customise-workflow

Configure prd-taskmaster workflow preferences via curated questions written to atlas.json.

593|58|Updated Oct 21, 2025
One-click install
npx skills add https://github.com/anombyte93/prd-taskmaster --skill customise-workflow
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: customise-workflow
Source: https://github.com/anombyte93/prd-taskmaster/tree/main/skills/customise-workflow
Command: npx skills add https://github.com/anombyte93/prd-taskmaster --skill customise-workflow

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Manually editing JSON configuration files to tune how prd-taskmaster behaves is error-prone and tedious. This Skill replaces raw JSON editing with a guided interview: the AI asks curated questions in plain English, validates each answer, and writes the result to .atlas-ai/config/atlas.json so future runs apply your preferences automatically.

Core Features & Use Cases

  • Guided configuration interview: Asks one curated question at a time covering provider, validation strictness, execution mode, template, autonomous behavior, and phase gates, then maps plain-English answers to config keys.
  • Validated, idempotent writes: Every answer is validated via script.py validate-answer before being written, and re-running the skill cleanly updates the existing per-project config.
  • Escape hatch for power users: Settings beyond the curated questions live in .atlas-ai/customizations/, which the skill never overwrites.
  • Use Case: You want prd-taskmaster to default to Gemini for task generation, use lenient PRD validation, and prefer execution mode B. Say "customise workflow", answer three questions, and the config is written and verified.

Quick Start

Ask the AI to customise the prd-taskmaster workflow and answer the curated questions about provider, validation strictness, and execution mode.

Frequently Asked Questions about customise-workflow

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

FAQPage Schema
How do I change prd-taskmaster default settings?

Run the customise-workflow skill and answer its curated questions in plain English. The AI validates each answer and writes your preferences to .atlas-ai/config/atlas.json, which phase skills read at runtime before falling back to documented defaults.

How do I change the default AI provider for task generation?

During the customisation interview, answer the provider question with your choice such as gemini-cli, claude-code, openai, openrouter, or ollama. The skill validates the value and writes it to the provider.main key in atlas.json.

Can I edit the atlas.json config file manually?

The skill is designed so the AI asks questions and writes the config, so manual JSON editing is discouraged. For tweaks beyond the curated questions, place override files in .atlas-ai/customizations/, which the skill never overwrites.

Is the workflow configuration global or per project?

Configuration is per project. The file lives in .atlas-ai/config/atlas.json inside the current project, alongside TaskMaster's .taskmaster/ directory, so different projects can have different preferences.

What happens if a config key is missing or invalid?

Every answer is validated with the script's validate-answer command before writing, so invalid values are never saved. If keys are missing at runtime, phase skills gracefully fall back to documented defaults.

How do I reset prd-taskmaster settings to defaults?

Run the script's reset-config command, which deletes .atlas-ai/config/atlas.json. Future runs then use the documented default behavior until you customise again.