brainstorm

Name: brainstorm
Author: withqwerty

30stars4forks

How to install brainstorm?

withqwerty/nutmeg/brainstorm

$npx -y skills add withqwerty/nutmeg --skill brainstorm

Installs into the current project.

Summary

Brainstorm football data visualisations and chart designs. Use when the user wants ideas for how to visualise football data, needs inspiration for chart types, wants to explore design approaches for match reports, player profiles, team dashboards, or any football analytics graphi

Files · 1

View on GitHub

SKILL.md

1	# Brainstorm
2
3	Help the user explore and choose football data visualisation approaches through research-backed ideation and collaborative refinement.
4
5	## Accuracy
6
7	Read and follow `docs/accuracy-guardrail.md` before answering any question about provider-specific facts (IDs, endpoints, schemas, coordinates, rate limits). Always use `search_docs` — never guess from training data.
8
9	## First: check profile
10
11	Read `.nutmeg.user.md`. If it doesn't exist, tell the user to run `/nutmeg` first. Use their profile for:
12	- Programming language (Python/R/JS)
13	- Visualisation libraries they use (mplsoccer, matplotlib, ggplot2, d3, Observable)
14	- Experience level (adapt complexity of suggestions)
15	- Available data sources (what providers they have access to)
16
17	## References (load as needed)
18
19	This skill has two reference documents. Load them when relevant — don't read both upfront for every question.
20
21	\| Reference \| When to load \| Path \|
22	\|---\|---\|---\|
23	\| Chart Canon \| When discussing specific football chart types, conventions, or anti-patterns \| `skills/brainstorm/references/chart-canon.md` \|
24	\| Viz Styles \| When helping the user choose a design approach or aesthetic direction \| `skills/brainstorm/references/viz-styles.md` \|
25	\| Campos Bridge \| Strong React/campos signal in cwd — loads the bridge; soft signals surface a mention only \| `skills/_shared/campos-bridge.md` \|
26
27	## Process
28
29	### Phase 1: Understand the goal
30
31	Ask one question at a time to understand:
32	- What data? Match events, player stats, team stats, tracking data?
33	- What story? What insight or comparison are they trying to show?
34	- What context? Dashboard, social media, blog post, presentation, academic paper?
35	- What format? Static image, interactive, animation, part of a larger report?
36
37	Don't ask all of these upfront. Start with the most important one based on what they said, then follow up.
38
39	Detect React/campos context before proposing approaches:
40
41	- Strong signal — Read cwd's `package.json`; if it contains `react` or `@withqwerty/campos-react` in `dependencies`/`devDependencies`, load `skills/_shared/campos-bridge.md` and include campos options alongside Python/R in Phase 3.
42	- Soft signal — user mentions React/TS/Next/Vite/campos/browser chart in conversation AND cwd does not have `pyproject.toml` / `requirements.txt` / `renv.lock` / `Gemfile`. Do not auto-load; mention the bridge exists and offer to load if the user confirms they want a React chart.
43	- Conflicting signal — cwd is a Python/R/Ruby project. Keep the existing mplsoccer/ggplot2 path; soft signals are ignored. Strong signals still win (monorepo case).
44	- Integration-self signal — cwd IS the campos or nutmeg repo itself (see the bridge doc for detection). Downgrade to soft — working on the integration is not the same as using it.
45	- No signal — existing path unchanged.
46
47	Determine their style early. Load `references/viz-styles.md` and identify which style fits their context (Analytical, Social Media, Editorial, Minimal/Academic). For advanced users, skip the style discussion — they know what they want. Focus on the specific technique.
48
49	### Phase 2: Research approaches
50
51	Before proposing options, research what works well.
52
53	Search strategy (follow this order):
54
55	1. Check football-docs:
56	- `search_docs(query="[viz type]", provider="mplsoccer")` — mplsoccer has extensive viz docs
57	- `search_docs(query="[concept] visualisation")` — check if any provider docs cover this
58
59	2. Load the chart canon if the question involves a standard football chart type:
60	- Read `skills/brainstorm/references/chart-canon.md`
61	- Check conventions, known weaknesses, and anti-patterns for the chart type
62
63	3. Search the web for real-world examples:
64	- Search: `"football analytics" "[viz type]" site:twitter.com OR site:x.com`
65	- Search: `"[viz type]" football "made with" mplsoccer OR matplotlib OR ggplot2`
66	- Search: `football data viz "[specific chart]" tutorial`
67	- Search for key practitioners: Karun Singh, Tom Worville, John Burn-Murdoch, Mark Thompson, StatsBomb
68
69	4. Check GitHub for open implementations:
70	- Search: `site:github.com football viz "[chart type]"`
71
72	Report what you find before proposing options. Show 2-3 real examples with links and explain what makes each effective.
73
74	### Phase 3: Propose approaches
75
76	Based on research,

