Write Tip
by getsentry
Create or improve AI productivity tips and guides for the Abacus dashboard. Use when writing new tips, editing existing tips, or reviewing tip content for quality. Ensures tips follow the established format with scenarios, prompts, and proper structure.
Skill Details
Repository Files
1 file in this skill directory
name: write-tip description: Create or improve AI productivity tips and guides for the Abacus dashboard. Use when writing new tips, editing existing tips, or reviewing tip content for quality. Ensures tips follow the established format with scenarios, prompts, and proper structure. allowed-tools: Read, Grep, Glob, Edit, Write
Write Tip Skill
Create high-quality AI productivity tips and guides for the Abacus dashboard.
Before Writing
Read these files to understand the existing format:
src/lib/tips.ts- All existing tips and guides (study the structure)CLAUDE.md- Project guidelines including tip writing rules
Tip Structure
Each tip has two parts:
1. TipBar Entry (in TIPS array)
{
id: 'unique-kebab-id',
text: 'Concise tip shown in the banner (one sentence)',
guide: 'guide-slug', // Links to the guide below
}
2. Guide Entry (in GUIDES object)
'guide-slug': {
slug: 'guide-slug',
title: 'Short Title',
description: 'One-line description',
externalDocs: 'https://...', // Optional official docs link
tools: ['claude-code', 'cursor'], // Which tools it applies to
content: `
## What is [Feature]?
One to two sentences explaining what this is. No fluff.
## Try It: [Scenario Name]
**Scenario**: Brief context (one sentence).
**Step 1**: Do this
\`\`\`
Exact prompt text the user types
\`\`\`
**Step 2**: Then this
\`\`\`
Another prompt
\`\`\`
## Key Points
- **Point one** - brief explanation
- **Point two** - brief explanation
- **Point three** - brief explanation
`,
}
Writing Rules
- Prompts are primary - Show exact text users type, not abstract descriptions
- Scenarios > theory - "Here's how to do X" beats "X is useful because..."
- Concise - Users skim; keep sections short
- No fluff - Skip "In this guide you'll learn..." intros
- No
>prefix - Don't prefix prompt examples with>(causes rendering issues) - Separate code blocks - Don't mix bash commands with prompts in the same block
Code Block Formatting
Use plain code blocks for prompts (no language specifier):
This is a prompt the user types
Use bash for shell commands:
git checkout -b feature/new-thing
Use markdown for file content examples:
---
name: my-skill
---
Tools Field
'claude-code'- Claude Code CLI features'cursor'- Cursor editor features- Use both if the tip applies to both tools
Quality Checklist
Before finishing, verify:
- Has a concrete "Try It" scenario with copy-pasteable prompts
- No
>prefix on prompt lines - Code blocks have correct language tags (or none for prompts)
- Description is one line, not a paragraph
- Tools array is accurate
- Slug matches the guide key
- At least 2-3 related TipBar entries point to this guide
Adding Icons
If creating a new guide, add its icon mapping in:
src/app/tips/page.tsx- GUIDE_ICONS objectsrc/app/tips/[slug]/page.tsx- GUIDE_ICONS object
Available icons from lucide-react: Compass, RefreshCw, Command, MapPin, Cpu, MessageSquare, GitBranch, Users, FileCode, Zap, Star, etc.
Related Skills
Attack Tree Construction
Build comprehensive attack trees to visualize threat paths. Use when mapping attack scenarios, identifying defense gaps, or communicating security risks to stakeholders.
Grafana Dashboards
Create and manage production Grafana dashboards for real-time visualization of system and application metrics. Use when building monitoring dashboards, visualizing metrics, or creating operational observability interfaces.
Matplotlib
Foundational plotting library. Create line plots, scatter, bar, histograms, heatmaps, 3D, subplots, export PNG/PDF/SVG, for scientific visualization and publication figures.
Scientific Visualization
Create publication figures with matplotlib/seaborn/plotly. Multi-panel layouts, error bars, significance markers, colorblind-safe, export PDF/EPS/TIFF, for journal-ready scientific plots.
Seaborn
Statistical visualization. Scatter, box, violin, heatmaps, pair plots, regression, correlation matrices, KDE, faceted plots, for exploratory analysis and publication figures.
Shap
Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing models, or implementing explainable AI. Works with tree-based models (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), linear models, and any black-box model
Pydeseq2
Differential gene expression analysis (Python DESeq2). Identify DE genes from bulk RNA-seq counts, Wald tests, FDR correction, volcano/MA plots, for RNA-seq analysis.
Query Writing
For writing and executing SQL queries - from simple single-table queries to complex multi-table JOINs and aggregations
Pydeseq2
Differential gene expression analysis (Python DESeq2). Identify DE genes from bulk RNA-seq counts, Wald tests, FDR correction, volcano/MA plots, for RNA-seq analysis.
Scientific Visualization
Meta-skill for publication-ready figures. Use when creating journal submission figures requiring multi-panel layouts, significance annotations, error bars, colorblind-safe palettes, and specific journal formatting (Nature, Science, Cell). Orchestrates matplotlib/seaborn/plotly with publication styles. For quick exploration use seaborn or plotly directly.
