analytics skill
Answer questions about project analytics, performance changes, and campaign summaries using data from analytics datamarts.
- GitHub stars
- 6
- Files
- 1
- Last commit
- Nov 10, 2026
- License
- MIT
- Allowed tools
- —
What does the analytics skill do?
analytics is an agent skill. Answer questions about project analytics, performance changes, and campaign summaries using data from analytics datamarts.
Summary generated from the skill's SKILL.md.
About the analytics skill
Retrieving specific figures and performance summaries from analytics datamarts is what this skill enables for project managers and analysts. An agent should load this tool when a user asks for revenue amounts, reasons for metric changes, campaign performance details, or summaries of specific time periods. It produces structured answers that include conclusions, comparison tables, and identified causes based strictly on available data.
To provide accurate responses, the skill relies on tool calls to fetch data and the admin_link tool to generate direct links to reports in the admin menu. It uses a localized wiki to map metric names and report paths to the user's language. This skill is specifically designed for quantitative analysis and should not be used when a user needs to build flows, change mailings, or request lists of individual customers.
What an agent can do with it
- 1Analyze revenue fluctuationsAsk the agent to explain why revenue decreased during a specific period.
- 2Summarize campaign performanceRequest a summary of how a specific mailing or campaign performed.
- 3Generate monthly reportsGet a breakdown of project metrics for the previous month.
- 4Compare period metricsRequest a comparison of figures between two different timeframes using a table.
Written from the skill's SKILL.md. Every use case is checked against a quote from it.
How to install the analytics skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the analytics skill in Plugin
/plugin marketplace add mindbox-cloud/agent-skills /plugin install mindbox@mindbox-cloud-plugins
Install the analytics skill in Claude Code
~/.claude/skills/analytics/SKILL.md
$ npx degit mindbox-cloud/agent-skills/plugins/mindbox/skills/analytics ~/.claude/skills/analyticsInstall the analytics skill in Claude Code (project)
.claude/skills/analytics/SKILL.md
$ npx degit mindbox-cloud/agent-skills/plugins/mindbox/skills/analytics .claude/skills/analyticsInstall the analytics skill in Codex
~/.agents/skills/analytics/SKILL.md
$ npx degit mindbox-cloud/agent-skills/plugins/mindbox/skills/analytics ~/.agents/skills/analyticsInstall the analytics skill in Gemini CLI
~/.gemini/skills/analytics/SKILL.md
$ npx degit mindbox-cloud/agent-skills/plugins/mindbox/skills/analytics ~/.gemini/skills/analyticsInstall the analytics skill in Claude.ai
npx degit mindbox-cloud/agent-skills/plugins/mindbox/skills/analytics analytics && zip -r analytics.zip analytics # claude.ai → Customize → Skills → + → Create skill → Upload a skill → analytics.zip
SKILL.md
View on GitHubAnalytics
Answer a question about one project with figures from its analytics datamarts. What a table holds and how to read it is in its description; the platform rules behind the figures are in the wiki. This file sets the shape of the answer and its limits.
Rules
- Answer the question that was asked — no more. Its size sets the size of the answer; if the user asks for more detail or a particular format, follow the user.
- Every figure comes from a tool call in this conversation. If the data has no answer, say so.
- Before you present a figure, check it: parts add up to the whole, periods are of equal length and complete, values are plausible.
- A cause is a finding only when the data shows it. Look for it in the data first; what you could not check, call possible.
- Say what the figure covers — brand, target action, period — and what it leaves out.
- Use the user's words: metric names as in the interface, report names as in the admin menu in the user's language (the localized wiki index gives the pairs), names of objects instead of keys, and an object's name as a link to its page when a tool gives you one; no SQL, table or column names unless the user asks how it was counted.
Format
Answer in the user's language: conclusion with the figure → what it is made of, as a table when comparing periods or parts → causes, if the user asked why → one next step, if there is an obvious one you can carry out → the report from the admin menu with the same filters, as the last line, if the answer has figures — as a link: the admin address comes from the admin_link tool and the report path from the wiki, with the same filters; without admin_link, by name and filters; never guess the address.
Example:
Mailing revenue for September was 4.2 million, 12% less than in August (brand Main, target action "Orders").
August September Change Bulk email 2.9 million 2.2 million −24% Automated 1.9 million 2.0 million +5% A third fewer bulk emails were sent than in August: 1.2 million against 1.8 million. The largest of them, Autumn sale, brought 0.6 million.
Break it down by week?
Campaigns
Limits
A benchmark or a "good / bad" threshold is either the product's own — from a tool or a table description, such as the email health report — or an outside one with its source named and marked as not the product's data. Without a source you can name, give no number.
Every call
In reason, the source is [analytics] and the version is v1.0.1. Fill it in every call, in this order: [analytics] v1.0.1 | <user's question> | <what this call fetches>.
- User's question: what the user asked in their latest message, close to their wording, in the user's language, up to 300 characters. Leave out names, emails, phone numbers, addresses and customer ids.
- What this call fetches: 5–15 words.
Feedback
When you conclude the user's task cannot be resolved — the data is missing or the tools refused, or the user disputed your result and the cause is in your calculation or was not found — call feedback with type=task_not_resolved once, as soon as you conclude it and before you reply to the user. In the text: what the user asked, what you calculated and why the task stayed unresolved; if the user disputed the result, what they compared it with — the report, the metric label, the period and the number shown there.
If the user's own comparison explains the difference and the user accepts your explanation, or you corrected your error and the user accepted the corrected answer, the task is resolved: do not send it.
An obstacle with a tool — an unclear description, a missing capability, a workaround you had to invent — goes to feedback with type=tool_problem, as the server instructions ask.
If feedback has no type parameter on this connection, send it without one. Do not include secrets or personal data.
Files in this skill
1analytics skill questions
How do I install the analytics skill in Claude Code?
Run npx degit mindbox-cloud/agent-skills/plugins/mindbox/skills/analytics ~/.claude/skills/analytics. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the analytics skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.
When should I use the analytics skill?
Use it when asked for specific figures, explanations for figure changes, campaign or flow performance, or a summary of a specific period.
What should I avoid when using this skill?
Do not use this skill if the user wants to build or change a flow, mailing, or filter, or if they need a list of customers instead of a figure.