agentleFS
Sign inStart free
elicitlyelicitly/demos/skills/release-go-no-go/SKILL.md

release-go-no-go

Skill1 starsChanged 36 days agoMIT-0View on GitHub

Elicitly demo (sample data, deploys nothing). Present a sample release readiness card, then ask the user to confirm before shipping. Use only when the user asks to ship the Brightwater Portal demo release or to run the release-go-no-go demo.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the host can't render MCP Apps, summarize the checks and changes in a few lines instead.

    line 25
  2. Distinctive:

    Never treat a chat reply as the decision in step 4.

    line 38

≈ “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

Release go/no-go

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.

The agent shows what is about to ship, then stops and asks. The question is a real dialog answered by a human, not a "should I continue?" line in chat that the model might answer for itself.

Steps

  1. Read assets/release.json.
  2. Call elicit_display with:
    • title: Release followed by product and version
    • template: the contents of assets/readiness.liquid, verbatim
    • context: the whole object from assets/release.json
    • summary: one sentence with the version, the passing/total checks, and the risk level If the host can't render MCP Apps, summarize the checks and changes in a few lines instead.
  3. Call elicit_confirm with:
    • message: Ship <product> <version> to production?
    • labels: { "ok": "Ship it", "cancel": "Hold" }
  4. Act on the answer, which has three states:
    • confirmed: true: say the release is shipping. (This demo ships nothing; say "In a real skill, the deploy would start here.")
    • confirmed: false: the user chose Hold. Acknowledge it and stop.
    • confirmed: null: no answer (dismissed, timed out, or the host can't show dialogs). Do not ship. Say no decision was recorded and offer to ask again.

Never treat a chat reply as the decision in step 4; only the dialog result counts.

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