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.
- package/README.md +44 -72
- package/agents/cross-role-reviewer.md +1 -1
- package/agents/impeccable-agent.md +1 -1
- package/agents/ralph-executor.md +1 -1
- package/agents/team-worker.md +1 -1
- package/agents/workflow-analyzer.md +1 -1
- package/agents/workflow-codebase-mapper.md +1 -1
- package/agents/workflow-collab-planner.md +1 -1
- package/agents/workflow-debugger.md +1 -1
- package/agents/workflow-executor.md +1 -1
- package/agents/workflow-integration-checker.md +1 -1
- package/agents/workflow-nyquist-auditor.md +1 -1
- package/agents/workflow-phase-researcher.md +1 -1
- package/agents/workflow-planner.md +1 -1
- package/agents/workflow-project-researcher.md +1 -1
- package/agents/workflow-reviewer.md +1 -1
- package/agents/workflow-verifier.md +1 -1
- package/package.json +18 -4
- package/skills/codify-to-knowhow/SKILL.md +1 -1
- package/skills/delegation-check/SKILL.md +1 -1
- package/skills/domain-add/SKILL.md +5 -5
- package/skills/insight-challenge/SKILL.md +1 -1
- package/skills/learn-decompose/SKILL.md +4 -4
- package/skills/learn-follow/SKILL.md +5 -5
- package/skills/learn-investigate/SKILL.md +5 -5
- package/skills/learn-second-opinion/SKILL.md +5 -5
- package/skills/maestro/SKILL.md +8 -8
- package/skills/maestro-amend/SKILL.md +4 -4
- package/skills/maestro-analyze/SKILL.md +9 -9
- package/skills/maestro-blueprint/SKILL.md +7 -7
- package/skills/maestro-brainstorm/SKILL.md +10 -10
- package/skills/maestro-collab/SKILL.md +4 -4
- package/skills/maestro-companion/SKILL.md +3 -3
- package/skills/maestro-composer/SKILL.md +10 -10
- package/skills/maestro-execute/SKILL.md +8 -8
- package/skills/maestro-fork/SKILL.md +7 -7
- package/skills/maestro-grill/SKILL.md +12 -12
- package/skills/maestro-guard/SKILL.md +5 -5
- package/skills/maestro-help/SKILL.md +3 -3
- package/skills/maestro-impeccable/SKILL.md +7 -7
- package/skills/maestro-init/SKILL.md +8 -8
- package/skills/maestro-merge/SKILL.md +6 -6
- package/skills/maestro-milestone-audit/SKILL.md +3 -3
- package/skills/maestro-milestone-complete/SKILL.md +8 -8
- package/skills/maestro-milestone-release/SKILL.md +9 -9
- package/skills/maestro-next/SKILL.md +5 -5
- package/skills/maestro-overlay/SKILL.md +19 -19
- package/skills/maestro-plan/SKILL.md +8 -8
- package/skills/maestro-player/SKILL.md +5 -5
- package/skills/maestro-quick/SKILL.md +5 -5
- package/skills/maestro-ralph/SKILL.md +15 -15
- package/skills/maestro-ralph-cli/SKILL.md +6 -6
- package/skills/maestro-ralph-cli-execute/SKILL.md +2 -2
- package/skills/maestro-ralph-execute/SKILL.md +4 -4
- package/skills/maestro-ralph-v2/SKILL.md +17 -17
- package/skills/maestro-roadmap/SKILL.md +7 -7
- package/skills/maestro-swarm-workflow/SKILL.md +9 -9
- package/skills/maestro-tools-execute/SKILL.md +5 -5
- package/skills/maestro-tools-register/SKILL.md +7 -7
- package/skills/maestro-ui-codify/SKILL.md +8 -8
- package/skills/maestro-universal-workflow/SKILL.md +15 -15
- package/skills/maestro-update/SKILL.md +10 -10
- package/skills/manage-codebase-rebuild/SKILL.md +4 -4
- package/skills/manage-drift-realign/SKILL.md +7 -7
- package/skills/manage-harvest/SKILL.md +5 -5
- package/skills/manage-issue/SKILL.md +4 -4
- package/skills/manage-issue-discover/SKILL.md +7 -7
- package/skills/manage-kg-extractors/SKILL.md +3 -3
- package/skills/manage-knowhow/SKILL.md +3 -3
- package/skills/manage-knowhow-capture/SKILL.md +4 -4
- package/skills/manage-knowledge-audit/SKILL.md +5 -5
- package/skills/manage-status/SKILL.md +3 -3
- package/skills/manage-wiki/SKILL.md +5 -5
- package/skills/odyssey-debug/SKILL.md +13 -13
- package/skills/odyssey-improve/SKILL.md +15 -15
- package/skills/odyssey-planex/SKILL.md +16 -16
- package/skills/odyssey-review-test-fix/SKILL.md +11 -11
- package/skills/odyssey-ui/SKILL.md +10 -10
- package/skills/prompt-generator/SKILL.md +5 -5
- package/skills/quality-auto-test/SKILL.md +3 -3
- package/skills/quality-debug/SKILL.md +3 -3
- package/skills/quality-refactor/SKILL.md +3 -3
- package/skills/quality-retrospective/SKILL.md +9 -9
- package/skills/quality-review/SKILL.md +4 -4
- package/skills/quality-sync/SKILL.md +3 -3
- package/skills/quality-test/SKILL.md +4 -4
- package/skills/scholar-anti-ai-writing/SKILL.md +1 -1
- package/skills/scholar-citation-verify/SKILL.md +1 -1
- package/skills/scholar-experiment/SKILL.md +2 -2
- package/skills/scholar-ideation/SKILL.md +7 -7
- package/skills/scholar-latex-organizer/SKILL.md +1 -1
- package/skills/scholar-publish/SKILL.md +3 -3
- package/skills/scholar-rebuttal-pro/SKILL.md +3 -3
- package/skills/scholar-review/SKILL.md +1 -1
- package/skills/scholar-writing/SKILL.md +1 -1
- package/skills/security-audit/SKILL.md +2 -2
- package/skills/skill-generator/SKILL.md +3 -3