People who liked this also viewed

6 picks

Type

brainstorm

30stars4forks

View on GitHub

How to install brainstorm?

withqwerty/nutmeg/brainstorm

$npx -y skills add withqwerty/nutmeg --skill brainstorm

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Brainstorm
2
3	Help the user explore and choose football data visualisation approaches through research-backed ideation and collaborative refinement.
4
5	## Accuracy
6
7	Read and follow `docs/accuracy-guardrail.md` before answering any question about provider-specific facts (IDs, endpoints, schemas, coordinates, rate limits). Always use `search_docs` — never guess from training data.
8
9	## First: check profile
10
11	Read `.nutmeg.user.md`. If it doesn't exist, tell the user to run `/nutmeg` first. Use their profile for:
12	- Programming language (Python/R/JS)
13	- Visualisation libraries they use (mplsoccer, matplotlib, ggplot2, d3, Observable)
14	- Experience level (adapt complexity of suggestions)
15	- Available data sources (what providers they have access to)
16
17	## References (load as needed)
18
19	This skill has two reference documents. Load them when relevant — don't read both upfront for every question.
20
21	\| Reference \| When to load \| Path \|
22	\|---\|---\|---\|
23	\| Chart Canon \| When discussing specific football chart types, conventions, or anti-patterns \| `skills/brainstorm/references/chart-canon.md` \|
24	\| Viz Styles \| When helping the user choose a design approach or aesthetic direction \| `skills/brainstorm/references/viz-styles.md` \|
25	\| Campos Bridge \| Strong React/campos signal in cwd — loads the bridge; soft signals surface a mention only \| `skills/_shared/campos-bridge.md` \|
26
27	## Process
28
29	### Phase 1: Understand the goal
30
31	Ask one question at a time to understand:
32	- What data? Match events, player stats, team stats, tracking data?
33	- What story? What insight or comparison are they trying to show?
34	- What context? Dashboard, social media, blog post, presentation, academic paper?
35	- What format? Static image, interactive, animation, part of a larger report?
36
37	Don't ask all of these upfront. Start with the most important one based on what they said, then follow up.
38
39	Detect React/campos context before proposing approaches:
40
41	- Strong signal — Read cwd's `package.json`; if it contains `react` or `@withqwerty/campos-react` in `dependencies`/`devDependencies`, load `skills/_shared/campos-bridge.md` and include campos options alongside Python/R in Phase 3.
42	- Soft signal — user mentions React/TS/Next/Vite/campos/browser chart in conversation AND cwd does not have `pyproject.toml` / `requirements.txt` / `renv.lock` / `Gemfile`. Do not auto-load; mention the bridge exists and offer to load if the user confirms they want a React chart.
43	- Conflicting signal — cwd is a Python/R/Ruby project. Keep the existing mplsoccer/ggplot2 path; soft signals are ignored. Strong signals still win (monorepo case).
44	- Integration-self signal — cwd IS the campos or nutmeg repo itself (see the bridge doc for detection). Downgrade to soft — working on the integration is not the same as using it.
45	- No signal — existing path unchanged.
46
47	Determine their style early. Load `references/viz-styles.md` and identify which style fits their context (Analytical, Social Media, Editorial, Minimal/Academic). For advanced users, skip the style discussion — they know what they want. Focus on the specific technique.
48
49	### Phase 2: Research approaches
50
51	Before proposing options, research what works well.
52
53	Search strategy (follow this order):
54
55	1. Check football-docs:
56	- `search_docs(query="[viz type]", provider="mplsoccer")` — mplsoccer has extensive viz docs
57	- `search_docs(query="[concept] visualisation")` — check if any provider docs cover this
58
59	2. Load the chart canon if the question involves a standard football chart type:
60	- Read `skills/brainstorm/references/chart-canon.md`
61	- Check conventions, known weaknesses, and anti-patterns for the chart type
62
63	3. Search the web for real-world examples:
64	- Search: `"football analytics" "[viz type]" site:twitter.com OR site:x.com`
65	- Search: `"[viz type]" football "made with" mplsoccer OR matplotlib OR ggplot2`
66	- Search: `football data viz "[specific chart]" tutorial`
67	- Search for key practitioners: Karun Singh, Tom Worville, John Burn-Murdoch, Mark Thompson, StatsBomb
68
69	4. Check GitHub for open implementations:
70	- Search: `site:github.com football viz "[chart type]"`
71
72	Report what you find before proposing options. Show 2-3 real examples with links and explain what makes each effective.
73
74	### Phase 3: Propose approaches
75
76	Based on research,

People who liked this also viewed

6 picks

Type