cm-brainstorm-idea

Name: cm-brainstorm-idea
Author: tody-agent

47stars23forks

How to install cm-brainstorm-idea?

tody-agent/codymaster/cm-brainstorm-idea

$npx -y skills add tody-agent/codymaster --skill cm-brainstorm-idea

Installs into the current project.

Summary

Strategic analysis gate for existing products — multi-dimensional evaluation (tech, product, design, business) using Design Thinking + 9 Windows (TRIZ) + Double Diamond. Outputs 2-3 qualified options with recommendations. Use BEFORE cm-planning for complex initiatives and enhance

Files · 1

View on GitHub

SKILL.md

1	# Brainstorm Idea — Strategic Analysis Gate
2
3	## TL;DR
4	- Use before cm-planning for complex/ambiguous initiatives
5	- Frameworks: Design Thinking + 9 Windows (TRIZ) + Double Diamond
6	- Output: 2-3 qualified options + recommendation
7	- Writes: handoff/intent.json
8
9	> Understand deeply. Evaluate multi-dimensionally. Propose qualified options. Then — and only then — plan.
10	> This skill is the BRIDGE between an existing product and its next evolution.
11
12	## When to Use
13
14	ALWAYS when:
15	- User requests complex changes to an existing product
16	- Initiatives or enhancements that touch multiple system areas
17	- User jumps straight into hard/complex tasks without analysis
18	- Post `cm-project-bootstrap` — product exists, needs improvement
19	- Feature requests that could be solved in fundamentally different ways
20	- "What should we do next?" / "What to improve?" / "Enhancement" / "Initiative"
21
22	Skip when:
23	- Simple bug fixes (use `cm-debugging`)
24	- New project from scratch (use `cm-project-bootstrap`)
25	- Task is already clearly defined and scoped (go to `cm-planning`)
26	- Quick one-off changes (< 30 min work)
27
28	## Gate Function
29
30	```
31	User requests complex task
32	→ Is the problem clearly understood and qualified?
33	→ NO → Run cm-brainstorm-idea FIRST
34	→ YES → Go to cm-planning directly
35	```
36
37	When downstream skills detect an unqualified complex request, they should REDIRECT here:
38	```
39	cm-planning detects ambiguity → "Problem not clear. Run cm-brainstorm-idea first."
40	cm-execution gets vague plan → "Plan lacks context. Go back to cm-brainstorm-idea."
41	```
42
43	---
44
45	## The Process
46
47	```
48	Phase 1: DISCOVER (Diamond 1 — Diverge) → Scan wide, understand current state
49	Phase 2: DEFINE (Diamond 1 — Converge) → Qualify the REAL problem
50	Phase 3: DEVELOP (Diamond 2 — Diverge) → Generate 2-3 solution options
51	Phase 4: EVALUATE (Diamond 2 — Converge) → Score, compare, recommend
52	Phase 4.5: UI PREVIEW (Visual Validation) → See it before you build it
53	Phase 5: HANDOFF (Bridge to cm-planning) → Package for downstream skills
54	```
55
56	### Phase 1: DISCOVER — Scan & Empathize
57
58	> Goal: Understand the current state of the product from all angles.
59
60	#### 1a. Codebase Scan
61
62	Read and map the existing system:
63
64	```
65	✅ DO:
66	- Read .cm/skeleton.md for instant overview. If missing, run `cm index skeleton`.
67	- Read .cm/architecture.mmd for an instant architectural diagram.
68	- IF codegraph is available (`codegraph status`):
69	→ Use `codegraph_files` to summarize project.
70	→ Use graph to identify most connected modules and dead code.
71	- Read AGENTS.md and key config files.
72	- Check test coverage and existing quality.
73
74	📋 OUTPUT: Codebase Summary
75	- Tech stack & Architecture: [...]
76	- Key dependencies & Test coverage: [...]
77	- Code health & Codebase insights (from skeleton/codegraph): [...]
78	- Present architecture diagram to user (if .cm/architecture.mmd exists).
79	- Corpus size: [total source files] src / [total doc files] docs
80
81	🔍 SIZE CHECK (auto — triggers cm-deep-search/cm-codeintell):
82	IF docs/ > 50 files OR source > 200 files:
83	→ Suggest: "This project is quite large. Run `cm index skeleton` and see cm-deep-search to setup semantic search."
84	→ Non-blocking: continue Phase 1 regardless of user response
85	```
86
87	#### 1b. User Context Interview
88
89	Ask targeted questions to understand intent:
90
91	```
92	📋 DISCOVERY QUESTIONS:
93	1. Who does the current product serve? (Target users?)
94	2. What is the biggest pain point right now? (Biggest pain point?)
95	3. What is the next business goal? (Next business goal?)
96	4. Are there any tech/budget/timeline constraints? (Constraints?)
97	5. What solutions have already been tried? (What's been tried?)
98	```
99
100	#### 1c. Multi-Dimensional Current State
101
102	\| Dimension \| What to Assess \| Sources \|
103	\|-----------\|---------------\|---------\|
104	\| Tech \| Code quality, scalability, tech debt, performance \| Codebase scan, test results \|
105	\| Product \| Feature completeness, user satisfaction, funnel gaps \| User interview, analytics \|
106	\| Design \| UX quality, accessibility, mobile readiness, design system \| UI review, `cm-ux-master` \|
107	\| Business \| Revenue impact, market position, competitive landscape \| User interview, research \|
108
109	---
110
111	### Phase 2: DEFINE — Qualify the Problem
112
113	> Goal: Use 9 Windows to see the problem from all time × system perspectives, then converge on the REAL problem.
114
115	#### 9 Windows Analysis (TRIZ)
116
117	Map the situation across time and system levels:
118
119	```
120	┌─────────────────┬──────────────────┬──────────────────┬──────────────────┐
121	│ │ PAST │ PRESENT │

