You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Add Vercel React Best Practices Skill with Performance Optimization Rules
- Introduced metadata for the Vercel React Best Practices skill.
- Created sections for performance optimization rules, categorized by impact.
- Added templates for rule documentation.
- Implemented various performance optimization rules including:
- Avoiding waterfalls in async operations.
- Optimizing bundle sizes and server-side performance.
- Using `requestIdleCallback` for non-critical tasks.
- Hoisting static I/O to module level to prevent repeated I/O per request.
- Ensuring no shared module state for request data to avoid concurrency issues.
- Implementing parallel nested data fetching to eliminate server-side waterfalls.
- Added additional rules for rendering performance and JavaScript optimizations.
Copy file name to clipboardExpand all lines: .agents/skills/brainstorming/SKILL.md
+79-11Lines changed: 79 additions & 11 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -5,8 +5,6 @@ description: "You MUST use this before any creative work - creating features, bu
5
5
6
6
# Brainstorming Ideas Into Designs
7
7
8
-
## Overview
9
-
10
8
Help turn ideas into fully formed designs and specs through natural collaborative dialogue.
11
9
12
10
Start by understanding the current project context, then ask questions one at a time to refine the idea. Once you understand what you're building, present the design and get user approval.
@@ -24,31 +22,44 @@ Every project goes through this process. A todo list, a single-function utility,
24
22
You MUST create a task for each of these items and complete them in order:
2.**Ask clarifying questions** — one at a time, understand purpose/constraints/success criteria
28
-
3.**Propose 2-3 approaches** — with trade-offs and your recommendation
29
-
4.**Present design** — in sections scaled to their complexity, get user approval after each section
30
-
5.**Write design doc** — save to `docs/plans/YYYY-MM-DD-<topic>-design.md` and commit
31
-
6.**Transition to implementation** — invoke writing-plans skill to create implementation plan
25
+
2.**Offer visual companion** (if topic will involve visual questions) — this is its own message, not combined with a clarifying question. See the Visual Companion section below.
26
+
3.**Ask clarifying questions** — one at a time, understand purpose/constraints/success criteria
27
+
4.**Propose 2-3 approaches** — with trade-offs and your recommendation
28
+
5.**Present design** — in sections scaled to their complexity, get user approval after each section
29
+
6.**Write design doc** — save to `docs/superpowers/specs/YYYY-MM-DD-<topic>-design.md` and commit
30
+
7.**Spec self-review** — quick inline check for placeholders, contradictions, ambiguity, scope (see below)
31
+
8.**User reviews written spec** — ask user to review the spec file before proceeding
32
+
9.**Transition to implementation** — invoke writing-plans skill to create implementation plan
32
33
33
34
## Process Flow
34
35
35
36
```dot
36
37
digraph brainstorming {
37
38
"Explore project context" [shape=box];
39
+
"Visual questions ahead?" [shape=diamond];
40
+
"Offer Visual Companion\n(own message, no other content)" [shape=box];
- Check out the current project state first (files, docs, recent commits)
61
-
- Ask questions one at a time to refine the idea
73
+
- Before asking detailed questions, assess scope: if the request describes multiple independent subsystems (e.g., "build a platform with chat, file storage, billing, and analytics"), flag this immediately. Don't spend questions refining details of a project that needs to be decomposed first.
74
+
- If the project is too large for a single spec, help the user decompose into sub-projects: what are the independent pieces, how do they relate, what order should they be built? Then brainstorm the first sub-project through the normal design flow. Each sub-project gets its own spec → plan → implementation cycle.
75
+
- For appropriately-scoped projects, ask questions one at a time to refine the idea
62
76
- Prefer multiple choice questions when possible, but open-ended is fine too
63
77
- Only one question per message - if a topic needs more exploration, break it into multiple questions
64
78
- Focus on understanding: purpose, constraints, success criteria
65
79
66
80
**Exploring approaches:**
81
+
67
82
- Propose 2-3 different approaches with trade-offs
68
83
- Present options conversationally with your recommendation and reasoning
69
84
- Lead with your recommended option and explain why
70
85
71
86
**Presenting the design:**
87
+
72
88
- Once you believe you understand what you're building, present the design
73
89
- Scale each section to its complexity: a few sentences if straightforward, up to 200-300 words if nuanced
74
90
- Ask after each section whether it looks right so far
75
91
- Cover: architecture, components, data flow, error handling, testing
76
92
- Be ready to go back and clarify if something doesn't make sense
77
93
94
+
**Design for isolation and clarity:**
95
+
96
+
- Break the system into smaller units that each have one clear purpose, communicate through well-defined interfaces, and can be understood and tested independently
97
+
- For each unit, you should be able to answer: what does it do, how do you use it, and what does it depend on?
