maestro-flow-one 0.2.5 → 0.2.7

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 (33) hide show
  1. package/maestro-flow/agents/impeccable-agent.md +99 -0
  2. package/maestro-flow/agents/ui-design-agent.md +1 -0
  3. package/maestro-flow/agents/workflow-executor.md +3 -0
  4. package/maestro-flow/commands/learn/decompose.md +91 -146
  5. package/maestro-flow/commands/learn/follow.md +102 -137
  6. package/maestro-flow/commands/learn/investigate.md +102 -167
  7. package/maestro-flow/commands/learn/retro.md +100 -243
  8. package/maestro-flow/commands/learn/second-opinion.md +95 -135
  9. package/maestro-flow/commands/lifecycle/amend.md +95 -232
  10. package/maestro-flow/commands/lifecycle/analyze.md +3 -8
  11. package/maestro-flow/commands/lifecycle/brainstorm.md +116 -112
  12. package/maestro-flow/commands/lifecycle/collab.md +104 -265
  13. package/maestro-flow/commands/lifecycle/composer.md +117 -292
  14. package/maestro-flow/commands/lifecycle/execute.md +10 -17
  15. package/maestro-flow/commands/lifecycle/impeccable.md +126 -0
  16. package/maestro-flow/commands/lifecycle/merge.md +3 -0
  17. package/maestro-flow/commands/lifecycle/plan.md +1 -6
  18. package/maestro-flow/commands/lifecycle/player.md +111 -340
  19. package/maestro-flow/commands/lifecycle/quick.md +9 -0
  20. package/maestro-flow/commands/lifecycle/roadmap.md +5 -1
  21. package/maestro-flow/commands/lifecycle/ui-codify.md +13 -0
  22. package/maestro-flow/commands/lifecycle/ui-craft.md +416 -0
  23. package/maestro-flow/commands/lifecycle/verify.md +12 -13
  24. package/maestro-flow/commands/manage/issue-discover.md +4 -0
  25. package/maestro-flow/commands/manage/knowhow-capture.md +45 -170
  26. package/maestro-flow/commands/quality/auto-test.md +9 -0
  27. package/maestro-flow/commands/quality/debug.md +11 -25
  28. package/maestro-flow/commands/quality/refactor.md +12 -0
  29. package/maestro-flow/commands/quality/review.md +5 -14
  30. package/maestro-flow/commands/spec/add.md +1 -1
  31. package/maestro-flow/commands/spec/load.md +3 -2
  32. package/package.json +1 -1
  33. package/maestro-flow/commands/lifecycle/ui-design.md +0 -93
@@ -1,112 +1,116 @@
1
- ---
2
- name: maestro-brainstorm
3
- description: Brainstorm with auto pipeline or single-role analysis
4
- argument-hint: "[topic|role-name] [--yes] [--count N] [--session ID] [--update] [--skip-questions] [--include-questions] [--style-skill PKG]"
5
- allowed-tools:
6
- - Read
7
- - Write
8
- - Bash
9
- - Glob
10
- - Grep
11
- - Agent
12
- - AskUserQuestion
13
- ---
14
- <purpose>
15
- Unified brainstorming combining interactive framework generation, multi-role parallel analysis, and cross-role synthesis. Two modes: Auto (full pipeline with guidance-specification → parallel role analysis → synthesis) and Single Role (individual role analysis for an existing session). Outputs structured artifacts in .brainstorming/ directory ready for downstream planning.
16
- </purpose>
17
-
18
- <required_reading>
19
- @~/.maestro/workflows/brainstorm.md
20
- </required_reading>
21
-
22
- <deferred_reading>
23
- - [scratch-index.json](~/.maestro/templates/scratch-index.json) — read when operating in scratch mode
24
- - [index.json](~/.maestro/templates/index.json) — read when operating in phase mode
25
- - [brainstorm-visualize.md](~/.maestro/workflows/brainstorm-visualize.md) — read when html-prototypes/ produced and user wants to browse them
26
- </deferred_reading>
27
-
28
- <context>
29
- $ARGUMENTS -- topic text for auto mode, or role name for single role mode.
30
-
31
- **Auto mode**: topic text (e.g., "Build real-time collaboration platform") triggers full pipeline.
32
- **Single role mode**: valid role name (e.g., "system-architect") runs one role analysis.
