agentleFS
CharleneTStrainCharleneTStrain/product-ops-skills/skills/data-request-router/SKILL.md

data-request-router

Skill0 starsChanged 17 days agoMITView on GitHub

Turn a vague "can I get a number for X?" into a clear data request — the exact question, the metric and definition, the source, and the right person or dashboard to answer it — and check whether the answer already exists before anyone pulls new data. Use when someone asks for data, a metric, a report, a quick number, or an analysis and it's unclear where it lives or who owns it, or when someone is managing a queue of incoming data requests.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the decision behind the ask is unclear, ask about it first.

    line 33
  2. Distinctive:

    Before routing, look for:

    line 37
  3. Distinctive:

    If something exists, point to it and say how current it is.

    line 42
  4. Distinctive:

    Use the team's actual owners if known.

    line 56
  5. Distinctive:

    Don't run the analysis or estimate the number unless asked.

    line 75

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Data request router

Most data requests are slow not because the data is hard to get, but because the question is unclear, the answer already exists somewhere, or it went to the wrong person. Routing fixes all three before any query is written.

Before you start

If .agents/product-ops-context.md exists (or .claude/product-ops-context.md), read it first. Use the team, owners, tools, meetings, and metric definitions it already has, and only ask for what's missing or specific to this task. If it doesn't exist, go ahead with what you're given, and suggest running product-ops-context once so the next skill doesn't have to ask.

Step 1: Sharpen the question

Turn the ask into a request someone could answer without a follow-up:

FieldWhat to capture
Asked asThe request in the requester's words
Decision it supportsWhat they'll do with the answer; if unknown, ask
Exact questionOne question, in plain words
MetricWhich metric, using the agreed definition (see product-metrics-definitions)
FiltersTime period, segments, plans, regions
ComparisonVersus what: last period, target, another segment
Precision neededBallpark is fine, or must be exact
Needed byDate, and why

"How's adoption?" becomes "What share of accounts on the Business plan used reporting at least once in September, compared with August?"

If the decision behind the ask is unclear, ask about it first. It often changes what data is actually needed.

Step 2: Check if it already exists

Before routing, look for:

  • An existing dashboard or report that answers it
  • A recent analysis, readout, or digest that covered it
  • A metric already defined in the glossary

If something exists, point to it and say how current it is. That's the fastest answer.

Step 3: Route it

Question typeUsually goes to
A number from an existing dashboardSelf-serve: link the dashboard
Product usage or behaviorProduct analytics owner
Revenue, billing, pricingFinance or RevOps
Pipeline or dealsSales ops or RevOps
Support volume or ticketsSupport ops
Survey or feedbackResearch or product ops
A new metric that doesn't exist yetMetric owner to define first, then analytics

Use the team's actual owners if known. Otherwise, name the type of owner and flag it.

Output

# Data request: [short title]
- **Requester:** [name] · **Needed by:** [date]
- **Decision it supports:** [one line]
- **Question:** [exact question]
- **Metric and definition:** [metric] — [definition or link]
- **Filters:** [period, segments]
- **Compare to:** [baseline]
- **Precision:** [ballpark / exact]

**Already answered?** [Yes: link, last updated] / [No]
**Route to:** [person or team] — [why]
**Questions back to requester:** [if any]

Don't run the analysis or estimate the number unless asked. The job here is to get the question to the right place, clearly.

Related skills

  • product-metrics-definitions — check whether a definition already exists
  • kpi-health-check — when the question is really 'is this number off?'

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.