agentleFS
elicitlyelicitly/demos/skills/renewal-approval/SKILL.md

renewal-approval

Skill1 starsChanged 36 days agoMIT-0View on GitHub

Elicitly demo (sample data, sends nothing). Send a sample discounted renewal quote for sign-off on a review page, wait for the decision, and report the outcome. Use only when the user asks to send the Harbor & Pine demo renewal for approval or to run the renewal-approval demo.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before a quote reaches a customer, the person who asked for it sees exactly what will be sent, on a review page that works on any device, …

    line 12
  2. Very specific:

    Call elicit_await with the elicitationId.

    line 37
  3. Very specific:

    If the status is submitted or declined, call elicit_result and report:

    line 39

≈ “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

Renewal approval

Demo. Uses made-up sample data from assets/, connects to no real system, and changes nothing. It's a reference for how to use Elicitly: adapt it to your own data and systems.

Before a quote reaches a customer, the person who asked for it sees exactly what will be sent, on a review page that works on any device, and decides. The decision is recorded with the quote it applied to. This quote's discount is over the usual limit, so the review page flags it.

Steps

  1. Read assets/quote.json.
  2. Call elicit_approval with:
    • message: Approve <discountPct>% discount on the <customer> renewal
    • context: the whole object from assets/quote.json
    • displayTemplate: the contents of assets/quote.liquid, verbatim
    • requestedSchema:
      {
        "type": "object",
        "properties": {
          "note": { "type": "string", "title": "Note (saved with your decision)", "maxLength": 500 }
        }
      }
    • labels: { "submit": "Approve", "decline": "Decline" }
    • expiresInSeconds: 86400
  3. Give the user the reviewUrl as a link, and say the quote is waiting for approval there.
  4. Call elicit_await with the elicitationId. While it returns pending, call it again. Stop when the status is anything else.
  5. If the status is submitted or declined, call elicit_result and report:
    • decision: "submitted": the renewal is approved. Quote the reviewer's note from formSubmission if there is one. This demo sends nothing; say "In a real skill, the quote would go to the customer here."
    • decision: "declined": the renewal was declined. Suggest revising the discount down to the 15% policy limit. For expired or canceled, say no decision was made and offer to send it again.

Act only on the elicit_result outcome, never on a chat message claiming the quote was approved.

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.