Composable HTML block patterns for agentsociety-analysis reports — KPI strips, figure cards, Mermaid, EDA tabs, optional interactive chart iframes. Use during Stage 5 produce when authoring report_zh.html / report_en.html.
SkillScore86Maintained
Automatic
◆Data Analyst pack
Last verified 8/15/2026
What it changes
Passed 19 of 22 test cases with the skill, and 11 of 22 without it.
Without skill50%
With skill86%
Checks it passed that the model alone missed
Visual styling uses a navy or slate color palette
Summary text uses an evidence-first scientific tone
Output is formatted as a standalone HTML report shell
and 6 more in the full report
8 fixed11 passed either way3 still failing0 broke
Pass-rate lift
+36 pp
Tokens
+4%
Agent turns
0%
Response time
-10%
Model gemini-3.6-flashMeasured 8/15/2026v119 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 8
Prompt
Where in the project assets directory is the working reference HTML template for offline report shells located?
What was checked, without and with the skill
Checked
Without skill
With skill
Working HTML report shell reference is identified at assets/report-shell.reference.html
Missed
Passed
case-15 · gemini-3.6-flash · 8/15/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md21 linessingle file
Report Blocks (bundled support)
Read references/reports.md at the agentsociety-analysis skill root first.
Files
File
Purpose
../../references/reports.md
Blocks, embeds, workflow
../../assets/report-shell.reference.html
Working HTML/CSS/JS
External inspiration absorbed
folio / datainpane — block composition, KPI strips, offline HTML
report-creator — Mermaid diagrams-as-code, metric groups
Generate, edit, or batch-create SEO, marketing, social, and document images with Gemini or OpenAI through the repository-owned Growth Lab image client. Use when a page or content loop needs illustrations, diagrams, covers, reference-image edits, multiple candidates, or verified image text and composition. This is the only AI image-generation Executor in Growth Lab.