- package/skills/skill-iter-tune/SKILL.md +3 -3
- package/skills/skill-simplify/SKILL.md +1 -1
- package/skills/skill-tuning/SKILL.md +1 -1
- package/skills/spec-add/SKILL.md +5 -5
- package/skills/spec-load/SKILL.md +3 -3
- package/skills/spec-remove/SKILL.md +4 -4
- package/skills/spec-setup/SKILL.md +6 -6
- package/skills/team-adversarial-swarm/SKILL.md +5 -5
- package/skills/team-arch-opt/SKILL.md +2 -2
- package/skills/team-brainstorm/SKILL.md +3 -3
- package/skills/team-coordinate/SKILL.md +4 -4
- package/skills/team-designer/SKILL.md +1 -1
- package/skills/team-executor/SKILL.md +3 -3
- package/skills/team-frontend/SKILL.md +2 -2
- package/skills/team-frontend-debug/SKILL.md +3 -3
- package/skills/team-interactive-craft/SKILL.md +2 -2
- package/skills/team-issue/SKILL.md +3 -3
- package/skills/team-lifecycle-v4/SKILL.md +4 -4
- package/skills/team-motion-design/SKILL.md +2 -2
- package/skills/team-perf-opt/SKILL.md +3 -3
- package/skills/team-planex/SKILL.md +2 -2
- package/skills/team-quality-assurance/SKILL.md +3 -3
- package/skills/team-review/SKILL.md +3 -3
- package/skills/team-roadmap-dev/SKILL.md +3 -3
- package/skills/team-swarm/SKILL.md +4 -4
- package/skills/team-tech-debt/SKILL.md +2 -2
- package/skills/team-testing/SKILL.md +3 -3
- package/skills/team-ui-polish/SKILL.md +2 -2
- package/skills/team-uidesign/SKILL.md +2 -2
- package/skills/team-ultra-analyze/SKILL.md +4 -4
- package/skills/team-ux-improve/SKILL.md +3 -3
- package/skills/team-visual-a11y/SKILL.md +2 -2
- package/skills/workflow-skill-designer/SKILL.md +8 -8
- package/templates/business-test-report.json +68 -0
- package/templates/config.json +48 -0
- package/templates/context.md +16 -0
- package/templates/doc-index.json +11 -0
- package/templates/index.json +68 -0
- package/templates/issue.json +36 -0
- package/templates/plan.json +38 -0
- package/templates/project.md +60 -0
- package/templates/reflection-log.md +20 -0
- package/templates/roadmap.md +45 -0
- package/templates/scratch-index.json +19 -0
- package/templates/search-tool.json +1 -0
- package/templates/search-tools.md +47 -0
- package/templates/state.json +18 -0
- package/templates/task-summary.md +21 -0
- package/templates/task.json +89 -0
- package/templates/terminology-template.json +22 -0
- package/templates/uat.md +21 -0
- package/templates/validation.json +31 -0
- package/templates/verification.json +37 -0
- package/templates/workflow.md +14 -0
- package/templates/worktree-scope.json +9 -0
- package/templates/worktrees.json +26 -0
- package/workflows/agy-instructions.md +156 -0
- package/workflows/analyze.md +768 -0
- package/workflows/auto-test.md +705 -0
- package/workflows/blueprint.md +406 -0
- package/workflows/boundary-grill.md +50 -0
- package/workflows/brainstorm.md +508 -0
- package/workflows/business-test.md +574 -0
- package/workflows/chinese-response.md +25 -0
- package/workflows/claude-instructions.md +167 -0
- package/workflows/codebase-rebuild.md +267 -0
- package/workflows/codebase-refresh.md +168 -0
- package/workflows/codex-instructions.md +156 -0
- package/workflows/coding-philosophy.md +70 -0
- package/workflows/command-authoring.md +823 -0
- package/workflows/debug.md +409 -0
- package/workflows/delegate-usage.md +99 -0
- package/workflows/domain-add.md +121 -0
- package/workflows/drift-realign.md +396 -0
- package/workflows/execute.md +631 -0
- package/workflows/explore-usage.md +93 -0
- package/workflows/finish-work.md +124 -0
- package/workflows/fork.md +162 -0
- package/workflows/grill.md +494 -0
- package/workflows/harvest.md +478 -0
- package/workflows/impeccable.md +168 -0
- package/workflows/init.md +157 -0
- package/workflows/instruction-authoring-guide.md +97 -0
- package/workflows/integration-test.md +186 -0
- package/workflows/interview-mechanics.md +8 -0
- package/workflows/issue-analyze.md +20 -0
- package/workflows/issue-discover.md +238 -0
- package/workflows/issue-execute.md +110 -0
- package/workflows/issue-gaps-analyze.codex.md +256 -0
- package/workflows/issue-gaps-analyze.md +215 -0
- package/workflows/issue-plan.md +110 -0
- package/workflows/issue.md +338 -0
- package/workflows/knowhow.md +429 -0
- package/workflows/knowledge-audit.md +355 -0
- package/workflows/learn.md +271 -0
- package/workflows/maestro-chain-execute.md +20 -0
- package/workflows/maestro-link-coordinate.md +114 -0
- package/workflows/maestro-super.md +120 -0
- package/workflows/maestro.md +501 -0
- package/workflows/map.md +74 -0
- package/workflows/merge.md +122 -0
- package/workflows/milestone-audit.md +155 -0
- package/workflows/milestone-complete.md +167 -0
- package/workflows/milestone-release.md +82 -0
- package/workflows/odyssey-base-codex.md +305 -0
- package/workflows/odyssey-base.md +256 -0
