agentleFS
DarthJonathanDarthJonathan/guac-skills/skills/make-bot-ui/SKILL.md

make-bot-ui

Skill0 starsChanged 17 days agoMITView on GitHub

Build a UI for an existing user-supplied automation webhook, keeping credentials server-side. Use when the user requests buttons or a dashboard to trigger that webhook.

20 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 19 edited versions we read keep these.

  • 2

    Distinctive

    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:

    Read the Codex runtime adapter once per session before using this skill.

    line 6
  2. Distinctive:

    Verify with a mock or read-only path first.

    line 17

“Common” is measured: kept by at least 6 in 10 of the 19 edited versions of this file we could read. “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

Read the Codex runtime adapter once per session before using this skill. Its tool, model, history, and authorization mappings apply to all linked instructions.

Make a bot UI

Build a small interface for an existing authorized webhook integration.

Codex does not supply an assumed equivalent of Cursor's automation webhook provisioning or SendToUser secret handoff. Do not invent an inbound Codex endpoint or request a secret in the chat. If the user needs a native Codex scheduled task, use the available automation tool instead.

  1. Establish the actual webhook contract, desired actions, authentication mechanism, response shape, and deployment destination from the supplied integration. Inspect the existing project before choosing a stack.
  2. Keep credentials in the server environment or the integration's secure secret mechanism. The browser sends action requests to the local or deployed application server; only that server contacts the webhook. Never include a sender key in source, a client bundle, a URL query, logs, or a screenshot.
  3. Limit actions and validate payloads at the server boundary. Preserve the existing authorization model. Show progress, a concrete result, and useful failure messages. Avoid duplicate submissions where a retry could repeat an effect.
  4. Verify with a mock or read-only path first. Exercise a live side effect only when the user's authorization covers it.
  5. Publish, expose through a tunnel, or configure network access only within the user's requested scope. Give the user a concrete local result and name any missing external endpoint.

Return the working interface, configuration names without their secret values, verification results, and any deployment or integration boundary still awaiting authorization.

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.