task-start

Create acceptance criteria and verification fixtures before writing implementation code.

Updated Mar 18, 2026
One-click install
npx skills add https://github.com/dmooney/Rundale --skill task-start-dmooney
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: task-start
Source: https://github.com/dmooney/Rundale/tree/main/.agents/skills/task-start
Command: npx skills add https://github.com/dmooney/Rundale --skill task-start-dmooney

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It prevents wasted effort by forcing teams to define acceptance criteria and a verification fixture before any implementation begins, so the final code is judged against observable signals rather than intent.

Core Features & Use Cases

  • Creates a standardized proof bundle: Generates a .proofs/<task-id>/ directory with an acceptance-criteria document and (for larger features) supporting design and plan artifacts.
  • Builds a deterministic verification fixture: Adds a parish/testing/fixtures/play_<task-id>.txt script that makes each criterion visible in the game’s JSON output.
  • Supports depth-first feature decomposition: For non-trivial features, requires a design note and an implementation plan that reference affected subsystems and observable harness signals.

Quick Start

Use the task-start skill with a kebab-case task id to produce .proofs/<task-id>/acceptance-criteria.md and parish/testing/fixtures/play_<task-id>.txt describing done, then stop for human review.

Frequently Asked Questions about task-start

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

FAQPage Schema
How do I define acceptance criteria before writing implementation code?

Defining acceptance criteria before coding involves creating a `.proofs/<task-id>/` bundle with an `acceptance-criteria.md` document and a verification fixture to establish observable signals for expected behavior.

What is a deterministic verification fixture for gameplay testing?

A deterministic verification fixture is a `play_<task-id>.txt` script that makes each acceptance criterion visible in the game's JSON output, ensuring the harness demonstrates expected behavior.

How do I set up CI readiness for game harness features?

CI readiness for game harness features requires creating a proof bundle with explicit acceptance criteria and a deterministic test fixture that produces observable in-game JSON signals before implementation begins.

When do I need a design note and implementation plan for feature decomposition?

Depth-first feature decomposition requires adding a design note and implementation plan under `docs/design/` and `docs/plans/` for non-trivial features, referencing affected subsystems and observable harness signals.

Can I use this coding workflow without prior test fixtures?

No, this coding workflow requires writing the test fixture and acceptance criteria first, stopping for human review before any implementation code is written to prevent wasted effort.

Why define done before writing artifacts in a coding workflow?

Defining done before writing artifacts ensures final code is judged against observable signals rather than intent, preventing wasted effort by forcing teams to establish verification fixtures before implementation begins.