Agent skill · Design & Presentation

routing-card-authoring

Use whenever a build emits or repairs .agentlas/routing-card.json — the shared card contract for the single-agent builder, the team builder, and the packager. States what belongs in every field, which fields the hub can actually match on, and which fields silently break matching when a sentence leaks into them.

Agentlas1,166★ · +196/wk · 1 repos on radarProfile →
claude-codeApache-2.0
Install
npx skills add agentlas-ai/Agentlas-OS --skill routing-card-authoring --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 1
SKILL.md size: 11 KB
Bundled scripts: none
Path: skills/routing-card-authoring/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 1,165
Language: Python
Read our review of the source →

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Routing Card Field Spec — what goes in every field, and where it lands One card, three builders. `10-single-agent-builder`, `20-multi-agent-team-builder` and `30-agentlas-packager` differ in what they assemble, but the routing card is the same artifact with the same rules in all three. This file is the reference they share, and `templates/routing-card.example.json` is a complete card that passes `schemas/routing-card.schema.json`. ## Why the fields behave the way they do Every rule below was measured against the live corpus on 2026-07-30 (492 workforce profiles, 253 stored manifests). The two facts that decide everything else: 1. **Only two columns can be compared between a work order and a card.** `communities` (422 of 492 populated, 105 distinct) and `skills` (492 of 492, 1,969 distinct). Everything else is either declared by almost nobody (`roles` 6, `tools` 10, `knowledge` 0, `forbiddenAuthorities` 0), or declared by everyone with the same value (`runtimes` 14 distinct over 492 profiles, `languages` exactly 2, `modalities` exactly 1) — neither can separate candidates. 2. **The real matching is sentence-to-sentence.** The slot's `task` text is compared semantically against the

What's inside
Steps it walks through
  1. Why the fields behave the way they do
  2. Field table
  3. Identity and display
  4. The sentences that actually win matches
  5. Short-id fields (open semantic concepts — never sentences)
  6. The workforce block — open-world semantic résumé fields
  7. Safety, cost and operations (not matching inputs)
  8. Checklist a builder can run
  9. Verified end to end
More from Agentlas-OS
All skills →
About this skill
What does the routing-card-authoring skill do?

Use whenever a build emits or repairs .agentlas/routing-card.json — the shared card contract for the single-agent builder, the team builder, and the packager. States what belongs in every field, which fields the hub can actually match on, and which fields silently break matching when a sentence leaks into them.

How do I install it?

Run `npx skills add agentlas-ai/Agentlas-OS --skill routing-card-authoring --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From agentlas-ai/Agentlas-OS, a repository with 1,165 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going