-visualize.md` and launch visualizer server |
137
+ | `html-prototypes/` produced with 2+ files and user wants to browse | Load `~/.pi/agent/packages/pi-maestro-flow/workflows/brainstorm-visualize.md` and launch visualizer server |
138
138
  | DESIGN.md established during Step 3.5 | `/maestro-impeccable build <feature-description>` |
139
139
 
140
140
  **Single role mode:**
@@ -189,5 +189,5 @@ Status verdicts:
189
189
  </success_criteria>
190
190
 
191
191
  <on_complete>
192
- @~/.maestro/workflows/finish-work.md — SESSION_DIR={output_dir}, SESSION_TYPE=brainstorm, SESSION_ID={artifact_id}, LINKED_MILESTONE=null
192
+ ~/.pi/agent/packages/pi-maestro-flow/workflows/finish-work.md — SESSION_DIR={output_dir}, SESSION_TYPE=brainstorm, SESSION_ID={artifact_id}, LINKED_MILESTONE=null
193
193
  </on_complete>
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  name: maestro-collab
3
3
  description: "Use when a question needs cross-verification from multiple CLI tools or diverse analytical perspectives Arguments: <requirement> [--tools agy,qwen,claude] [--mode analysis|write] [--rule <template>] [-y]"
4
- allowed-tools: Read Write Bash Glob Grep Agent AskUserQuestion
4
+ allowed-tools: Read Write Bash Glob Grep teammate maestro
5
5
  ---
6
6
 
7
7
  <purpose>
@@ -45,7 +45,7 @@ S_REPORT — 显示摘要 + next-step routing PERSIST:
45
45
 
46
46
  S_PARSE:
47
47
  → S_DISCOVER WHEN: requirement non-empty DO: extract requirement, tools, mode, rule, autoYes
48
- → S_PARSE WHEN: requirement empty DO: AskUserQuestion for requirement
48
+ → S_PARSE WHEN: requirement empty DO: user prompt for requirement
49
49
 
50
50
  S_DISCOVER:
51
51
  → S_CONFIRM WHEN: eligible tools >= 2 DO: A_DISCOVER_TOOLS
@@ -79,7 +79,7 @@ S_SYNTHESIZE:
79
79
  S_REGISTER:
80
80
  → S_REPORT WHEN: user confirms or -y DO: append CLB artifact to state.json (type: collab, scope: adhoc)
81
81
  → S_REPORT WHEN: user declines DO: skip artifact registration, proceed to report
82
- GUARD: AskUserQuestion "Register collab artifact to state.json?" (skipped if -y)
82
+ GUARD: user prompt "Register collab artifact to state.json?" (skipped if -y)
83
83
 
84
84
  S_REPORT:
85
85
  → END DO: display summary (requirement, tools, consensus_level, per-tool status, artifact id, output dir)
@@ -137,7 +137,7 @@ If consensus_level < 40%: W003.
137
137
 
138
138
  ### A_BOUNDARY_GRILL
139
139
 
140
- Run boundary grill per `~/.maestro/workflows/boundary-grill.md`.
140
+ Run boundary grill per `~/.pi/agent/packages/pi-maestro-flow/workflows/boundary-grill.md`.
141
141
  Input: classified CONFLICT findings + per-tool outputs. Check upstream scope if `--from` used.
142
142
  IF conflicts → tag with resolution, feed into A_GENERATE_OUTPUTS. No conflicts → pass through.
143
143
 
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  name: maestro-companion
3
3
  description: "Knowledge companion — load context, record companion doc, capture insights, route to skills Arguments: [before|note|after|route] [--task <description>] [--type <task_type>] [--category <cat>]"
4
- allowed-tools: Read Write Edit Bash Glob Grep Skill AskUserQuestion
4
+ allowed-tools: Read Write Edit Bash Glob Grep maestro
5
5
  ---
6
6
 
