sdd-task-dag

Generates a task-dependency DAG grouping tasks into conflict-free parallel execution waves.

1|Updated Mar 5, 2026
One-click install
npx skills add https://github.com/AlessioScarfone/aine-copilot-plugins --skill sdd-task-dag-alessioscarfone
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: sdd-task-dag
Source: https://github.com/AlessioScarfone/aine-copilot-plugins/tree/main/src/sdd-team/skills/sdd-task-dag
Command: npx skills add https://github.com/AlessioScarfone/aine-copilot-plugins --skill sdd-task-dag-alessioscarfone

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes assets (resource) components.

What problem does it solve? When implementing a spec-driven change with many tasks, running them in parallel risks file conflicts and broken dependencies. This Skill inspects the codebase and tasks.md to produce a conservative dependency graph (task-dag.md) that groups tasks into sequential waves of parallel-safe agent bundles. ## Core Features & Use Cases - Dependency Graph Generation: Reads tasks.md, design.md, and proposal.md, then inspects the codebase to identify which files each task touches and which tasks depend on others. - Wave and Bundle Planning: Assigns tasks to sequential waves and bundles them into agent slots (W1-A, W1-B, ...) where bundles in the same wave share no files and can run in parallel. - Use Case: Before launching the sdd-dev-orchestrator for parallel implementation, run this Skill on a change like "add-auth" to get a task-dag.md showing three waves, max parallelism of two agents, and all file conflicts resolved by serialization. ## Quick Start Ask the AI to build the task DAG for your current change, for example: "Generate the task-dag for the add-auth change so I can plan parallel execution."

Frequently Asked Questions about sdd-task-dag

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

FAQPage Schema
How do I plan parallel task execution for a spec-driven change?▼

Run this Skill on your change to generate task-dag.md, which groups tasks into sequential waves of parallel-safe agent bundles. It inspects the codebase to find file touch points and serializes any tasks that share files or depend on each other.

How are tasks grouped into execution waves and bundles?▼

Tasks with no dependencies and no file conflicts go into Wave 1, and dependent or conflicting tasks go into later waves. Within each wave, tasks sharing a parent group number are bundled together, but bundles that share any file are merged or split across waves.

What inputs does the task DAG generation require?▼

It requires a tasks.md file in the change directory, plus design.md and proposal.md for context. If tasks.md is missing, the Skill stops and tells you to run /sdd-propose first.

Does this Skill run the parallel implementation itself?▼

No, it only generates the execution plan in task-dag.md and does not launch subagents or modify source code. To execute the plan, switch to the sdd-dev-orchestrator agent.

What happens if task-dag.md already exists for a change?▼

The Skill shows the existing DAG and asks whether to regenerate it or use it as-is. It always confirms with the user before overwriting an existing file.