$npx -y skills add withqwerty/nutmeg --skill reviewReview football data code and visualisations for correctness. Use after building a chart, data pipeline, or analysis. Dispatches specialised reviewers for data correctness, chart conventions, visual inspection, and interactive edge cases.
| 1 | # Review |
| 2 | |
| 3 | Dispatch specialised reviewers to check football data code and visualisations for correctness, convention compliance, and edge cases. |
| 4 | |
| 5 | ## Accuracy |
| 6 | |
| 7 | Read and follow `docs/accuracy-guardrail.md` before answering any question about provider-specific facts. |
| 8 | |
| 9 | ## First: check profile |
| 10 | |
| 11 | Read `.nutmeg.user.md`. If it doesn't exist, tell the user to run `/nutmeg` first. |
| 12 | |
| 13 | ## Determine scope |
| 14 | |
| 15 | Look at what the user wants reviewed. Read the relevant files. Then decide which reviewers to dispatch: |
| 16 | |
| 17 | | Signal | Dispatch | |
| 18 | |---|---| |
| 19 | | Code processes football data (fetching, filtering, transforming, computing metrics) | **data-reviewer** agent | |
| 20 | | Code renders a chart or visualisation | **chart-reviewer** agent (Mode 1: Code Review) | |
| 21 | | User provides a URL or says "check how it looks" | **chart-reviewer** agent (Mode 2: Visual Inspection) | |
| 22 | | Chart has filters, tooltips, state, or dynamic data | **chart-reviewer** agent (Mode 3: Interactive Edge Cases) | |
| 23 | | Code imports `@withqwerty/campos-*` (React + campos) | **chart-reviewer** agent (Mode 4: React + Campos) — pass `skills/_shared/campos-bridge.md` in context | |
| 24 | | Code does both data processing AND chart rendering | **Both agents** in parallel | |
| 25 | |
| 26 | **Always dispatch at least one.** If unclear, dispatch both — redundant findings are better than missed issues. |
| 27 | |
| 28 | Detection for Mode 4: grep the reviewed files for `@withqwerty/campos-` or `from "@withqwerty/campos`. Any match activates Mode 4 alongside Mode 1. |
| 29 | |
| 30 | ## Dispatch |
| 31 | |
| 32 | Spawn agents in parallel when dispatching multiple. Each agent receives: |
| 33 | |
| 34 | 1. The file paths to review |
| 35 | 2. The user's profile (language, provider, experience level) |
| 36 | 3. Which mode(s) to run (for chart-reviewer) |
| 37 | 4. Context: what the user said they built and what they're worried about |
| 38 | |
| 39 | ### Data reviewer prompt template |
| 40 | |
| 41 | ``` |
| 42 | Review the football data code in [FILE_PATHS]. |
| 43 | |
| 44 | The user is working with [PROVIDER] data in [LANGUAGE]. |
| 45 | They built: [DESCRIPTION] |
| 46 | Their concern: [WHAT_THEY_SAID] |
| 47 | |
| 48 | Follow the full review checklist in your agent prompt. Use search_docs to verify |
| 49 | provider-specific facts (coordinate systems, qualifier IDs, event types). |
| 50 | ``` |
| 51 | |
| 52 | ### Chart reviewer prompt template |
| 53 | |
| 54 | ``` |
| 55 | Review the chart code in [FILE_PATHS]. |
| 56 | |
| 57 | Mode(s): [Code Review / Visual Inspection / Interactive Edge Cases] |
| 58 | The user is building: [DESCRIPTION] |
| 59 | Their concern: [WHAT_THEY_SAID] |
| 60 | Stack: [LANGUAGE + LIBRARIES from profile] |
| 61 | [If visual inspection: URL or instructions to render] |
| 62 | |
| 63 | Load skills/brainstorm/references/chart-canon.md for convention checking. |
| 64 | ``` |
| 65 | |
| 66 | ## Synthesise findings |
| 67 | |
| 68 | After both agents report back: |
| 69 | |
| 70 | 1. **Deduplicate** — if both flag the same issue (e.g., wrong coordinate system), merge into one finding |
| 71 | 2. **Sort by severity** — Critical first, then Warning, then Info |
| 72 | 3. **Group logically** — Data issues, then Rendering issues, then Convention issues, then Edge cases |
| 73 | 4. **Present concisely** — table format with severity, location, issue, fix |
| 74 | |
| 75 | ## When to suggest visual inspection |
| 76 | |
| 77 | If the chart-reviewer's code review finds potential rendering issues but can't confirm without seeing the output, suggest: |
| 78 | |
| 79 | > "The code review found [N] potential rendering issues. Want me to visually inspect the chart? I'll need a URL or you can run it locally." |
| 80 | |
| 81 | Don't require visual inspection — many users can't easily serve their chart locally. Code review alone catches most issues. |
| 82 | |
| 83 | ## After review |
| 84 | |
| 85 | If findings are found: |
| 86 | - Ask the user which ones to fix |
| 87 | - For Critical issues, offer to fix them directly |
| 88 | - For Warning/Info, explain the trade-off and let them decide |
| 89 | |
| 90 | If no findings: |
| 91 | - Say so clearly. Don't invent issues to justify the review. |
| 92 | - Optionally mention what was checked so the user knows the review was thorough. |