7
7
  <purpose>
@@ -439,7 +439,7 @@ Promotable entries:
439
439
 
440
440
  ### 3. Promote entries
441
441
 
442
- If promotable entries exist, AskUserQuestion:
442
+ If promotable entries exist, user prompt:
443
443
 
444
444
  - Option 1: "Promote to spec" — short coding/arch/test constraint
445
445
  - Option 2: "Promote to knowhow" — detailed recipe/template/decision/tip
@@ -517,7 +517,7 @@ Delegates intent routing to maestro-next, which recommends the best single comma
517
517
  - [ ] note: typed entries cross-posted to matching context tables (decisions→Decisions, hypothesis→Hypotheses, etc.)
518
518
  - [ ] after: companion doc entries reviewed and promotable items identified
519
519
  - [ ] after: outcome fields populated (files_changed, completed, status)
520
- - [ ] after: AskUserQuestion routes to spec-add or manage-knowhow-capture
520
+ - [ ] after: user prompt routes to spec-add or manage-knowhow-capture
521
521
  - [ ] after: todo entries extracted to follow_up field
522
522
  - [ ] after: companion doc marked completed, active pointer cleared
523
523
  - [ ] after: accumulation reminder + next-step routing displayed
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  name: maestro-composer
3
3
  description: "Compose reusable workflow templates from natural language Arguments: <workflow-description> [--resume] [--edit <template-path>]"
4
- allowed-tools: Read Write Edit Bash Glob Grep Agent AskUserQuestion Skill
4
+ allowed-tools: Read Write Edit Bash Glob Grep teammate maestro
5
5
  ---
6
6
 
7
7
  <purpose>
@@ -10,8 +10,8 @@ Three modes: new design (default), resume (`--resume`), edit (`--edit <path>`).
10
10
  </purpose>
11
11
 
12
12
  <deferred_reading>
13
- - [node-catalog](~/.maestro/templates/workflows/specs/node-catalog.md) — read at Phase 2 (Resolve)
14
- - [template-schema](~/.maestro/templates/workflows/specs/template-schema.md) — read at Phase 5 (Persist)
13
+ - [node-catalog](~/.pi/agent/packages/pi-maestro-flow/templates/workflows/specs/node-catalog.md) — read at Phase 2 (Resolve)
14
+ - [template-schema](~/.pi/agent/packages/pi-maestro-flow/templates/workflows/specs/template-schema.md) — read at Phase 5 (Persist)
15
15
  </deferred_reading>
16
16
 
17
17
  <context>
@@ -20,8 +20,8 @@ $ARGUMENTS — natural language description, or flags.
20
20
  **Flags**: `--resume` (resume in-progress design), `--edit <path>` (edit existing template)
21
21
 
22
22
  **Constants**:
23
- - Template dir: `~/.maestro/templates/workflows/`
24
- - Template index: `~/.maestro/templates/workflows/index.json`
23
+ - Template dir: `~/.pi/agent/packages/pi-maestro-flow/templates/workflows/`
24
+ - Template index: `~/.pi/agent/packages/pi-maestro-flow/templates/workflows/index.json`
25
25
  - Design drafts: `.workflow/templates/design-drafts/`
26
26
  - Template ID: `wft-<slug>-<YYYYMMDD>`, Node ID: `N-<seq>`, Checkpoint: `CP-<seq>`
27
27
  - Max nodes: 20
@@ -31,14 +31,14 @@ $ARGUMENTS — natural language description, or flags.
31
31
  2. **Coding specs**: Run `maestro load --type spec --category coding` to load coding conventions. Informs executor argument defaults and context injection.
32
32
  3. Optional — proceed without if unavailable.
33
33
 
34
- **Output boundary**: ALL file writes MUST target `~/.maestro/templates/workflows/` (template JSON + index.json) and `.workflow/templates/design-drafts/` (intermediate drafts) only. NEVER modify source code or `.claude/commands/` files.
34
+ **Output boundary**: ALL file writes MUST target `~/.pi/agent/packages/pi-maestro-flow/templates/workflows/` (template JSON + index.json) and `.workflow/templates/design-drafts/` (intermediate drafts) only. NEVER modify source code or `.claude/commands/` files.
35
35
  </context>
36
36
 
