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

context-assemble

Skill95 starsChanged 6 days agoMITView on GitHub

Assembles customer, order, loyalty and carrier context, detects record-vs-account contradictions, and selects the resolution path deterministically with the context_assemble engine. Use after inquiry-intake, or on "pull up everything on this order".

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:

    After inquiry-intake in every run.

    line 11
  2. Very specific:

    Run scripts/context_assemble.py --classified classified.json --records records.json --config service-config.json --out assembled.json

    line 15
  3. Distinctive:

    Every context fact cites its extract.

    line 20

≈ “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

Context Assemble

Purpose

One consolidated view + deterministic path selection: contradictions trigger the DNR process (#2.1); money boundaries enforced (#3.1).

When to use

After inquiry-intake in every run.

Inputs

classified.json + records.json (the records extract that ships with the case: OMS order, carrier scans, loyalty) + config/service-config.json.

Steps

  1. Run scripts/context_assemble.py --classified classified.json --records records.json --config service-config.json --out assembled.json
  2. Quote the path and gate arithmetic verbatim (tier and value against the instant-resolution gate). The response never disputes the customer's account - it explains the process and the clock (#2.2).

Output

assembled.json - the {context} hop.

Grounding requirements

Every context fact cites its extract; the path cites the policy config.

Constraints

  • Path selection is engine-only; sympathy, volume or channel pressure never flips dnr_investigation to instant refund.
  • Goodwill credit is out of scope at any tier - propose-for-human at most (#3.1).

Escalation / uncertainty

Contradiction present -> the escalation carries the carrier scan citation for the investigation.

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