- package/workflows/overlays.md +109 -0
- package/workflows/plan.md +520 -0
- package/workflows/quick.md +350 -0
- package/workflows/ralph-amend-goal.md +177 -0
- package/workflows/refactor.md +87 -0
- package/workflows/retrospective.md +471 -0
- package/workflows/review.md +448 -0
- package/workflows/roadmap-common.md +193 -0
- package/workflows/roadmap.md +106 -0
- package/workflows/shell-exec-protocol.md +30 -0
- package/workflows/skill-authoring.md +265 -0
- package/workflows/spec-generate.md +475 -0
- package/workflows/specs-add.md +123 -0
- package/workflows/specs-load.md +76 -0
- package/workflows/specs-remove.md +104 -0
- package/workflows/specs-setup.md +316 -0
- package/workflows/status.md +149 -0
- package/workflows/sync.md +116 -0
- package/workflows/tdd.md +255 -0
- package/workflows/test-gen.md +226 -0
- package/workflows/test.md +385 -0
- package/workflows/tools-spec.md +70 -0
- package/workflows/ui-codify-extract.md +372 -0
- package/workflows/ui-codify-knowhow.md +258 -0
- package/workflows/ui-codify-package.md +159 -0
- package/workflows/ui-codify.md +227 -0
- package/workflows/ui-design.md +393 -0
- package/workflows/ui-style.md +201 -0
- package/workflows/verify.md +557 -0
- package/workflows/wiki-connect.md +153 -0
- package/workflows/wiki-digest.md +180 -0
- package/workflows/wiki-manage.md +113 -0
package/skills/maestro/SKILL.md
CHANGED
|
@@ -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
|
|
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:
|
|
98
|
+
→ END DO: invoke /skill: "maestro-ralph-execute" })
|
|
99
99
|
|
|
100
100
|
S_FALLBACK:
|
|
101
|
-
→ S_CLASSIFY WHEN: user provides new intent DO:
|
|
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. `
|
|
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 → `
|
|
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
|
|
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
|
-
|
|
13
|
-
|
|
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 +
|
|
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
|
|
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
|
-
|
|
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
|
|
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
|
-
|
|
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
|
|
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
|
-
|
|
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
|
|
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
|
|
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
|
-
|
|
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
|
|
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
|
-
|
|
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
|
|
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
|
-
|
|
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
|
|
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:
|
|
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:
|
|
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
|
|
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,
|
|
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:
|
|
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
|
|
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
|
|
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:
|
|
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**:
|
|
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
|
|
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
|
-
|
|
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:
|
|
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: `
|
|
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
|
-
|
|
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
|
|
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
|
-
|
|
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:
|
|
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 |
|
|
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
|
|
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
|
-
|
|
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
|
|
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 | `
|
|
120
|
-
| Need deep technical analysis | `
|
|
121
|
-
| Scope is clear, ready for roadmap | `
|
|
122
|
-
| Need formal spec package | `
|
|
123
|
-
| More branches to walk | `
|
|
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
|
|
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
|
-
|
|
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
|
|
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
|
|
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`,
|
|
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`,
|
|
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
|
|
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
|