agentleFS
Sign inStart free
MicrosoftKnown publishermicrosoft/cat-agent-skills/submissions/customer-service-order-support/skills/inquiry-intake/SKILL.md

inquiry-intake

Skill95 starsChanged 6 days agoMITView on GitHub

Takes the customer inquiry from any channel and classifies intent against the taxonomy with the deterministic intent_classify engine. Use when a service inquiry arrives - "where is my order", "it says delivered but I never got it", "can I return this", "is it in stock", "how do I set this up".

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Start of every service run.

    line 11
  2. Very specific:

    Run scripts/intent_classify.py --inquiry inquiry.json --config service-config.json --out classified.json

    line 16
  3. Distinctive:

    No resolution content here.

    line 24

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Inquiry Intake

Purpose

Structured inquiry + deterministic intent (#1.1). DNR outranks generic WISMO when both match - the contradiction path is safety-relevant.

When to use

Start of every service run.

Inputs

Inquiry text verbatim (chat/email/voice transcript), channel, customer id, order reference; the records extract that ships with the case (records.json - OMS order, carrier scans, loyalty); config/service-config.json. Emits the entry hop (schema in contracts/).

Steps

  1. Capture text verbatim; record channel/tone; note explicit asks (refund now, goodwill credit) as flags.
  2. Run scripts/intent_classify.py --inquiry inquiry.json --config service-config.json --out classified.json
  3. Below the confidence floor -> the run is a handoff, never a guessed answer (#1.1).
  4. Intake is a hop, not a stopping point. Continue to context-assemble in the same run; do not pause to ask for records that ship with the case (records.json).

Output

classified.json - the {intent} hop. Hand straight to context-assemble.

Grounding requirements

Intent cites the taxonomy; the customer's words stay verbatim.

Constraints

  • No resolution content here; no promises of any kind at intake.

Escalation / uncertainty

Unclassified or ambiguous -> handoff packet path.

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.

Check your setup, free