37
37
  <invariants>
38
38
  1. **Max 20 nodes** — workflow templates MUST NOT exceed 20 nodes; larger workflows MUST be split into sub-workflows
39
39
  2. **Acyclic DAG** — generated template MUST be a directed acyclic graph; cycles MUST be detected and rejected before persistence
40
40
  3. **No orphan nodes** — every node MUST be reachable from at least one edge; unreachable nodes MUST be flagged
41
- 4. **Confirmation before write** — template JSON MUST be shown to user via AskUserQuestion before writing to `~/.maestro/templates/workflows/`; cancellation saves draft only
41
+ 4. **Confirmation before write** — template JSON MUST be shown to user via user prompt before writing to `~/.pi/agent/packages/pi-maestro-flow/templates/workflows/`; cancellation saves draft only
42
42
  5. **Draft preservation** — abandoning at any confirmation gate MUST save current progress to design-drafts directory; NEVER discard user's partial work
43
43
  6. **Deferred reading only** — node-catalog and template-schema MUST be read at their designated phases (P2, P5), NEVER loaded eagerly at startup
44
44
  </invariants>
@@ -98,7 +98,7 @@ S_PERSIST:
98
98
 
99
99
  ### A_PARSE_INTENT
100
100
 
101
- 1. Parse description (if empty: AskUserQuestion for workflow description)
101
+ 1. Parse description (if empty: user prompt for workflow description)
102
102
  2. Extract candidate nodes via semantic signals:
103
103
 
104
104
  | Signal | Type hint |
@@ -156,8 +156,8 @@ Write `nodes.json`. Display resolved node list.
156
156
 
157
157
  Read deferred `template-schema.md` (fallback to built-in structure).
158
158
  Assemble template JSON: template_id, name, nodes, edges, checkpoints, context_schema, execution_mode.
159
- **Confirmation gate**: AskUserQuestion showing template summary (ID, node count, variables) before writing.
160
- - User confirms → write to `~/.maestro/templates/workflows/<slug>.json` and update index.json.
159
+ **Confirmation gate**: user prompt showing template summary (ID, node count, variables) before writing.
160
+ - User confirms → write to `~/.pi/agent/packages/pi-maestro-flow/templates/workflows/<slug>.json` and update index.json.
161
161
  - User cancels → save draft, do not write template or index.
162
162
  Display: path, ID, node count, variables, execute/edit commands. Clean up draft dir.
163
163
 
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  name: maestro-execute
3
3
  description: "Use when a confirmed plan is ready for implementation Arguments: [milestone] [--auto-commit] [--method agent|cli|auto] [--executor <tool>] [--dir <path>] [-y]"
4
- allowed-tools: Read Write Edit Bash Glob Grep Agent AskUserQuestion
4
+ allowed-tools: Read Write Edit Bash Glob Grep teammate maestro
5
5
  ---
6
6
 
7
7
  <purpose>
@@ -10,12 +10,12 @@ Consumes plan from maestro-plan; registers EXC artifact in state.json.
10
10
  </purpose>
11
11
 
12
12
  <required_reading>
13
- @~/.maestro/workflows/execute.md
13
+ ~/.pi/agent/packages/pi-maestro-flow/workflows/execute.md
14
14
  </required_reading>
15
15
 
16
16
  <deferred_reading>
17
- - [task.json](~/.maestro/templates/task.json) — read when reading task definitions
18
- - [state.json](~/.maestro/templates/state.json) — read when registering artifact
17
+ - [task.json](~/.pi/agent/packages/pi-maestro-flow/templates/task.json) — read when reading task definitions
18
+ - [state.json](~/.pi/agent/packages/pi-maestro-flow/templates/state.json) — read when registering artifact
19
19
  </deferred_reading>
20
20
 
