Back to skills

Agent Skill

Implement Spec

implement-spec

Implement a specification in code.

MattpocockGeneralShell
github.com/mattpocock/skills/tree/main/skills/in-progress/implement-spec

142K installs

•

mattpocock/skills

•

by Mattpocock

Score

8.7

/ 10

Installs

142K

Repo Stars

269.0K

Last Updated

0d ago

Fresh

Quality Ratio

81%

Description

Verified

Language

Shell

First Published

Aug 2026

Summary

The Implement Spec agent skill orchestrates the complex process of turning a technical specification, defined by a task graph of tickets, into a fully implemented pull request by intelligently managing concurrent subagent activity. This agent skill is invaluable for developers and engineering teams tackling large features or projects that require decomposing a specification into an interconnected task graph and managing concurrent development. It is a skill with 142K installs, indicating significant adoption within the agent skill registry. This agent skill guides the AI to treat tickets as a "task graph" with blocking relationships, identifying a "frontier" of available tasks for subagents. It instructs "implementer subagents" to work concurrently on these tickets in separate worktrees and branches, maximizing parallel execution and merging their progress via a "merger subagent." Communication between subagents is sparse, relying on "context pointers" to the spec, tickets, and commits to prevent redundant information sharing and ensure efficient collaboration as the task frontier evolves.

Skill Definition

You have been provided a spec. This spec should have tickets associated with it, describing how to implement the spec.

The goal is a PR which implements the entire spec on a single branch.

The tickets are not a list of steps. They are a task graph with blocking relationships between them. This means there is always a frontier of tickets which are ready to be grabbed.

Communication to and from subagents should be sparse. Communicate primarily through context pointers: to the spec, tickets, research notes, and previous commits. Don't duplicate information already available via pointers.

Implementer subagents should be run in the background where possible for maximum concurrency.

Steps

  1. Read the spec and tickets. Read enough to understand the task graph.

  2. (optional) Use an exploration subagent to conduct any exploration required by the tickets - relevant codebase files or external documentation. Ensure the exploration subagent can save files - it should save its markdown notes in a directory outside the repo, accessible by all future subagents. This lets implementer subagents focus on implementation rather than exploration.

  3. Create a branch, and a draft PR. The PR should be marked as 'closing' the spec issue and tickets.

  4. Use implementer subagents to implement each ticket. Each implementer subagent should work in its own worktree, on its own branch.

  5. Once an implementer subagent completes, merge its work to the PR branch with a merger subagent.

  6. If this changes the frontier of available tickets, kick off more implementer subagents to work on the new tickets. This allows for maximum concurrency.

  7. Once all tickets are complete, run /code-review on the PR branch. Fix all issues raised by the code review in a single implementer subagent.

  8. Mark the PR as ready for review.

  9. Clean up all implementer subagent worktrees.

How to Use

Use in O-mega

Claude Code

npx skills add mattpocock/skills implement-spec