capture

Route ideas to bounded contexts and create indexed backlog tasks.

27|6|Updated Apr 24, 2026
One-click install
npx skills add https://github.com/heimeshoff/Agentheim --skill capture-heimeshoff
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: capture
Source: https://github.com/heimeshoff/Agentheim/tree/main/skills/capture-workspace/iteration-1/eval-2-infra-routing/without_skill/project/skills/capture
Command: npx skills add https://github.com/heimeshoff/Agentheim --skill capture-heimeshoff

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Capture offloads ideas into the backlog.

Core Features & Use Cases

  • Route each idea to the best-fit bounded context and create one backlog task per idea.
  • No questions are asked; tasks are indexed for discovery.
  • Supports rapid-entry of multiple ideas.

Quick Start

Provide a brief idea and the system will route it to the best BC and create a backlog task for each idea.

Frequently Asked Questions about capture

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I rapidly capture ideas into a backlog without answering clarifying questions?

You can rapidly capture ideas by providing a brief description, and the system routes each idea to the best-fit bounded context and creates a backlog task automatically without asking questions.

What is the best way to route multiple ideas to bounded contexts for task creation?

Routing multiple ideas to bounded contexts happens automatically during rapid entry; each idea is matched to the best-fit bounded context and generates one indexed backlog task for discovery.

Can I dump a list of unstructured ideas into my backlog and have them indexed automatically?

Yes, you can dump unstructured ideas into your backlog; the system creates one task per idea and writes captured work with index updates to ensure future discovery.

Does this rapid-entry backlog tool support multiple ideas in a single input?

Yes, the rapid-entry feature supports inputting multiple ideas at once, routing each to its best-fit bounded context and creating a separate backlog task for every idea provided.

Why does the backlog task creation process skip clarifying questions?

The backlog task creation process skips clarifying questions to offload ideas into the backlog as fast as possible, prioritizing rapid entry and indexing over upfront requirement gathering.

When should I avoid using a no-questions approach for backlog task creation?

You should avoid this no-questions approach when your ideas require detailed clarification or specific context before task creation, as it prioritizes speed and immediate routing over precision.