98
+
- Can someone understand what a unit does without reading its internals? Can you change the internals without breaking consumers? If not, the boundaries need work.
99
+
- Smaller, well-bounded units are also easier for you to work with - you reason better about code you can hold in context at once, and your edits are more reliable when files are focused. When a file grows large, that's often a signal that it's doing too much.
100
+
101
+
**Working in existing codebases:**
102
+
103
+
- Explore the current structure before proposing changes. Follow existing patterns.
104
+
- Where existing code has problems that affect the work (e.g., a file that's grown too large, unclear boundaries, tangled responsibilities), include targeted improvements as part of the design - the way a good developer improves code they're working in.
105
+
- Don't propose unrelated refactoring. Stay focused on what serves the current goal.
106
+
78
107
## After the Design
79
108
80
109
**Documentation:**
81
-
- Write the validated design to `docs/plans/YYYY-MM-DD-<topic>-design.md`
110
+
111
+
- Write the validated design (spec) to `docs/superpowers/specs/YYYY-MM-DD-<topic>-design.md`
112
+
- (User preferences for spec location override this default)
82
113
- Use elements-of-style:writing-clearly-and-concisely skill if available
83
114
- Commit the design document to git
84
115
116
+
**Spec Self-Review:**
117
+
After writing the spec document, look at it with fresh eyes:
118
+
119
+
1.**Placeholder scan:** Any "TBD", "TODO", incomplete sections, or vague requirements? Fix them.
120
+
2.**Internal consistency:** Do any sections contradict each other? Does the architecture match the feature descriptions?
121
+
3.**Scope check:** Is this focused enough for a single implementation plan, or does it need decomposition?
122
+
4.**Ambiguity check:** Could any requirement be interpreted two different ways? If so, pick one and make it explicit.
123
+
124
+
Fix any issues inline. No need to re-review — just fix and move on.
125
+
126
+
**User Review Gate:**
127
+
After the spec review loop passes, ask the user to review the written spec before proceeding:
128
+
129
+
> "Spec written and committed to `<path>`. Please review it and let me know if you want to make any changes before we start writing out the implementation plan."
130
+
131
+
Wait for the user's response. If they request changes, make them and re-run the spec review loop. Only proceed once the user approves.
132
+
85
133
**Implementation:**
134
+
86
135
- Invoke the writing-plans skill to create a detailed implementation plan
87
136
- Do NOT invoke any other skill. writing-plans is the next step.
88
137
@@ -94,3 +143,22 @@ digraph brainstorming {
94
143
-**Explore alternatives** - Always propose 2-3 approaches before settling
95
144
-**Incremental validation** - Present design, get approval before moving on
96
145
-**Be flexible** - Go back and clarify when something doesn't make sense
146
+
147
+
## Visual Companion
148
+
149
+
A browser-based companion for showing mockups, diagrams, and visual options during brainstorming. Available as a tool — not a mode. Accepting the companion means it's available for questions that benefit from visual treatment; it does NOT mean every question goes through the browser.
150
+
151
+
**Offering the companion:** When you anticipate that upcoming questions will involve visual content (mockups, layouts, diagrams), offer it once for consent:
152
+
> "Some of what we're working on might be easier to explain if I can show it to you in a web browser. I can put together mockups, diagrams, comparisons, and other visuals as we go. This feature is still new and can be token-intensive. Want to try it? (Requires opening a local URL)"
153
+
154
+
**This offer MUST be its own message.** Do not combine it with clarifying questions, context summaries, or any other content. The message should contain ONLY the offer above and nothing else. Wait for the user's response before continuing. If they decline, proceed with text-only brainstorming.
155
+
156
+
**Per-question decision:** Even after the user accepts, decide FOR EACH QUESTION whether to use the browser or the terminal. The test: **would the user understand this better by seeing it than reading it?**
157
+
158
+
-**Use the browser** for content that IS visual — mockups, wireframes, layout comparisons, architecture diagrams, side-by-side visual designs
159
+
-**Use the terminal** for content that is text — requirements questions, conceptual choices, tradeoff lists, A/B/C/D text options, scope decisions
160
+
161
+
A question about a UI topic is not automatically a visual question. "What does personality mean in this context?" is a conceptual question — use the terminal. "Which wizard layout works better?" is a visual question — use the browser.
162
+
163
+
If they agree to the companion, read the detailed guide before proceeding:
0 commit comments