agentleFS
Sign inStart free
FracteraFractera/Agentic-Engineering-Infrastructure/.claude/skills/route-to-element/SKILL.md

route-to-element

Skill61 starsChanged 56 days agoMITView on GitHub

Both natures. Hand a request to the element of this node that does it — found by its role — with its agent's Telegram bot or terminal; never do its work yourself. Load it when the person asks for something an element does (sign-in, data, settings, design, a site, a custom element's job), asks who does what, or names an element.

1 other project uses a version of this.

Adopted by

Most recently taken up by

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
  1. Distinctive:

    Every element has its own agent with its own instruction, skills and code.

    line 14

≈ “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

Route a request to its element

Process: both — you change nothing yourself and answer in two or three lines; the first line names the process of the request you pass on.

A hint, not a law: models of late 2026 work worse under rigid step-by-step instructions.

Why

Every element has its own agent with its own instruction, skills and code. That agent knows its element; you know the node. Doing an element's job from here means loading what its agent already has — the person pays twice and the element's code changes without its agent knowing.

How

  1. npm run find -- <the job in plain English words> — the registry's candidates, at most five, each with its role and how to reach its agent (npm run contacts -- <id> — one element again). Never list the whole node: it grows.
  2. Pick the element whose role covers the job — each candidate says why it matched (670-4): does it now — skill X (route the job there); nearest by its AREA (its card confirms → a route its own agent builds there; then npm run role -- <id> --grows "<the job>"); matches only its description (read its card — usually it does not do this job: nobody). Two fit — ask the person one question about how they differ, then record one role for each (npm run role).
  3. Answer with the element and how to reach its agent, as find prints it:

    «Это делает элемент auth — вход и роли для всех элементов. Его агент: Telegram t.me/<bot>, терминал <link>. Там его среда разработки — напишите ему.»

  4. The element has no bot — give its terminal and say a bot can be connected on its page «Messenger → H2A → Telegram».

Not here

  • Nobody in the node fits → skill create-element (the network first, then a new element).
  • The person wants you to do it anyway — say once why the element's agent should do it, then pass it on and tell the person it went there. A job (the element's work, only data changes) → npm run task -- <id> --work [--skill <one of its skills from npm run card>] "<the person's words>": its worker does it, not its builder, and its «done» wakes you with the report (npm run state -- <id>). A change of its code → npm run task -- <id> "<the person's words>" (its builder). --dry shows what would be sent.

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