Skip to content
Get packs

Product And Business Analysis

Turns product or business data into evidence-backed recommendations for a specific decision

Source Download skill
Repository
XiaomiMiMo/MiMo-Code
Stars
13,743
Licence
MIT
Files
2 files

What it does

This skill makes an AI agent approach a product or business question the way an analyst would: first pin down the decision and who will act on it, then gather relevant context, frame specific data questions, run focused quantitative checks against proper baselines, and finish with a recommendation that states its uncertainty. It also tells the agent to check data source reliability and reconcile conflicting sources before drawing conclusions. It relies on several other named skills (for context gathering, KPI design, data quality, notebooks and validation) that must be installed separately to be fully used.

Great for

  • Product managers deciding which opportunity or feature direction to pursue using usage or retention data
  • Business analysts who need a metric-backed recommendation with stated assumptions and caveats
  • Teams with connected warehouses or dashboards who want the agent to verify numbers before presenting them

Skip it if

  • Quick one-off lookups or simple metric questions, since the workflow is designed for decision-level analysis and would be heavyweight
  • Explaining an unexpected metric movement on its own, which the file says is better handled by the metric-diagnostics skill
  • Settings where the agent has no access to real data, because the skill expects live source reads and will stop if a required source is missing

Try asking

  • “Should we prioritize the SMB segment or the enterprise segment next quarter? Use our usage and revenue data to recommend a direction.”
  • “Evaluate whether the new onboarding change actually improved activation, and tell me how confident we can be.”
  • “Size the potential impact of expanding the free tier limit, with the denominator and data gaps stated clearly.”
Step-by-step guide: how to use Product And Business AnalysisInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 2 original files, the MIT licence and an attribution note.

    product-business-analysis.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip product-business-analysis.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip product-business-analysis.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • State the decision, audience and comparison up front so the agent does not drift into broad exploration.
  • Connect the actual data sources the analysis needs; the skill will stop rather than substitute weaker data when a required source is missing.
  • Ask for the notebook or query record if you want to audit how numbers were produced.

What's inside

  • agents/openai.yaml
  • SKILL.md

Redistributed unmodified from XiaomiMiMo/MiMo-Code under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.