21
21
  <context>
@@ -26,7 +26,7 @@ $ARGUMENTS — milestone number, or no args for current milestone, with optional
26
26
  | Flag | Effect | Default |
27
27
  |------|--------|---------|
28
28
  | `--auto-commit` | Auto-commit after each completed task | false |
29
- | `--method agent\|cli\|auto` | Execution method: Agent tool, CLI delegate, or auto-select | `auto` |
29
+ | `--method agent\|cli\|auto` | Execution method: teammate tool, CLI delegate, or auto-select | `auto` |
30
30
  | `--executor <tool>` | Explicit executor tool for CLI delegate mode | First enabled in config |
31
31
  | `--dir <path>` | Execute a specific plan directory instead of auto-discovery | — |
32
32
  | `-y` / `--yes` | Auto mode — skip ALL interactive questions (executor selection, wave progression, blocked prompts) | false |
@@ -63,7 +63,7 @@ Bash("maestro collab preflight --phase <phase-number>")
63
63
  ```
64
64
  If exit code is 1, present warnings and ask whether to proceed.
65
65
 
66
- Follow '~/.maestro/workflows/execute.md' completely.
66
+ Follow '~/.pi/agent/packages/pi-maestro-flow/workflows/execute.md' completely.
67
67
 
68
68
  ### Phase Gates (MANDATORY, BLOCKING)
69
69
 
@@ -82,7 +82,7 @@ Follow '~/.maestro/workflows/execute.md' completely.
82
82
  - IF all tasks in a wave failed: halt wave progression, report E005 with per-task failure reasons. Do NOT proceed to next wave — downstream waves depend on current wave outputs.
83
83
  - IF cascading failure (wave N fails → wave N+1 has unmet dependencies): mark all dependent tasks in subsequent waves as `blocked` with reason `"upstream_wave_failed"`. Skip blocked waves and proceed to completion with partial results.
84
84
  - `-y` mode: auto-skip blocked waves without prompting, log warning W002.
85
- - Non `-y` mode: `AskUserQuestion` with options [retry wave / skip and continue / abort execution].
85
+ - Non `-y` mode: `user prompt` with options [retry wave / skip and continue / abort execution].
86
86
 
87
87
  **GATE 3: All Tasks → Completion**
88
88
  - REQUIRED: All waves executed in dependency order (or explicitly skipped via Gate 2.5).
@@ -127,7 +127,7 @@ For each completed/failed TASK with issue_id:
127
127
  all task_refs completed → proposed issue.status = "resolved"
128
128
  any task_ref failed → proposed issue.status = "in_progress"
129
129
  IF NOT auto_mode (-y):
130
- AskUserQuestion: "Update issue {issue_id} status to {proposed_status}?" [Yes / Skip]
130
+ user prompt: "Update issue {issue_id} status to {proposed_status}?" [Yes / Skip]
131
131
  IF Skip → continue to next task without writing
132
132
  Append history entry: { action: "executed", at: <ISO>, by: "maestro-execute", summary: "TASK-{NNN} {status}" }
133
133
  Write updated issue back to issues.jsonl
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  name: maestro-fork
3
3
  description: "Create or sync milestone worktree for parallel dev Arguments: -m <milestone-number> [--base <branch>] [--sync]"
4
- allowed-tools: Read Write Edit Bash Glob Grep Agent AskUserQuestion
4
+ allowed-tools: Read Write Edit Bash Glob Grep teammate maestro
5
5
  ---
6
6
 
7
7
  <purpose>
@@ -10,12 +10,12 @@ Supports `--sync` mode to pull latest main changes into an active worktree.
10
10
  </purpose>
11
11
 
12
12
  <required_reading>
13
- @~/.maestro/workflows/fork.md
13
+ ~/.pi/agent/packages/pi-maestro-flow/workflows/fork.md
14
14
  </required_reading>
15
15
 
16
16
  <deferred_reading>
17