People who liked this also viewed

6 picks

Type

cm-brainstorm-idea

47stars23forks

View on GitHub

How to install cm-brainstorm-idea?

tody-agent/codymaster/cm-brainstorm-idea

$npx -y skills add tody-agent/codymaster --skill cm-brainstorm-idea

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Brainstorm Idea — Strategic Analysis Gate
2
3	## TL;DR
4	- Use before cm-planning for complex/ambiguous initiatives
5	- Frameworks: Design Thinking + 9 Windows (TRIZ) + Double Diamond
6	- Output: 2-3 qualified options + recommendation
7	- Writes: handoff/intent.json
8
9	> Understand deeply. Evaluate multi-dimensionally. Propose qualified options. Then — and only then — plan.
10	> This skill is the BRIDGE between an existing product and its next evolution.
11
12	## When to Use
13
14	ALWAYS when:
15	- User requests complex changes to an existing product
16	- Initiatives or enhancements that touch multiple system areas
17	- User jumps straight into hard/complex tasks without analysis
18	- Post `cm-project-bootstrap` — product exists, needs improvement
19	- Feature requests that could be solved in fundamentally different ways
20	- "What should we do next?" / "What to improve?" / "Enhancement" / "Initiative"
21
22	Skip when:
23	- Simple bug fixes (use `cm-debugging`)
24	- New project from scratch (use `cm-project-bootstrap`)
25	- Task is already clearly defined and scoped (go to `cm-planning`)
26	- Quick one-off changes (< 30 min work)
27
28	## Gate Function
29
30	```
31	User requests complex task
32	→ Is the problem clearly understood and qualified?
33	→ NO → Run cm-brainstorm-idea FIRST
34	→ YES → Go to cm-planning directly
35	```
36
37	When downstream skills detect an unqualified complex request, they should REDIRECT here:
38	```
39	cm-planning detects ambiguity → "Problem not clear. Run cm-brainstorm-idea first."
40	cm-execution gets vague plan → "Plan lacks context. Go back to cm-brainstorm-idea."
41	```
42
43	---
44
45	## The Process
46
47	```
48	Phase 1: DISCOVER (Diamond 1 — Diverge) → Scan wide, understand current state
49	Phase 2: DEFINE (Diamond 1 — Converge) → Qualify the REAL problem
50	Phase 3: DEVELOP (Diamond 2 — Diverge) → Generate 2-3 solution options
51	Phase 4: EVALUATE (Diamond 2 — Converge) → Score, compare, recommend
52	Phase 4.5: UI PREVIEW (Visual Validation) → See it before you build it
53	Phase 5: HANDOFF (Bridge to cm-planning) → Package for downstream skills
54	```
55
56	### Phase 1: DISCOVER — Scan & Empathize
57
58	> Goal: Understand the current state of the product from all angles.
59
60	#### 1a. Codebase Scan
61
62	Read and map the existing system:
63
64	```
65	✅ DO:
66	- Read .cm/skeleton.md for instant overview. If missing, run `cm index skeleton`.
67	- Read .cm/architecture.mmd for an instant architectural diagram.
68	- IF codegraph is available (`codegraph status`):
69	→ Use `codegraph_files` to summarize project.
70	→ Use graph to identify most connected modules and dead code.
71	- Read AGENTS.md and key config files.
72	- Check test coverage and existing quality.
73
74	📋 OUTPUT: Codebase Summary
75	- Tech stack & Architecture: [...]
76	- Key dependencies & Test coverage: [...]
77	- Code health & Codebase insights (from skeleton/codegraph): [...]
78	- Present architecture diagram to user (if .cm/architecture.mmd exists).
79	- Corpus size: [total source files] src / [total doc files] docs
80
81	🔍 SIZE CHECK (auto — triggers cm-deep-search/cm-codeintell):
82	IF docs/ > 50 files OR source > 200 files:
83	→ Suggest: "This project is quite large. Run `cm index skeleton` and see cm-deep-search to setup semantic search."
84	→ Non-blocking: continue Phase 1 regardless of user response
85	```
86
87	#### 1b. User Context Interview
88
89	Ask targeted questions to understand intent:
90
91	```
92	📋 DISCOVERY QUESTIONS:
93	1. Who does the current product serve? (Target users?)
94	2. What is the biggest pain point right now? (Biggest pain point?)
95	3. What is the next business goal? (Next business goal?)
96	4. Are there any tech/budget/timeline constraints? (Constraints?)
97	5. What solutions have already been tried? (What's been tried?)
98	```
99
100	#### 1c. Multi-Dimensional Current State
101
102	\| Dimension \| What to Assess \| Sources \|
103	\|-----------\|---------------\|---------\|
104	\| Tech \| Code quality, scalability, tech debt, performance \| Codebase scan, test results \|
105	\| Product \| Feature completeness, user satisfaction, funnel gaps \| User interview, analytics \|
106	\| Design \| UX quality, accessibility, mobile readiness, design system \| UI review, `cm-ux-master` \|
107	\| Business \| Revenue impact, market position, competitive landscape \| User interview, research \|
108
109	---
110
111	### Phase 2: DEFINE — Qualify the Problem
112
113	> Goal: Use 9 Windows to see the problem from all time × system perspectives, then converge on the REAL problem.
114
115	#### 9 Windows Analysis (TRIZ)
116
117	Map the situation across time and system levels:
118
119	```
120	┌─────────────────┬──────────────────┬──────────────────┬──────────────────┐
121	│ │ PAST │ PRESENT │

People who liked this also viewed

6 picks

Type