Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add hollandkevint/data-product-operator --skill data-storytellinggit clone --depth 1 https://github.com/hollandkevint/data-product-operatorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hollandkevint/data-product-operator/data-storytelling)<a href="https://agentmods.dev/skills/hollandkevint/data-product-operator/data-storytelling"><img src="https://agentmods.dev/badge/skills/hollandkevint/data-product-operator/data-storytelling/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hollandkevint/data-product-operator/data-storytelling"><img src="https://agentmods.dev/badge/skills/hollandkevint/data-product-operator/data-storytelling.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00076 | $0.00735 |
| Opus 5 | $0.00038 | $0.00367 |
| Sonnet 5 | $0.00015 | $0.00147 |
| Haiku 4.5 | $0.00008 | $0.00073 |
Grade A, and why
data-storytelling scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Headline Formula
Every data finding needs a headline: [Specific Number] + [Business Impact] + [Actionable Context].
"Readmission risk scores now flag 23% more high-risk patients, saving $2.1M annually." Not "We improved our model performance." Not "Results were statistically significant."
The number makes it concrete. The impact makes it relevant. The context makes it actionable.
Narrative Structures
Pick the structure that matches the situation:
| Structure | When to Use | Shape |
|---|---|---|
| Problem-Solution | Pitching new work | "Here's the gap, here's what we built" |
| Trend | Status updates | "Here's what changed and why it matters" |
| Comparison | Trade-off decisions | "Here are two options with costs" |
Narrative Arc for Presentations
Hook (the surprise or gap) → Context (what the audience needs to know) → Evidence (the data, 2-3 charts max) → Implication (so what?) → Recommendation (now what?)
Start with the finding, not the methodology. Executives care about the answer. They'll ask about the method if they want it.
Chart Selection
Match the metric type to the right chart:
| Metric Type | Chart | Example |
|---|---|---|
| Counts | Bar chart | Monthly patient encounters |
| Rates over time | Line chart | 30-day readmission rate by quarter |
| Part-of-whole | Stacked bar | Claim denials by category |
| Distribution | Histogram or box plot | Length of stay distribution |
| Correlation | Scatter plot | Cost vs complexity score |
| Ranking | Horizontal bar | Top 10 diagnoses by volume |
NEVER use pie charts. Stacked bar does everything a pie chart does, with readable labels.
NEVER use dual Y-axes. Two metrics, two charts. Dual axes let you imply any correlation by scaling the axes.
ALWAYS label data directly on the chart. A legend across the room is useless.
Presentation Anti-Patterns
Charts without a "so what." Every chart needs a headline that states the finding. "Figure 3: Revenue by Region" tells the audience nothing. "Northeast revenue dropped 12% after formulary change" tells them what to see.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 69 lines · 76 tokens per session scan A 0c62038de76c
data-storytelling is a skill published in the GitHub repository hollandkevint/data-product-operator (3 stars, last pushed yesterday), licensed MIT. It adds 76 tokens to every session and 735 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
fechar-dia
Fecha o dia de trabalho. Avalia as 3 do dia, classifica o que não fechou, semeia o movimento.
processar-reuniao
Transforma uma reunião que aconteceu em nota estruturada e propaga o que importa. A pessoa cola a transcrição, o resumo automático ou as notas cruas. Use quando a pessoa disser "processa essa reunião", "processa esse 1:1", "olha o que rolou na reunião", colar uma transcrição pedindo organização, ou…
preparar-conversa
Monta a pauta antes de uma conversa que importa. 1:1 com liderado, 1:1 com o próprio líder, alinhamento com par ou stakeholder. Use quando a pessoa disser "prepara o 1:1 com [nome]", "monta a pauta", "vou falar com [nome]", "tenho reunião com [nome], me prepara", "/preparar-conversa". NÃO use pra processar a conversa…
classify
Assess or re-assess the innovation-vs-implementation classification and 0-100 innovation weight for one feature or the whole Product/Features set, then regenerate the ranked features-index.md and run the portfolio sanity check. Use when features need (re)ranking or after editing the UVP.
feature
Create or revise a single Product feature file with a complete user story, Given/When/Then acceptance criteria, and an innovation-vs-implementation classification. Use when adding one feature to Product/Features/, or refining an existing feature, outside a full /innovate run.
iflow
The front door / orchestrator for the I-Framework. Reads the Product/ folder, determines which stage (Intent, Ideation, Innovation) you're in from the artifacts and their gates, reports the risk-burndown state, and routes you to the next step. Use to start or resume the Intent → Ideation → Innovation flow.