- - [worktrees.json](~/.maestro/templates/worktrees.json) — read when updating registry
18
- - [worktree-scope.json](~/.maestro/templates/worktree-scope.json) — read when writing scope marker
17
+ - [worktrees.json](~/.pi/agent/packages/pi-maestro-flow/templates/worktrees.json) — read when updating registry
18
+ - [worktree-scope.json](~/.pi/agent/packages/pi-maestro-flow/templates/worktree-scope.json) — read when writing scope marker
19
19
  </deferred_reading>
20
20
 
21
21
  <context>
@@ -25,7 +25,7 @@ Modes (`Fork` / `Sync`), flags (`-m`, `--base`, `--sync`), milestone resolution,
25
25
  </context>
26
26
 
27
27
  <execution>
28
- Follow '~/.maestro/workflows/fork.md' completely.
28
+ Follow '~/.pi/agent/packages/pi-maestro-flow/workflows/fork.md' completely.
29
29
 
30
30
  Fork and sync algorithm steps are defined in workflow `fork.md`.
31
31
 
@@ -45,7 +45,7 @@ Fork and sync algorithm steps are defined in workflow `fork.md`.
45
45
  - BLOCKED if missing: worktree creation failed or shared files not copied — do not proceed to artifact scoping.
46
46
 
47
47
  **GATE 3: Artifact Copy → Completion**
48
- - REQUIRED: AskUserQuestion confirmation before registry writes — show milestone scope, worktree path, and state entries to be written. User must confirm or abort.
48
+ - REQUIRED: user prompt confirmation before registry writes — show milestone scope, worktree path, and state entries to be written. User must confirm or abort.
49
49
  - REQUIRED: `worktree-scope.json` written with milestone scope (after confirmation).
50
50
  - REQUIRED: Scoped `state.json` written (only this milestone's artifacts) (after confirmation).
51
51
  - REQUIRED: `worktrees.json` registry updated in main worktree (after confirmation).
@@ -67,7 +67,7 @@ Fork and sync algorithm steps are defined in workflow `fork.md`.
67
67
  |-----------|-----------|
68
68
  | Fork complete | `cd {wt.path} && /maestro-analyze` |
69
69
  | Fork + automated | `maestro delegate "run full lifecycle for milestone" --cd {wt.path} --mode write` |
70
- | Fork + status check | Skill({ skill: "manage-status" }) |
70
+ | Fork + status check | invoke /skill: "manage-status" }) |
71
71
  | Sync complete | Resume work in worktree |
72
72
  | Sync conflicts found | Resolve manually, then retry |
73
73
  </completion>
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  name: maestro-grill
3
3
  description: "Use when stress-testing a plan, idea, or requirement against codebase reality before brainstorming Arguments: <topic|plan> [-y] [-c] [--from <source>] [--depth shallow|standard|deep]"
4
- allowed-tools: Read Write Edit Bash Glob Grep Agent AskUserQuestion
4
+ allowed-tools: Read Write Edit Bash Glob Grep teammate maestro
5
5
  ---
6
6
 
7
7
  <purpose>
@@ -11,11 +11,11 @@ Pipeline position: BEFORE brainstorm (stress-test → then elaborate).
11
11
  </purpose>
12
12
 
13
13
  <required_reading>
14
- @~/.maestro/workflows/grill.md
14
+ ~/.pi/agent/packages/pi-maestro-flow/workflows/grill.md
15
15
  </required_reading>
16
16
 
17
17
  <deferred_reading>
18
- - [state.json](~/.maestro/templates/state.json) — read when registering artifact
18
+ - [state.json](~/.pi/agent/packages/pi-maestro-flow/templates/state.json) — read when registering artifact
19
19
  </deferred_reading>
20
20
 
21
21
  <context>
@@ -47,7 +47,7 @@ $ARGUMENTS -- topic/plan text for interactive mode, or --from source for upstrea
47
47
  </context>
48
48
 
49
49
  <interview_protocol>
50