33
- **All output** goes to `.workflow/scratch/{YYYYMMDD}-brainstorm-{slug}/`.
34
- **Artifact registration**: On completion, registers artifact (type=brainstorm) in state.json.
35
- **Output boundary**: ALL file writes MUST target `{output_dir}/` or `.workflow/state.json` only. NEVER modify source code or files outside these paths.
36
-
37
- **Valid roles**: data-architect, product-manager, product-owner, scrum-master, subject-matter-expert, system-architect, test-strategist, ui-designer, ux-expert
38
-
39
- **Flags**:
40
- - `--yes` / `-y`: Auto mode, skip interactive questions, use defaults
41
- - `--count N`: Number of roles to select (default 3, max 9)
42
- - `--session ID`: Use existing session
43
- - `--update`: Update existing analysis (single role)
44
- - `--skip-questions`: Skip context gathering questions
45
- - `--include-questions`: Force context gathering even if analysis exists
46
- - `--style-skill PKG`: Style package for ui-designer role
47
-
48
- ### Role Knowledge
49
- 1. Browse accumulated knowledge for this role:
50
- `maestro wiki list --category arch`
51
- 2. Analyze the index, identify entries relevant to the current task
52
- 3. Load selected documents:
53
- `maestro wiki load <id1> [id2] [id3...]`
54
- 4. Review loaded knowledge before proceeding
55
- </context>
56
-
57
- <execution>
58
- Follow '~/.maestro/workflows/brainstorm.md' completely.
59
-
60
- **Next-step routing on completion:**
61
-
62
- Auto mode:
63
- - Project not initialized → Skill({ skill: "maestro-init" })
64
- - Project initialized, need spec package → Skill({ skill: "maestro-roadmap", args: "--mode full --from-brainstorm {session_id}" })
65
- - Project initialized, quick roadmap → Skill({ skill: "maestro-roadmap", args: "--from-brainstorm {session_id}" })
66
- - Need deeper analysis first → Skill({ skill: "maestro-analyze", args: "{topic}" })
67
- - `html-prototypes/` produced with 2+ files and user wants to browse → load `~/.maestro/workflows/brainstorm-visualize.md` and launch visualizer server (optional, user-triggered)
68
-
69
- Single role mode:
70
- - More roles needed → Skill({ skill: "maestro-brainstorm", args: "{next_role} --session {session_id}" })
71
- - All roles done, run synthesisSkill({ skill: "maestro-brainstorm", args: "{topic} --session {session_id}" })
72
- </execution>
73
-
74
- <error_codes>
75
- | Code | Severity | Condition | Recovery |
76
- |------|----------|-----------|----------|
77
- | E001 | error | Topic or role argument required | Prompt user for topic text or role name |
78
- | E002 | error | No active session for single role mode | Guide user to run auto mode first |
79
- | E003 | error | Invalid role name | Show valid roles list |
80
- | W001 | warning | Fewer than 10 ideas in divergent phase | Proceed with available ideas |
81
- | W002 | warning | Project context (.workflow/) not found | Continue without project context |
82
- | W003 | warning | Role template not found | Use generic analysis structure |
83
- | W004 | warning | Validation score < 60 | Log warning, suggest manual review |
84
- | W005 | warning | External research agent failed | Continue without designResearchContext |
85
- </error_codes>
86
-
87
- <success_criteria>
88
- **Auto mode**:
89
- - [ ] guidance-specification.md with RFC 2119 keywords, terminology, non-goals, feature decomposition
90
- - [ ] design-research.md persisted when Step 1.7 external research ran (fail-soft: absence not a failure)
91
- - [ ] Spec Review Gate passed (Step 3.5) or `--yes` bypassed
92
- - [ ] Role analysis files for each selected NON-UI role in `.brainstorming/{role}/`
93
- - [ ] If `ui-designer` in selected_roles: `ui-designer/analysis.md` exists AND exactly one of `html-prototypes/` / `ascii-mockups/` / `api-sketches/` exists with `README.md` + ≥1 prototype file
94
- - [ ] ui-designer/analysis.md references each prototype via `@-notation`
95
- - [ ] HTML prototypes are self-contained (no external `<link>`/`<script src>` URLs warn only)
96
- - [ ] Feature specs in `.brainstorming/feature-specs/` (or synthesis-specification.md)
97
- - [ ] UI-bearing feature specs reference the corresponding prototype in Section 3 (Interface Contract)
98
- - [ ] feature-index.json and synthesis-changelog.md
99
- - [ ] Final Output Gate passed (Step 5.5) or `--yes` bypassed
100
- - [ ] All user decisions captured with Decision Recording Protocol
101
- - [ ] Session metadata updated with completion status
102
- - [ ] Confidence scored per role completion and after cross-role analysis
103
- - [ ] Readiness gate checked before spec generation
104
- - [ ] Pressure pass completed on at least 1 feature spec
105
- - [ ] Confidence summary appended to synthesis-changelog.md
106
-
107
- **Single role mode**:
108
- - [ ] analysis.md written to `{output_dir}/{role}/`
109
- - [ ] Feature-point organization used when feature list available
110
- - [ ] Framework reference included when guidance-specification.md exists
111
- - [ ] Session metadata updated
112
- </success_criteria>
1
+ ---
2
+ name: maestro-brainstorm
3
+ description: Brainstorm with auto pipeline or single-role analysis
4
+ argument-hint: "[topic|role-name] [--yes] [--count N] [--session ID] [--update] [--skip-questions] [--include-questions] [--style-skill PKG]"
5
+ allowed-tools:
6
+ - Read
7
+ - Write
8
+ - Bash
9
+ - Glob
10
+ - Grep
11
+ - Agent
12
+ - AskUserQuestion
13
+ ---
14
+ <purpose>
15
+ Unified brainstorming combining interactive framework generation, multi-role parallel analysis, and cross-role synthesis. Two modes: Auto (full pipeline with guidance-specification → parallel role analysis → synthesis) and Single Role (individual role analysis for an existing session). Outputs structured artifacts in .brainstorming/ directory ready for downstream planning.
16
+ </purpose>
17
+
18
+ <required_reading>
19
+ @~/.maestro/workflows/brainstorm.md
20
+ </required_reading>
21
+
22
+ <deferred_reading>
23
+ - [scratch-index.json](~/.maestro/templates/scratch-index.json) — read when operating in scratch mode
24
+ - [index.json](~/.maestro/templates/index.json) — read when operating in phase mode
25
+ - [brainstorm-visualize.md](~/.maestro/workflows/brainstorm-visualize.md) — read when html-prototypes/ produced and user wants to browse them
26
+ </deferred_reading>
27
+
28
+ <context>
29
+ $ARGUMENTS -- topic text for auto mode, or role name for single role mode.
30
+
31
+ **Auto mode**: topic text (e.g., "Build real-time collaboration platform") triggers full pipeline.
32
+ **Single role mode**: valid role name (e.g., "system-architect") runs one role analysis.
33
+ **All output** goes to `.workflow/scratch/{YYYYMMDD}-brainstorm-{slug}/`.
34
+ **Artifact registration**: On completion, registers artifact (type=brainstorm) in state.json.
35
+ **Output boundary**: ALL file writes MUST target `{output_dir}/` or `.workflow/state.json` only. NEVER modify source code or files outside these paths.
36
+
37
+ **Valid roles**: data-architect, product-manager, product-owner, scrum-master, subject-matter-expert, system-architect, test-strategist, ui-designer, ux-expert
38
+
39
+ **Flags**:
40
+ - `--yes` / `-y`: Auto mode, skip interactive questions, use defaults
41
+ - `--count N`: Number of roles to select (default 3, max 9)
42
+ - `--session ID`: Use existing session
43
+ - `--update`: Update existing analysis (single role)
44
+ - `--skip-questions`: Skip context gathering questions
45
+ - `--include-questions`: Force context gathering even if analysis exists
46
+ - `--style-skill PKG`: Style package for ui-designer role
47
+
48
+ ### Pre-load specs
49
+ 1. **Architecture specs**: Run `maestro spec load --category arch` to load architecture constraints. Use as context for multi-role analysis — ensures roles respect documented decisions.
50
+ 2. Optional proceed without if unavailable.
