transit_skill

This skill routes Transit tickets to the correct workflow by extracting the T-[number], fetching task details, and handing off to the appropriate handler.
  • Python

16

GitHub Stars

1

Bundled Files

2 months ago

Catalog Refreshed

4 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstrat where the catalogue uses aiagentskills.

npx veilstrat add skill arjenschwarz/agentic-coding --skill transit

  • SKILL.md2.3 KB

Overview

This skill routes Transit tickets to the correct workflow based on the ticket reference and task type. It extracts T-[number] references, fetches task details from Transit, and dispatches the task to the appropriate downstream skill or asks clarifying questions when needed.

How this skill works

The skill parses the user's message to find a T-[number] display ID and queries Transit for the matching task. It checks task existence and status, warns if the task is done or abandoned, then routes by the task's type to the corresponding workflow while passing the ticket reference, name, description, and metadata.

When to use it

  • When a user mentions a Transit ticket like T-42 and wants to work on it.
  • When you need to determine whether a ticket is a bug, feature, research task, chore, or documentation item.
  • When you want to hand off a Transit ticket to the correct downstream skill with full context.
  • When task status needs to be checked before proceeding (done/abandoned).

Best practices

  • Always confirm the parsed display ID with the user if multiple T- references are present.
  • If Transit returns no matching task, inform the user and stop; do not guess.
  • If task status is done or abandoned, ask the user whether to continue before routing.
  • For ambiguous types or missing descriptions, ask one concise clarifying question and then route.
  • When handing off, include ticket reference, name, description, and relevant metadata.

Example use cases

  • User: 'Please work on T-42' — Parse T-42, fetch task, and route to fix-bug or creating-spec based on type.
  • User: 'I want to start research for T-128' — Enter planning mode using the research question from the description.
  • User: 'T-77 looks like a chore' — Ask whether it should be treated as a bug fix or feature, then route accordingly.
  • User: 'T-99 has no description' — Ask the user for context and then route once details are provided.

FAQ

The skill asks the user which ticket they want to work on instead of proceeding.

How are tasks handled if their status is done or abandoned?

The skill warns the user that the ticket is marked done or abandoned and asks whether to continue; it stops if the user declines.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational