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 san-npm/skills-ws --skill data-analyticsgit clone --depth 1 https://github.com/san-npm/skills-wsWrote 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/san-npm/skills-ws/data-analytics)<a href="https://agentmods.dev/skills/san-npm/skills-ws/data-analytics"><img src="https://agentmods.dev/badge/skills/san-npm/skills-ws/data-analytics.svg" alt="Measured on agentmods" 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 | $0.00067 | $0.06290 |
| Opus 5 | $0.00034 | $0.03145 |
| Sonnet 5 | $0.00013 | $0.01258 |
| Haiku 4.5 | $0.00007 | $0.00629 |
Grade A, and why
data-analytics 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 6d 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 — 401 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Analytics
Workflow
1. Define the Question
Before writing any query, articulate:
- What decision will this analysis inform?
- What metric answers the question?
- What timeframe is relevant?
- What segments matter?
Bad: "How are we doing?" → Good: "What's our 30-day retention rate by acquisition channel for Q1 cohorts?"
2. KPI Framework Selection
| Framework | Best for | Core metrics |
|---|---|---|
| AARRR (Pirate) | Growth-stage SaaS | Acquisition, Activation, Retention, Revenue, Referral |
| HEART | Product/UX teams | Happiness, Engagement, Adoption, Retention, Task success |
| NSM (North Star) | Company alignment | One metric that captures core value delivery |
| OKR | Goal tracking | Objectives + measurable Key Results |
Choose NSM first, then AARRR for operational metrics, HEART for product teams.
2b. Define the Metric Before You Query It
Most "the numbers don't match" fights are definition fights, not SQL bugs. Write a one-page metric spec and store it in version control (ideally as a semantic-layer definition, below) so every dashboard computes the same thing.
| Field | Example (Weekly Active Account) |
|---|---|
| Name / owner | Weekly Active Account — owned by Growth analytics |
| Grain | One row per account per ISO week |
| Numerator | Distinct accounts with ≥1 session_start |
| Denominator | (rate metrics only) eligible accounts that week |
| Filters | is_internal = false, plan != 'trial_expired' |
| Exclusions | Bots, internal/staff users, test accounts, refunded orders |
| Timezone | UTC week boundaries (WEEK(MONDAY)) |
| Refresh cadence | Daily 06:00 UTC; closed week is final after +2 days (late events) |
| Source tables | fct_sessions, dim_accounts |
| Known caveats | Single-sign-on shares one account across users; counts accounts not seats |
Semantic layer / metrics-as-code (mid-2026). Define metrics once and let BI tools query them, so "revenue" can't mean three things:
- dbt Semantic Layer (powered by MetricFlow): declare
semantic_modelsandmetricsin YAML; consumers query via the JDBC/GraphQL API or the dbt CLI (formerly the dbt Cloud CLI), e.g.dbt sl query --metrics revenue --group-by metric_time__month. The legacydbt_metricspackage is deprecated; use MetricFlow. - Cube, Looker (LookML), Lightdash, MetricFlow, Malloy are the common alternatives; pick one and treat metric definitions as reviewed code.
- Net effect: the SQL patterns below are how a metric is implemented once in the semantic layer or a dbt model — not copy-pasted into every dashboard.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 401 lines · 67 tokens per session scan A 20b9cb741e80
data-analytics is a skill published in the GitHub repository san-npm/skills-ws (2 stars, last pushed today), licensed MIT. It adds 67 tokens to every session and 6,290 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…