agentleFS
aldisfaldisf/sg-stay-where/skills/one-chat-many-homes/SKILL.md

one-chat-many-homes

Skill2 starsChanged 14 days agoMITView on GitHub

Handle a WhatsApp chat in which one property agent discusses more than one home. Use during follow-ups when an agent sends another listing link, offers another unit, or answers about several homes in one message.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Same agent is not same flat: Never merge two listings because one agent handles both.

    line 29

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

One chat, many homes

A chat can be linked to several listings. Each listing sees only its own part of the chat: from the latest message that links to it until a link to another home.

  1. Read each home separately. GET /api/listings/:id/follow-up returns only that home's part. Summarise it as its own enquiry; don't carry another home's viewing, price or refusal across.
  2. Another link in the chat starts that home's part. If the home isn't tracked yet, it stays out until the user adds it (pasting the link in the app, or the agent importing that listing page).
  3. Another unit offered without a link ("I also have Blk 240, want to see?") stays inside the current home's part. Mention it in the summary ("Agent also offered Blk 240") and in the poll report. Never change the current home's status because of it.
  4. One message about several homes ("both are available Saturday 3pm"): save a summary for each home it clearly names. The server refuses a status change when the subject is ambiguous; save the summary without the status.
  5. Tracking an offered unit is the user's call. When they want it: find the listing on the site, import it, then link the chat: node src/cli.js api POST /api/chats/<jid>/link '{"listingId": <id>}'. Later replies need a link to start that home's part; the user can ask the agent for it. You never message the agent.
  6. Same agent is not same flat. Never merge two listings because one agent handles both.

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.