- Follows @~/.maestro/workflows/interview-mechanics.md standard.
50
+ Follows ~/.pi/agent/packages/pi-maestro-flow/workflows/interview-mechanics.md standard.
51
51
 
52
52
  **Interaction mode override**: adversarial Socratic — NOT menu-driven
53
53
  **Question style**:
@@ -62,7 +62,7 @@ Follows @~/.maestro/workflows/interview-mechanics.md standard.
62
62
  </interview_protocol>
63
63
 
64
64
  <execution>
65
- Follow '~/.maestro/workflows/grill.md' completely.
65
+ Follow '~/.pi/agent/packages/pi-maestro-flow/workflows/grill.md' completely.
66
66
 
67
67
  ### Phase Gates (MANDATORY, BLOCKING)
68
68
 
@@ -116,11 +116,11 @@ Status verdicts:
116
116
 
117
117
  | Condition | Suggestion |
118
118
  |-----------|-----------|
119
- | Need multi-role elaboration | `Skill({ skill: "maestro-brainstorm", args: "{topic} --from grill:{artifact_id}" })` |
120
- | Need deep technical analysis | `Skill({ skill: "maestro-analyze", args: "{topic} --from grill:{artifact_id}" })` |
121
- | Scope is clear, ready for roadmap | `Skill({ skill: "maestro-roadmap", args: "--from grill:{artifact_id}" })` |
122
- | Need formal spec package | `Skill({ skill: "maestro-blueprint", args: "--from grill:{artifact_id}" })` |
123
- | More branches to walk | `Skill({ skill: "maestro-grill", args: "{topic} -c" })` |
119
+ | Need multi-role elaboration | `invoke /skill: "maestro-brainstorm", args: "{topic} --from grill:{artifact_id}" })` |
120
+ | Need deep technical analysis | `invoke /skill: "maestro-analyze", args: "{topic} --from grill:{artifact_id}" })` |
121
+ | Scope is clear, ready for roadmap | `invoke /skill: "maestro-roadmap", args: "--from grill:{artifact_id}" })` |
122
+ | Need formal spec package | `invoke /skill: "maestro-blueprint", args: "--from grill:{artifact_id}" })` |
123
+ | More branches to walk | `invoke /skill: "maestro-grill", args: "{topic} -c" })` |
124
124
  </completion>
125
125
 
126
126
  <error_codes>
@@ -143,9 +143,9 @@ Status verdicts:
143
143
  - [ ] Risk register captures all unresolved tensions
144
144
  - [ ] `context-package.json` generated with schema "context-package/1.0"
145
145
  - [ ] Artifact registered in state.json (type=grill, id=GRL-xxx)
146
- - [ ] Session sealed via finish-work (finish-work.md includes AskUserQuestion confirmation before state.json artifact registration and optional spec/knowhow extraction)
146
+ - [ ] Session sealed via finish-work (finish-work.md includes user prompt confirmation before state.json artifact registration and optional spec/knowhow extraction)
147
147
  </success_criteria>
148
148
 
149
149
  <on_complete>
150
- @~/.maestro/workflows/finish-work.md — SESSION_DIR={output_dir}, SESSION_TYPE=grill, SESSION_ID={artifact_id}, LINKED_MILESTONE=null
150
+ ~/.pi/agent/packages/pi-maestro-flow/workflows/finish-work.md — SESSION_DIR={output_dir}, SESSION_TYPE=grill, SESSION_ID={artifact_id}, LINKED_MILESTONE=null
151
151
  </on_complete>
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  name: maestro-guard
3
3
  description: "Manage editing boundary restrictions Arguments: <on|off|status|allow <path>|deny <path>>"
4
- allowed-tools: Read Write Bash Glob
4
+ allowed-tools: Read Write Bash Glob maestro
5
5
  ---
6
6
 
7
7
  <purpose>
@@ -33,7 +33,7 @@ and blocks operations targeting files outside boundaries. Requires hooks level >
33
33
  <invariants>
34
34
  1. **Config-only mutation** — guard MUST only modify the `guard` section of `.workflow/config.json`; NEVER touch other config sections or files