51
+
52
+ ### Role Knowledge
53
+ 1. Browse accumulated knowledge for this role:
54
+ `maestro wiki list --category arch`
55
+ 2. Analyze the index, identify entries relevant to the current task
56
+ 3. Load selected documents:
57
+ `maestro wiki load <id1> [id2] [id3...]`
58
+ 4. Review loaded knowledge before proceeding
59
+ </context>
60
+
61
+ <execution>
62
+ Follow '~/.maestro/workflows/brainstorm.md' completely.
63
+
64
+ **Next-step routing on completion:**
65
+
66
+ Auto mode:
67
+ - Project not initialized Skill({ skill: "maestro-init" })
68
+ - Project initialized, need spec package → Skill({ skill: "maestro-roadmap", args: "--mode full --from-brainstorm {session_id}" })
69
+ - Project initialized, quick roadmap → Skill({ skill: "maestro-roadmap", args: "--from-brainstorm {session_id}" })
70
+ - Need deeper analysis first → Skill({ skill: "maestro-analyze", args: "{topic}" })
71
+ - `html-prototypes/` produced with 2+ files and user wants to browse load `~/.maestro/workflows/brainstorm-visualize.md` and launch visualizer server (optional, user-triggered)
72
+ - DESIGN.md established during Step 3.5 → suggest: "Run `/maestro-ui-craft <feature-description> --chain build` to build with the established design system"
73
+
74
+ Single role mode:
75
+ - More roles needed Skill({ skill: "maestro-brainstorm", args: "{next_role} --session {session_id}" })
76
+ - All roles done, run synthesis → Skill({ skill: "maestro-brainstorm", args: "{topic} --session {session_id}" })
77
+ </execution>
78
+
79
+ <error_codes>
80
+ | Code | Severity | Condition | Recovery |
81
+ |------|----------|-----------|----------|
82
+ | E001 | error | Topic or role argument required | Prompt user for topic text or role name |
83
+ | E002 | error | No active session for single role mode | Guide user to run auto mode first |
84
+ | E003 | error | Invalid role name | Show valid roles list |
85
+ | W001 | warning | Fewer than 10 ideas in divergent phase | Proceed with available ideas |
86
+ | W002 | warning | Project context (.workflow/) not found | Continue without project context |
87
+ | W003 | warning | Role template not found | Use generic analysis structure |
88
+ | W004 | warning | Validation score < 60 | Log warning, suggest manual review |
89
+ | W005 | warning | External research agent failed | Continue without designResearchContext |
90
+ </error_codes>
91
+
92
+ <success_criteria>
93
+ **Auto mode**:
94
+ - [ ] guidance-specification.md with RFC 2119 keywords, terminology, non-goals, feature decomposition
95
+ - [ ] design-research.md persisted when Step 1.7 external research ran (fail-soft: absence not a failure)
96
+ - [ ] Spec Review Gate passed (Step 3.5) or `--yes` bypassed
97
+ - [ ] Role analysis files for each selected NON-UI role in `.brainstorming/{role}/`
98
+ - [ ] If `ui-designer` in selected_roles AND Step 3.5 ran: `.workflow/impeccable/DESIGN.md` exists (visual style established via impeccable explore)
99
+ - [ ] If `ui-designer` in selected_roles: `ui-designer/analysis.md` exists with UX analysis (interaction flows, state design, information architecture)
100
+ - [ ] Feature specs in `.brainstorming/feature-specs/` (or synthesis-specification.md)
101
+ - [ ] UI-bearing feature specs reference DESIGN.md for visual constraints in Section 3 (Interface Contract)
102
+ - [ ] feature-index.json and synthesis-changelog.md
103
+ - [ ] Final Output Gate passed (Step 5.5) or `--yes` bypassed
104
+ - [ ] All user decisions captured with Decision Recording Protocol
105
+ - [ ] Session metadata updated with completion status
106
+ - [ ] Confidence scored per role completion and after cross-role analysis
107
+ - [ ] Readiness gate checked before spec generation
108
+ - [ ] Pressure pass completed on at least 1 feature spec
109
+ - [ ] Confidence summary appended to synthesis-changelog.md
110
+
111
+ **Single role mode**:
112
+ - [ ] analysis.md written to `{output_dir}/{role}/`
113
+ - [ ] Feature-point organization used when feature list available
114
+ - [ ] Framework reference included when guidance-specification.md exists
115
+ - [ ] Session metadata updated
116
+ </success_criteria>