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 Uxcel-Lab/product-skills --skill analyticsgit clone --depth 1 https://github.com/Uxcel-Lab/product-skillsWrote 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/uxcel-lab/product-skills/analytics)<a href="https://agentmods.dev/skills/uxcel-lab/product-skills/analytics"><img src="https://agentmods.dev/badge/skills/uxcel-lab/product-skills/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 | $0.00129 | $0.02681 |
| Opus 5 | $0.00064 | $0.01340 |
| Sonnet 5 | $0.00026 | $0.00536 |
| Haiku 4.5 | $0.00013 | $0.00268 |
Grade A, and why
pm-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 7d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Analytics Skill
How this skill behaves (read first)
This is a generative process skill (it plans or performs an analysis, and can critique one). Analytics is where an AI assistant produces confident, wrong conclusions: Claude reports vanity metrics (page views, total signups), treats correlation as causation, reacts to a two-day spike or an n=20 sample as if it were a trend, quotes the average (which hides every interesting subgroup), and stops at "here are the numbers" instead of a decision. A dashboard nobody acts on, or an insight built on a bias, is worse than no analysis.
So this skill gates:
- Establish context — the decision/question this informs, the goal it ladders to, and the data available (these set what to measure and which method).
- Apply the always-true core — question first, actionable metrics, signal vs. noise, segment, quant+qual, end in a recommendation.
- Surface the context-dependent decisions (analysis method, leading vs. lagging, tooling, attribution model, cohort type, retention window) with trade-offs; let the user choose.
Then it hands off to pm-okr-metric-validity-audit (are the chosen metrics valid, not vanity?) and pm-assumption-rigor-audit (do the causal claims and read-outs survive scrutiny?).
Scope: this skill owns the analysis process — what to measure, funnels/cohorts/segments/journeys, reading signal from noise, and the data-to-decision story. It defers the rigorous validity of a metric's definition to pm-okr-metric-validity-audit, the statistics of a controlled change (sample size, significance, guardrails) to pm-experimentation-ab, OKR/KPI artifacts to pm-okrs-kpis, and the discovery research that generates qualitative "why" to pm-discovery.
Step 0 — Establish context before analyzing
Ask if not known; state the assumption if proceeding without an answer:
- What decision or question does this inform? Start from the question, not the data — "why did activation drop?" or "which onboarding step loses users?" An analysis with no decision attached produces noise.
- What goal does it ladder to? Tie the metric to a business/user objective so you measure what matters, not what's convenient to track.
- What data exists, and is it trustworthy? Event coverage, time range, segments available, known tracking gaps. Thin or biased data changes what you can honestly conclude.
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.
- 7d ago First seen · 119 lines · 129 tokens per session scan A a55d44488e96
pm-analytics is a skill published in the GitHub repository Uxcel-Lab/product-skills (10 stars, last pushed 2mo ago), licensed MIT. It adds 129 tokens to every session and 2,681 once invoked, about $0.0006 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
pm-brainstorm
A guided brainstorming workflow for exploring a new product idea before detailed research or requirements work. It collects basic information about the product, users, and problem through staged questions.
pm-priority
A Chinese-language procedure for ranking several product requests when time or resources are limited. It supports scoring or grouping methods such as RICE, KANO, and MoSCoW to decide what should be done first.
pm-proto
A product-prototyping workflow for planning how an application should work and what its screens should contain. It connects product requirements to interface layouts and interactions.
pm-decision
A structured guide for making major business and product choices, such as building, outsourcing, buying, investing, or entering a market.
pm-clarify
A requirements-clarification workflow that turns a rough feature list into specific scenarios, user actions, boundaries, and acceptance checks. Acceptance checks are the conditions used to decide whether the work is complete.
pm-market
A guided market-research workflow for understanding an industry, its competitors, customers, risks, and opportunities. It can use existing product-research documents or ask for basic information first.