35
35
  2. **Non-destructive** — `off` MUST preserve existing paths and mode; NEVER clear the path list when disabling
36
- 3. **Mode switch confirmation** — switching between allow/deny mode MUST require AskUserQuestion confirmation when existing paths will be cleared
36
+ 3. **Mode switch confirmation** — switching between allow/deny mode MUST require user prompt confirmation when existing paths will be cleared
37
37
  4. **Hook dependency** — guard MUST warn when enabled but `workflow-guard` hook is not active (hooks level < full)
38
38
  5. **Path normalization** — all paths MUST use forward slashes with trailing slash for directories; NEVER store raw backslash paths
39
39
  </invariants>
@@ -52,7 +52,7 @@ and blocks operations targeting files outside boundaries. Requires hooks level >
52
52
 
53
53
  **GATE 3: Execute → Confirm**
54
54
  - REQUIRED: Config mutation applied (for on/off/allow/deny) or status displayed (for status).
55
- - REQUIRED: Mode-switch AskUserQuestion answered (for allow↔deny transitions with existing paths).
55
+ - REQUIRED: Mode-switch user prompt answered (for allow↔deny transitions with existing paths).
56
56
  - BLOCKED if: user declines mode switch.
57
57
 
58
58
  **Step 1: Parse subcommand**
@@ -85,14 +85,14 @@ Read `.workflow/config.json`. If file missing, initialize with empty guard secti
85
85
 
86
86
  **`allow <path>`:**
87
87
  - Normalize path to forward slashes, ensure trailing slash for directories
88
- - If `guard.mode` is `deny`, AskUserQuestion: "Switching from deny to allow mode will clear existing paths ({N} paths). Continue?" — abort if user declines.
88
+ - If `guard.mode` is `deny`, user prompt: "Switching from deny to allow mode will clear existing paths ({N} paths). Continue?" — abort if user declines.
89
89
  - Add path to `guard.paths` (deduplicate)
90
90
  - Set `guard.enabled = true` if not already
91
91
  - Write config
92
92
 
93
93
  **`deny <path>`:**
94
94
  - Normalize path to forward slashes, ensure trailing slash for directories
95
- - If `guard.mode` is `allow`, AskUserQuestion: "Switching from allow to deny mode will clear existing paths ({N} paths). Continue?" — abort if user declines.
95
+ - If `guard.mode` is `allow`, user prompt: "Switching from allow to deny mode will clear existing paths ({N} paths). Continue?" — abort if user declines.
96
96
  - Set `guard.mode = "deny"`
97
97
  - Add path to `guard.paths` (deduplicate)
98
98
  - Set `guard.enabled = true` if not already (symmetric with `allow`: adding a deny path auto-enables the guard)
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  name: maestro-help
3
3
  description: "Maestro Flow 命令帮助系统。搜索命令、浏览技能、工作流推荐、新手引导。Triggers on \"maestro-help\", \"帮助\", \"命令\", \"怎么用\", \"skill\", \"workflow\", \"maestro 怎么用\"."
4
- allowed-tools: Read Grep Glob AskUserQuestion
4
+ allowed-tools: Read Grep Glob maestro
5
5
  ---
6
6
 
7
7
  # Maestro Help
@@ -314,8 +314,8 @@ Odyssey 长周期循环(独立路径)
314
314
  ## Related Resources
315
315
 
316
316
  - **Guide 目录**: `guide/` — 17 个专题指南文档
317
- - **Delegate 参考**: `~/.maestro/workflows/delegate-usage.md`
318
- - **Coding 哲学**: `~/.maestro/workflows/coding-philosophy.md`
317
+ - **Delegate 参考**: `~/.pi/agent/packages/pi-maestro-flow/workflows/delegate-usage.md`
318
+ - **Coding 哲学**: `~/.pi/agent/packages/pi-maestro-flow/workflows/coding-philosophy.md`
319
319
  - **CLI 工具配置**: `~/.maestro/cli-tools.json`
320
320
 
321
321
  ## Statistics