create-report
Skill49 starsChanged 3 months agoMITView on GitHub
Create a polished visual report as an HTML artifact with charts, tables, and formatted text. Use when the user asks for a report, dashboard, analysis, or visual summary of data.
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 33
Add a "Download" or "Print" button if appropriate
- Very specific: line 35
For data-heavy reports: use generate_csv alongside the artifact so the user gets both the visual and the raw data.
- Distinctive: line 71
Don't output just text — use the artifact for visual impact
- Distinctive: line 72
Don't make tiny charts — use at least 300px height
- Distinctive: line 73
Don't forget dark theme — bright backgrounds look bad in chat
- Distinctive: line 74
Don't hardcode widths — use percentages and flexbox
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Create Report
When to use
The user wants a polished visual output: a report, dashboard, analysis summary, or formatted document with data.
Steps
- Gather the data — use search, browser, or recall tools to collect information. Structure it before creating the artifact.
- Choose the right artifact type:
- Dashboard with charts → HTML with Chart.js via CDN
- Process/architecture diagram → Mermaid
- Formatted report/document → HTML with marked.js for markdown rendering
- Infographic → SVG or HTML
- Create the artifact using
create_artifactwith typehtml. Include these CDN scripts as needed:- Charts:
<script src="https://cdn.jsdelivr.net/npm/chart.js"></script> - Markdown:
<script src="https://cdn.jsdelivr.net/npm/marked/marked.min.js"></script> - Maps:
<script src="https://cdn.jsdelivr.net/npm/leaflet/dist/leaflet.js"></script>
- Charts:
- Design rules:
- Dark background:
#0f1117or#1a1b26 - Light text:
#e2e8f0 - Accent colours: use vibrant colours for charts/data
- System font:
font-family: system-ui, -apple-system, sans-serif - Responsive: use CSS grid/flexbox, test at different widths
- Include a title bar with the report name
- Add a "Download" or "Print" button if appropriate
- Dark background:
- For data-heavy reports: use
generate_csvalongside the artifact so the user gets both the visual and the raw data. - Offer follow-ups via
offer_choices:- "Export as Word document"
- "Add more data"
- "Change the chart type"
- "Download as CSV"
Chart.js quick reference
<canvas id="myChart"></canvas>
<script>
new Chart(document.getElementById('myChart'), {
type: 'bar', // bar, line, pie, doughnut, radar, scatter
data: {
labels: ['Jan', 'Feb', 'Mar'],
datasets: [{
label: 'Revenue',
data: [12, 19, 3],
backgroundColor: ['#3b82f6', '#10b981', '#f59e0b'],
}]
},
options: {
responsive: true,
plugins: { legend: { labels: { color: '#e2e8f0' } } },
scales: {
x: { ticks: { color: '#94a3b8' }, grid: { color: '#334155' } },
y: { ticks: { color: '#94a3b8' }, grid: { color: '#334155' } }
}
}
});
</script>What not to do
- Don't output just text — use the artifact for visual impact
- Don't make tiny charts — use at least 300px height
- Don't forget dark theme — bright backgrounds look bad in chat
- Don't hardcode widths — use percentages and flexbox
In this repository32 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- agent-asks-tasksSkill
- caretakerSkill
- code-reviewSkill
- compare-optionsSkill
- csv-analyseSkill
- document-qaSkill
- draft-emailSkill
- enrich-errorSkill
- extract-structured-dataSkill
- fact-checkSkill
- git-diff-summariserSkill
- librarian-curateSkill
- meeting-notesSkill
- morning-briefSkill
- plan-taskSkill
- reflectSkill
- remember-conversationSkill
- reverieSkill
- review-code-securitySkill
- review-email-toneSkill
- review-outputSkill
- review-summary-faithfulnessSkill
- rewrite-for-audienceSkill
- route-findingSkill
- routine-health-checkSkill
- save-research-docSkill
- score-importanceSkill
- summarise-urlSkill
- web-researchSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

